DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 9/4/2025 has been entered.
Response to Amendment
Claims 1 and 25-27 are amended and claim 22 is cancelled. Claims 1-21 and 23-27 are pending.
Response to Arguments
Applicant's arguments filed 9/4/2025 have been fully considered.
Regarding the rejections of claims 1 and 25-27, Applicant contends on pages 4-5 of Applicant’s Remarks that the steps of “obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment” and “wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule” cannot be reasonably performed in the mind but instead require using computing components configured in a particular way.
The Examiner acknowledges that the step “providing an output associated with the desired cleaning schedule, wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule” falls outside any judicial exception, such as mental processes. However, as noted in the grounds for rejecting claim 1 under 101, this element represents routine, conventional and high-level data processing activity in the form outputting instructions (data configured for directly or indirectly controlling equipment) having no significant functional relation to the method steps falling within the judicial exception (the manning of determining the desired cleaning schedule) and therefore constituting insignificant post-solution activity that neither integrates the judicial exception into a practical application nor results in the claim as a whole amounting to significantly more than the judicial exception.
The Examiner has reconsidered the characterization of “obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment” as itself falling within the mental processes judicial exception such that the current grounds of rejection treat this element as an additional element. However, and as noted in the Final Office Action dated 6/11/2025 in which an alternative interpretation and treatment for this element was provided, this element represents high-level data collection/gathering having no particularized relation to the portions of the respective claim that constitutes a judicial exception and therefore constitutes extra-solution activity that fails to integrate the judicial exception into a practical application.
Applicant further contends on page 5 of the remarks, in relation to Step 2A Prong 1 analysis, that even if, for the sake of argument, claims 1 and 25-27 are considered to involve an abstract idea these claims do not necessarily recite an abstract idea.
The Examiner submits that the key functional elements of claim 1, including “obtaining historical sensor data,” “pre-processing the obtained historical sensor data by applying engineering metrics to generate the transformed data,” “applying data analytics to the transformed data” “to predict an indicator of fouling,” “predicting the indicator of fouling in the equipment using the obtained operating data,” “obtaining cost data associated with the equipment being analyzed,” and “determining from the prediction and the cost data, a desired cleaning schedule for the equipment” fall within the mental processes judicial exception such that claim 1 (and similarly for claims 25-27) does not merely involve but recites an abstract idea.
Regarding Step 2A Prong 2, Applicant contends on page 5 of the Remarks, that “obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment” and “wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule” clearly tie the claimed methods, computer readable medium, and system to the manner in which data is collected and how the equipment may be operated based on the desired cleaning schedule. In support, Applicant asserts that the use of “one or more” data collection interfaces for obtaining operating data and providing control instructions to operating the equipment implements a practical application of the alleged abstract idea, and should for this reason be considered patent-eligible subject matter. Applicant further contends that from a computer perspective, obtaining the operating data via one or more data collection interfaces improves the functionality of the associated system in general as supported in paragraph [0080].
The Examiner submits that as currently set forth the claims do not require a multi-interface structure/function for obtaining operating data (one or more interfaces may be only a single interface). In this manner, the operating data collection step is recited at a very high level of generality having no particularized functional relation to the method steps falling within the judicial exception such that this element constitutes insignificant extra solution activity that fails to integrate the judicial exception into a practical application.
Regarding Step 2B, Applicant notes on pages 5-6 of the Remarks, that the claim elements must be considered in combination as well as individually when determining whether the claim as a whole amounts to significantly more than a judicial exception.
The Examiner submits that the elements, whether determined to fall within or outside the judicial exception have been considered in combination and appear, in combination to be directed to an abstract idea (the functional steps being performable individually and in combination (e.g., in sequence) as mental processes and/or implemented as mathematical concepts) with the additional with the additional elements constituting insignificant extra solution activity.
In further regard to Step 2B, Applicant notes on page 6 of the Remarks, that claim 27, which includes features appearing to being patentably distinct with respect to the prior arts, includes the previously discussed elements “obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment” and “wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule,” which cannot be considered an abstract idea.
As previous discussed with reference to Step 2A Prong 2, the Examiner acknowledges that these steps are additional elements that do not fall within the judicial exception. However, these elements constitute insignificant extra solution activity as explained in the grounds of rejection and therefore nether integrate the judicial exception into a practical application (Step 2A Prong 2) nor result in the claim as a whole amounting to significantly more than the judicial exception (Step 2B). Furthermore, these elements appear to be generic and well understood as evidenced by the disclosures of Jadhav (US 2022/0083716 A1), Rodin (US 2022/0180329 A1), Shehri (US 2021/0041347 A1), and Victor (US 2018/0283818 A1), such that they do not result in the claim as a whole amounting to significantly more than the judicial exception.
Regarding the rejections of claims 1 and 25-26 under 103, Applicant contends on page 9 of the Remarks that none of the cited references teach or suggest “pre-processing the obtained historical sensor data by applying engineering metric to generate transformed data,” or “applying data analytics to the transformed data to train at least one statistical model to predict an indicator of fouling.” However, Applicant provides no particularized reasons why the current grounds of rejection fail in this regard. Examiner notes that as set forth in the grounds for rejecting claims 1 and 25-26, the combination of Jadhav and Shehri teaches these elements.
On page 9 of the Remarks, Applicant further contends that Jadhav does not teach “wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule.” The Examiner submits, as set forth in the current grounds for rejecting claims 1 and 25-26, that Jadhav teaches “wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule ([0028] and [0031] corrective actions may include heat exchanger process parameters, changes in operation; FIG. 12 blocks 1204, 1206, and 1208, [0058] operation recommendations (instructions) provided to user based on optimal cleaning schedule).”
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-21 and 23-27 are rejected under 35 U.S.C. 101 because the claimed invention in each of these claims is directed to the abstract idea judicial exception without significantly more.
Claim 1, substantially representative also of independent claims 25 and 26, recites:
“[a] method of determining cleaning schedules for equipment comprising fired heaters and/or heat exchangers, comprising:
obtaining historical sensor data;
pre-processing the obtained historical sensor data by applying engineering metrics to generate the transformed data;
applying data analytics to the transformed data to train at least one statistical model to predict an indicator of fouling;
obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment;
predicting the indicator of fouling in the equipment using the obtained operating data and the at least one trained statistical model;
obtaining cost data associated with the equipment being analyzed;
determining from the prediction and the cost data, a desired cleaning schedule for the equipment; and
providing an output associated with the desired cleaning schedule, wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule.”
Claim 27 recites:
“[a] method of detecting cleaning schedules for equipment comprising fired heaters and/or heat exchangers, comprising:
obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment;
determining at least one cleaning detection variable from the operating data;
transforming the at least one cleaning detection variable to a ratio of forward and backwards moving averages of the respective variable;
setting a number of points representing a number of days used in the respective moving average;
determining whether the ratio exceeds a specified threshold, the threshold being adjustable based on at least one sensitivity requirement;
selecting a local maximum within a cluster of the points;
using the local maximum in determining a desired cleaning schedule; and
providing an output associated with the desired cleaning schedule, wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule.
The claim limitations considered to fall within in the abstract idea are highlighted in bold font above and the remaining features are “additional elements.”
Step 1 of the subject matter eligibility analysis entails determining whether the claimed subject matter falls within one of the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: process, machine, manufacture, or composition of matter. Claims 1 and 27 each recite a method and claims 25 and 26 each recites a system and therefore each falls within a statutory category.
Step 2A, Prong One of the analysis entails determining whether the claim recites a judicial exception such as an abstract idea. Under a broadest reasonable interpretation, the highlighted portions of claim 1 fall within the abstract idea judicial exception. Specifically, under the 2019 Revised Patent Subject matter Eligibility Guidance, the highlighted subject matter in claim 1 falls within the mental processes category (including an observation, evaluation, judgment, opinion) MPEP § 2106.04(a)(2). The highlighted portions of claim 27 fall within the mental processes category, except for “transforming the at least one cleaning detection variable to a ratio of forward and backwards moving averages of the respective variable,” which falls within the within the mathematical concepts category (mathematical relationships, mathematical formulas or equations, mathematical calculations). MPEP § 2106.04(a)(2).
Regarding claim 1, the recited functions:
“determining cleaning schedules for equipment comprising fired heaters and/or heat exchangers, comprising:
obtaining historical sensor data;
pre-processing the obtained historical sensor data by applying engineering metrics to generate the transformed data;
applying data analytics to the transformed data” “to predict an indicator of fouling;”
“predicting the indicator of fouling in the equipment using the obtained operating data”
“obtaining cost data associated with the equipment being analyzed;
determining from the prediction and the cost data, a desired cleaning schedule for the equipment,” may be performed as mental processes.
Determining cleaning schedules for equipment comprising fired heaters and/or heat exchangers may be performed via mental processes (e.g., judgment). Obtaining historical sensor data and pre-processing the obtained historical sensor data by applying engineering metrics to generate the transformed data process may be performed via mental processes (e.g., observation of historical sensor data and evaluating based on engineering metrics to select or deduce other data (transformation) based thereon). Applying data analytics to the transformed data to predict an indicator of fouling may be performed via mental processes (e.g., analytic evaluation and judgement). Predicting an indicator of fouling in the equipment using operating data may be performed via mental processes (e.g., evaluation of operating data and judgement to derive a prediction). Obtaining cost data associated with the equipment being analyzed and determining from the prediction and cost data a desired cleaning schedule for the equipment may be performed via mental processes (e.g., observation of cost and prediction data and evaluation and judgment applied to the data to determine a desired cleaning schedule).
Regarding claim 27, the recited functions:
“determining at least one cleaning detection variable from the operating data;
transforming the at least one cleaning detection variable to a ratio of forward and backwards moving averages of the respective variable;
setting a number of points representing a number of days used in the respective moving average;
determining whether the ratio exceeds a specified threshold, the threshold being adjustable based on at least one sensitivity requirement;
selecting a local maximum within a cluster of the points; and
using the local maximum in determining a desired cleaning schedule,”
may be performed as mental processes.
Determining at least one cleaning detection variable from the operating data may be performed via mental processes (e.g., evaluation of operating data to determine via judgement a cleaning detection variable). Setting a number of points representing a number of days used in a respective moving average may be performed via mental processes (e.g., evaluating moving average to determine via judgment the points representing a number of days). Determining whether the ratio exceeds a specified threshold that is adjustable based on at least one sensitivity requirement may be performed via mental processes (e.g., evaluation of ratio information with respect to an adjustable threshold). Selecting a local maximum within a cluster of the points may be performed via mental processes (e.g., mentally deriving, via judgement, a local maximum by evaluating points cluster). Using a local maximum in determining a desired cleaning schedule may also be performed via mental processes (e.g., determining, via judgement, a desired cleaning schedule by evaluating a local maximum data).
The type of high-level information analysis and deduction recited in these elements has been found by the Federal Circuit to constitute patent ineligible matter (see Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016), a claim to "collecting information, analyzing it, and displaying certain results of the collection and analysis," where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind).
Regarding claim 27, the recited function “transforming the at least one cleaning detection variable to a ratio of forward and backwards moving averages of the respective variable” falls within the mathematical concepts category because the transforming is performed via a ratio calculation which constitutes a mathematical calculation (see Applicant’s FIG. 10b).
Step 2A, Prong Two of the analysis entails determining whether the claim includes additional elements that integrate the recited judicial exception into a practical application. “A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, such that the claim is more than a drafting effort designed to monopolize the judicial exception” (MPEP § 2106.04(d)).
MPEP § 2106.04(d) sets forth considerations to be applied in Step 2A, Prong Two for determining whether or not a claim integrates a judicial exception into a practical application. Based on the individual and collective limitations of claim 1 (representative also of claims 25 and 26) and claim 27, and applying a broadest reasonable interpretation, the most applicable of such considerations appear to include: improvements to the functioning of a computer, or to any other technology or technical field (MPEP 2106.05(a)); applying the judicial exception with, or by use of, a particular machine (MPEP 2106.05(b)); and effecting a transformation or reduction of a particular article to a different state or thing (MPEP 2106.05(c)).
Regarding improvements to the functioning of a computer or other technology, none of the “additional elements” in claim 1, individually or in any combination, including “train at least one statistical model,” “obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment,” predicting the indicator of fouling in the equipment using the obtained operating data “and the at least one trained statistical model,” and “providing an output associated with the desired cleaning schedule, wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule” (claims 1 and 27) in any combination appear to integrate the abstract idea in a manner that technologically improves any aspect of a device or system that may be used to implement the highlighted step or a device for implementing the highlighted step such as a generic computer. Instead, “train at least one statistical model” represents routine, conventional data processing activity in terms of generating program instructions (training) for implementing the method steps falling within the judicial exception. The step “obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment,” represents high-level data collection having no particularized relation to the portions of the respective claim that constitutes a judicial exception and therefore constitutes extra-solution activity that fails to integrate the judicial exception into a practical application. Using a trained statistical model for predicting the indicator of fouling represents routine, conventional computing processes in terms of using program instructions to implement the underlying function (prediction) that falls within the judicial exception and therefore constitutes extra solution activity that fails to integrate the judicial exception into a practical application. The step “providing an output associated with the desired cleaning schedule, wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule” represents routine, conventional and high-level data processing activity in the form outputting instructions (data configured for directly or indirectly controlling equipment) having no significant functional relation to the method steps falling within the judicial exception (the manning of determining the desired cleaning schedule) and therefore constituting insignificant post-solution activity that neither integrates the judicial exception into a practical application nor results in the claim as a whole amounting to significantly more than the judicial exception.
Regarding application of the judicial exception with, or by use of, a particular machine, the additional elements “train at least one statistical model” and “providing an output associated with the desired cleaning schedule, wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule” are configured and implemented in a conventional rather than a particularized manner of implementing heat exchanger monitoring. The function “train at least one statistical model” is recited at a high level that provides no indication of the manner in which the model is trained that may have a significant relation to the portions of the claim constituting an abstract idea such that this function constitutes conventional means for providing a processing function (program instructions in the form of the trained model) for implementing the abstract idea.
Regarding a transformation or reduction of a particular article to a different state or thing, claim 1 does not include any such transformation or reduction. Instead, claim 1 as a whole entails receiving input information (i.e., historical sensor data and cost data), applying conventional processing techniques (e.g., statistical modeling including training of the model) to the information to obtain and deduce fouling and scheduling information with the additional elements “train at least one statistical model” (claim 1) and “providing an output associated with the desired cleaning schedule, wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule” (claims 1 and 27) failing to provide a meaningful integration of the abstract idea in an application that transforms an article to a different state. Instead, the additional elements represent extra-solution activity that does not integrate the judicial exception into a practical application. In view of the various considerations encompassed by the Step 2A, Prong Two analysis, claims 1 and 27 do not include additional elements that integrate the recited abstract idea into a practical application.
Therefore, claims 1 and 27 are directed to a judicial exception and requires further analysis under Step 2B.
Regarding application of Step 2B to claims 1 and 27, and as explained in the Step 2A Prong Two analysis, the additional elements constitute extra-solution activity and therefore in addition to failing to integrate the judicial exception into a practical application, also fail to result in the claim as whole amounting to significantly more than the judicial exception. Furthermore, the additional elements, including training a model, “obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment,” and “providing an output associated with the desired cleaning schedule, wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule,” appear to be generic and well understood as evidenced by the disclosures of Jadhav (US 2022/0083716 A1), Rodin (US 2022/0180329 A1), Shehri (US 2021/0041347 A1), and Victor (US 2018/0283818 A1). Jadhav generally teaches training a model (see [0059] disclosing that scheduling modeling may be performed by various machine learning models including deep learning algorithms, reinforcement learning (Examiner notes that a learning algorithm inherently entails a training process), obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment (FIG. 2 digital replica 104 configured to obtain operation data via interfaces (e.g., “Operation Data” within data repository 118); [0030] digital replica 104 receives sensor data from a plurality of sources; [0007], [0037] operations data collected), and providing an output associated with the desired cleaning schedule wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule (FIG. 12 blocks 1204 and 1208, [0058] cleaning schedule information include equipment operation instructions output to an operator). Rodin (US 2022/0180329 A1) discloses a similar modeling/training structure (see [0047]-[0050] disclosing using machine learning methods (inherently entails training) for training a model, and FIG. 2 blocks S206 and S208, [0181] describing selection and application (entails outputting) of cleaning schedule for outputting cleaning schedule). Shehri (US 2021/0041347 A1) also teaches that model training may be applied in relation to monitoring heat exchanger fouling ([0008]-[0009]), and further teaches obtaining, via one or more data collection interfaces, operating data from at least one source associated with the equipment (FIG. 1 infrared camera 120 and historic and synthetic data 150; FIG. 3 Data capturing 310 and data analysis and imaging processing 320). Victor discloses method/system for detecting and correcting for heat exchanger fouling (Abstract) that includes changing equipment operations (process changes or operating conditions) based on a scheduled (desired) maintenance period ([0104] altering operation processor or conditions (inherently requires a change in the control instructions) until a next scheduled maintenance period).
As set forth above, the elements “obtaining historical sensor data” and “obtaining cost data associated with the equipment being analyzed” in claim 1 are found to fall within the mental processes judicial exception. However, the Examiner notes that even if these elements are interpreted more narrowly and as not falling within a judicial exception (i.e., considered an additional element), these functions represent high-level data collection having no particularized relation to the portions of the respective claim that constitutes a judicial exception. Therefore, these functions constitutes extra-solution activity that neither integrates the judicial exception into a practical application nor results in the claim as a whole amounting to significantly more than the judicial exception.
Therefore, the additional elements are insufficient to amount to significantly more than the judicial exception.
Independent claims 1 and 27 are therefore not patent eligible.
Independent claims 25 and 26 include substantially similar elements as claim 1 and are rejected under 101 for the same reasons as for claim 1.
Claims 2-10, 14-20, and 23-24 depending directly or indirectly from claim 1, provide additional features/steps which are part of an expanded algorithm that includes the abstract idea of claim 1 (Step 2A, Prong One). None of dependent claims 2-10, 14-20, and 23-24 recite additional elements that integrate the abstract idea into practical application (Step 2A, Prong Two), and all fail the “significantly more” test under the step 2B for substantially similar reasons as discussed with regards to the independent claims.
Dependent claims 2-10, 14-20, and 23-24 therefore also constitute ineligible subject matter.
Dependent claims 11-13 include further additional elements “wherein the data analytics comprises applying at least one machine learning technique to train the at least one statistical model” for claim 11, “re-training the at least one statistical model using data accumulated since the model was previously trained” for claim 12, and “wherein at least one first statistical model is trained for heat exchangers, and/or at least one second statistical model is trained for fired heaters” for claim 13. Each of these additional elements describes training or re-training a model that implements the abstract idea with no detail about how the training is particularized to enable the model to implement the abstract idea in any particular manner. As a result, each of claims 11-13 recites provisioning a machine learning model via training which essentially entails providing the instructions for performing the abstract idea (e.g., configuring instructions to implement the abstract idea), which constitutes extra-solution activity that neither integrates the abstract idea into a practical application or results in the claim as a whole amounting to significantly more than the abstract idea.
Claims 11-13 are therefore also constitute ineligible subject matter under 101.
Dependent claim 21 recites the additional element “wherein the output comprises a graphical user interface dashboard” which constitutes extra-solution activity (computer implementation of the abstract idea) and is furthermore well-known and conventional such that this element neither integrates the abstract idea into a practical application nor results in the claim as a whole amounting to significantly more than the judicial exception.
Claim 21 therefore also constitutes ineligible subject matter under 101.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 4, 11-13, 23, and 25-26 are rejected under 35 U.S.C. 103 as being unpatentable over Jadhav (US 2022/0083716 A1) in view of Shehri (US 2021/0041347 A1).
As to claim 1, Jadhav teaches “[a] method of determining cleaning schedules for equipment comprising fired heaters and/or heat exchangers (Abstract method performed with respect to heat exchangers; method implemented by FIG. 2 system 100, FIG. 12), comprising:
obtaining historical sensor data (FIG. 2 depicting data repository 118 configured to collect operation data (operation data is historical in terms of being collected in the past); [0007], [0037] operations data and other historical collected);
pre-processing the obtained historical sensor data by applying engineering metrics to generate transformed data (FIG. 2 Data Transformation Unit 120, [0038] received data is pre-processed and transformed using various engineering based metrics including outlier removal, missing data imputation, and synchronization and integration of data);
applying data analytics to the transformed data to” “at least one statistical model to predict an indicator of fouling ([0040]-[0043] operating data applied to heat transfer efficiency model to predict thermal properties of feeds and per FIG. 3 thermal efficiency (fouling indicator), to fouling type prediction model to predict type of fouling, to fouling parameter estimation model to predict fouling coefficients, and to fouling propensity index model for predicting fouling rate and severity with each of the models constituting a statistical model in terms of generating outputs based on particularized types and values of input numeric values as indicated in [0047]);
obtaining, via one or more data collection interfaces, operating data from at least one source (FIG. 2 digital replica 104 configured to obtain operation data via interfaces (e.g., “Operation Data” within data repository 118); [0030] digital replica 104 receives sensor data from a plurality of sources; [0007], [0037] operations data collected) associated with the equipment ([0037]-[0038] describing collection of input data from sources that may be sensors for sensing specific operating conditions (the sensed data is operationally associated with the sensing target(s); [0007] received input data relates to heat exchanger network);
predicting the indicator of fouling in the equipment using the obtained operating data ([0041]-[0043] operating data applied to fouling type prediction model to predict type of fouling, fouling parameter estimation model to predict fouling coefficients, and fouling propensity index model for predicting fouling rate and severity) and the at least one” “statistical model (FIG. 5 heat transfer efficiency model configured to process operating data (e.g., “Temperature measurement of feed-1 at inlet” and “Thermal properties of feed-1”) to determine/predict indicators of fouling such as thermal efficiency, [0046]; FIG. 7 fouling parameter estimation model configured to process operating data (e.g., “flow rate of feed-1” and “heat transfer efficiency”) to predict fouling coefficients, [0048]);
obtaining cost data associated with the equipment being analyzed ([0058] cost parameter data used to determine cleaning schedule (cost parameter data must be in some manner obtained));
determining from the prediction and the cost data, a desired cleaning schedule for the equipment (FIG. 12 blocks 1202 and 1204, [0058] cost data and predicted fouling rate and fouling severity (per FIG. 8 fouling propensity index prediction model determines fouling rate and severity based on operating data (e.g., heat transfer efficiency) and fouling coefficients)); and
providing an output associated with the desired cleaning schedule (FIG. 12 block 1204 generate (output) cleaning schedule and 1208 provide operation recommendations associated with cleaning schedule to user, [0058]), wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule ([0028] and [0031] corrective actions may include heat exchanger process parameters, changes in operation; FIG. 12 blocks 1204, 1206, and 1208, [0058] operation recommendations (instructions) provided to user based on optimal cleaning schedule).
Regarding application of data analytics to the transformed data to “train” at least one statistical model such that the model used for processing operating data to predict the indicator of fouling in the equipment is a “trained” statistical model, Jadhav discloses that one or more of the models may be data driven models, knowledge-based models, and rule-based models which may entail trained models (e.g., machine learning models).
Furthermore, Sheri discloses a method for determining heat exchanger fouling that uses machine learning modelling for determining indications of fouling and explicitly recites the need for training the learning algorithms that may be performed using pre-processed input training data ([0008]-[0009] pre-processing historical fouling data (selective application via quantification of fouling as it relates to thermograms) to train machine learning circuit (model) that is used to identify fouling).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Sheri’s teaching of applying machine learning technique for training (i.e., apply training to machine learning model) a model using pre-processed operation data to generate a trained machine learning model (that in accordance with the scope of Applicant’s specification also constitutes a statistical model) to the method taught by Jadhav which discloses use of various types of modeling for determining/predicting fouling indicators such that the combined method includes applying data analytics to the transformed data to train at least one statistical model to predict an indicator of fouling, and predicting the indicator of fouling in the equipment using the obtained operating data and the at least one trained statistical model.
The motivation would have been to leverage a known modeling technique for determining fouling including selective application of input training data (guided by engineering metrics as taught by each of Jadhav and Shehri) enable dynamically adaptable modeling updates via efficient learning processes as suggested by Shehri.
As to claim 2, the combination of Jadhav and Shehri teaches “[t]he method of claim 1, wherein the desired cleaning schedule is determined as an economic optimum (Jadhav: [0058] various cost data parameters such as cleaning cost and production loss (economics) considered for determining optimal schedule)” by comparing an optimum cleaning time to at least one external factor (Jadhav: FIG. 13 cleaning schedule generation module configured to schedule cleaning (i.e., determine timing of cleaning event(s)) in accordance with multiple external factors such as maintenance planning and unavailability and production loss. Examiner notes that selective determination of a timing for a cleaning event entails an inherent comparison of prospective cleaning times with respect to the external factors that guide the determination).
As to claim 4, the combination of Jadhav and Shehri teaches “[t]he method of claim 2, wherein the desired cleaning schedule is selected as the optimum cleaning time (Jadhav: [0058] various cost data parameters such as cleaning cost and production loss (economics) considered for determining optimal and therefore desired schedule).”
As to claim 11, the combination of Jadhav and Shehri teaches “[t]he method of claim 1, wherein the data analytics comprises applying at least one machine learning technique to train the at least one statistical model (Jadhav: [0059] disclosing that scheduling modeling may be performed by various machine learning models including deep learning algorithms, reinforcement learning. Examiner notes that a learning algorithm entails training in order to learn).”
Furthermore, Sheri discloses a method for determining heat exchanger fouling that uses machine learning modelling and explicitly recites the need for training the learning algorithms ([0009]).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Sheri’s teaching of applying machine learning technique for training (i.e., apply training to machine learning model) a model to the method taught by Jadhav as modified by Shehri to including training a model and using a trained model such that in combination the method includes using machine learning technique to train the statistical model.
The motivation would have been to enable the machine learning algorithms to learn and therefore become more accurate as suggested by Shehri using a known design option for training models.
As to claim 12, the combination of Jadhav and Shehri teaches “[t]he method of claim 11, further comprising re-training the at least one statistical model using data accumulated since the model was previously trained (Shehri: [0009] additional, subsequently obtained data can be used to further train the model over time).”
As to claim 13, the combination of Jadhav and Shehri teaches “[t]he method of claim 11, wherein at least one first statistical model is trained for heat exchangers (Shehri: [0008]-[0010] models generated (includes training) for detecting fouling on different parts of reactor including heat exchanger); , and/or at least one second statistical model is trained for fired heaters.”
As to claim 23, the combination of Jadhav and Shehri teaches “[t]he method of claim 1, further comprising continually collecting raw field data (Jadhav: [0037] sensor data (raw) is collected and accumulated (i.e., conveys ongoing/continuous collection). Examiner notes that the overall process in which the need for cleaning maintenance is monitored during ongoing heat exchanger operations effectively conveys that the underlying data collection is continuous.).”
As to claim 25, Jadhav teaches “[a] non-transitory computer readable medium comprising computer executable instructions (FIGS. 1-2 depicting system 100 for identification and forecasting fouling that includes a one or more computing devices 108; [0032] computing devices may include a computer (inherently includes non-transitory computer readable storage such as memory); [0006]) for determining cleaning schedules for equipment comprising fired heaters and/or heat exchangers (Abstract method performed with respect to heat exchangers; method implemented by FIG. 2 system 100, FIG. 12), the computer executable instructions comprising instructions for:
obtaining historical sensor data (FIG. 2 depicting data repository 118 configured to collect operation data (operation data is historical in terms of being collected in the past); [0007], [0037] operations data and other historical collected);
pre-processing the obtained historical sensor data by applying engineering metrics to generate transformed data (FIG. 2 Data Transformation Unit 120, [0038] received data is pre-processed and transformed using various engineering based metrics including outlier removal, missing data imputation, and synchronization and integration of data);
applying data analytics to the transformed data to” “at least one statistical model to predict an indicator of fouling ([0040]-[0043] operating data applied to heat transfer efficiency model to predict thermal properties of feeds and per FIG. 3 thermal efficiency (fouling indicator), to fouling type prediction model to predict type of fouling, to fouling parameter estimation model to predict fouling coefficients, and to fouling propensity index model for predicting fouling rate and severity with each of the models constituting a statistical model in terms of generating outputs based on particularized types and values of input numeric values as indicated in [0047]);
obtaining, via one or more data collection interfaces, operating data from at least one source (FIG. 2 digital replica 104 configured to obtain operation data via interfaces (e.g., “Operation Data” within data repository 118); [0030] digital replica 104 receives sensor data from a plurality of sources; [0007], [0037] operations data collected) associated with the equipment ([0037]-[0038] describing collection of input data from sources that may be sensors for sensing specific operating conditions (the sensed data is operationally associated with the sensing target(s); [0007] received input data relates to heat exchanger network);
predicting the indicator of fouling in the equipment using the obtained operating data ([0041]-[0043] operating data applied to fouling type prediction model to predict type of fouling, fouling parameter estimation model to predict fouling coefficients, and fouling propensity index model for predicting fouling rate and severity) and the at least one” “statistical model (FIG. 5 heat transfer efficiency model configured to process operating data (e.g., “Temperature measurement of feed-1 at inlet” and “Thermal properties of feed-1”) to determine/predict indicators of fouling such as thermal efficiency, [0046]; FIG. 7 fouling parameter estimation model configured to process operating data (e.g., “flow rate of feed-1” and “heat transfer efficiency”) to predict fouling coefficients, [0048]);
obtaining cost data associated with the equipment being analyzed ([0058] cost parameter data used to determine cleaning schedule (cost parameter data must be in some manner obtained));
determining from the prediction and the cost data, a desired cleaning schedule for the equipment (FIG. 12 blocks 1202 and 1204, [0058] cost data and predicted fouling rate and fouling severity (per FIG. 8 fouling propensity index prediction model determines fouling rate and severity based on operating data (e.g., heat transfer efficiency) and fouling coefficients)); and
providing an output associated with the desired cleaning schedule (FIG. 12 block 1204 generate (output) cleaning schedule and 1208 provide operation recommendations associated with cleaning schedule to user, [0058]), wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule ([0028] and [0031] corrective actions may include heat exchanger process parameters, changes in operation; FIG. 12 blocks 1204, 1206, and 1208, [0058] operation recommendations (instructions) provided to user based on optimal cleaning schedule).
Regarding application of data analytics to the transformed data to “train” at least one statistical model such that the model used for processing operating data to predict the indicator of fouling in the equipment is a “trained” statistical model, Jadhav discloses that one or more of the models may be data driven models, knowledge-based models, and rule-based models which may entail trained models (e.g., machine learning models).
Furthermore, Sheri discloses a method for determining heat exchanger fouling that uses machine learning modelling for determining indications of fouling and explicitly recites the need for training the learning algorithms that may be performed using pre-processed input training data ([0008]-[0009] pre-processing historical fouling data (selective application via quantification of fouling as it relates to thermograms) to train machine learning circuit (model) that is used to identify fouling).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Sheri’s teaching of applying machine learning technique for training (i.e., apply training to machine learning model) a model using pre-processed operation data to generate a trained machine learning model (that in accordance with the scope of Applicant’s specification also constitutes a statistical model) to the apparatus taught by Jadhav which discloses use of various types of modeling for determining/predicting fouling indicators such that the combined method includes applying data analytics to the transformed data to train at least one statistical model to predict an indicator of fouling, and predicting the indicator of fouling in the equipment using the obtained operating data and the at least one trained statistical model.
The motivation would have been to leverage a known modeling technique for determining fouling including selective application of input training data (guided by engineering metrics as taught by each of Jadhav and Shehri) enable dynamically adaptable modeling updates via efficient learning processes as suggested by Shehri.
As to claim 26, Jadhav teaches “[a] system for determining cleaning schedules for equipment comprising fired heaters and/or heat exchangers (Abstract system implements method performed with respect to heat exchangers; FIG. 2 system 100), the system comprising a processor and memory, the memory storing computer executable instructions that, when executed by the processor ([0006] system includes processor and memory configured to execute instructions), cause the system to:
obtain historical sensor data (FIG. 2 depicting data repository 118 configured to collect operation data (operation data is historical in terms of being collected in the past); [0007], [0037] operations data and other historical collected);
pre-process the obtained historical sensor data by applying engineering metrics to generate transformed data (FIG. 2 Data Transformation Unit 120, [0038] received data is pre-processed and transformed using various engineering based metrics including outlier removal, missing data imputation, and synchronization and integration of data);
apply data analytics to the transformed data to” “at least one statistical model to predict an indicator of fouling ([0040]-[0043] operating data applied to heat transfer efficiency model to predict thermal properties of feeds and per FIG. 3 thermal efficiency (fouling indicator), to fouling type prediction model to predict type of fouling, to fouling parameter estimation model to predict fouling coefficients, and to fouling propensity index model for predicting fouling rate and severity with each of the models constituting a statistical model in terms of generating outputs based on particularized types and values of input numeric values as indicated in [0047]);
obtain, via one or more data collection interfaces, operating data from at least one source (FIG. 2 digital replica 104 configured to obtain operation data via interfaces (e.g., “Operation Data” within data repository 118); [0030] digital replica 104 receives sensor data from a plurality of sources; [0007], [0037] operations data collected) associated with the equipment ([0037]-[0038] describing collection of input data from sources that may be sensors for sensing specific operating conditions (the sensed data is operationally associated with the sensing target(s); [0007] received input data relates to heat exchanger network);
predict the indicator of fouling in the equipment using the obtained operating data ([0041]-[0043] operating data applied to fouling type prediction model to predict type of fouling, fouling parameter estimation model to predict fouling coefficients, and fouling propensity index model for predicting fouling rate and severity) and the at least one” “statistical model (FIG. 5 heat transfer efficiency model configured to process operating data (e.g., “Temperature measurement of feed-1 at inlet” and “Thermal properties of feed-1”) to determine/predict indicators of fouling such as thermal efficiency, [0046]; FIG. 7 fouling parameter estimation model configured to process operating data (e.g., “flow rate of feed-1” and “heat transfer efficiency”) to predict fouling coefficients, [0048]);
obtain cost data associated with the equipment being analyzed ([0058] cost parameter data used to determine cleaning schedule (cost parameter data must be in some manner obtained));
determine from the prediction and the cost data, a desired cleaning schedule for the equipment (FIG. 12 blocks 1202 and 1204, [0058] cost data and predicted fouling rate and fouling severity (per FIG. 8 fouling propensity index prediction model determines fouling rate and severity based on operating data (e.g., heat transfer efficiency) and fouling coefficients)); and
provide an output associated with the desired cleaning schedule (FIG. 12 block 1204 generate (output) cleaning schedule and 1208 provide operation recommendations associated with cleaning schedule to user, [0058]), wherein the output comprises control instructions for operating the equipment based on the desired cleaning schedule ([0028] and [0031] corrective actions may include heat exchanger process parameters, changes in operation; FIG. 12 blocks 1204, 1206, and 1208, [0058] operation recommendations (instructions) provided to user based on optimal cleaning schedule).
Regarding application of data analytics to the transformed data to “train” at least one statistical model such that the model used for processing operating data to predict the indicator of fouling in the equipment is a “trained” statistical model, Jadhav discloses that one or more of the models may be data driven models, knowledge-based models, and rule-based models which may entail trained models (e.g., machine learning models).
Furthermore, Sheri discloses a method/system for determining heat exchanger fouling that uses machine learning modelling for determining indications of fouling and explicitly recites the need for training the learning algorithms that may be performed using pre-processed input training data ([0008]-[0009] pre-processing historical fouling data (selective application via quantification of fouling as it relates to thermograms) to train machine learning circuit (model) that is used to identify fouling).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Sheri’s teaching of applying machine learning technique for training (i.e., apply training to machine learning model) a model using pre-processed operation data to generate a trained machine learning model (that in accordance with the scope of Applicant’s specification also constitutes a statistical model) to the system taught by Jadhav which discloses use of various types of modeling for determining/predicting fouling indicators such that the combined method includes applying data analytics to the transformed data to train at least one statistical model to predict an indicator of fouling, and predicting the indicator of fouling in the equipment using the obtained operating data and the at least one trained statistical model.
The motivation would have been to leverage a known modeling technique for determining fouling including selective application of input training data (guided by engineering metrics as taught by each of Jadhav and Shehri) enable dynamically adaptable modeling updates via efficient learning processes as suggested by Shehri.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Jadhav in view of Shehri as applied to claim 2 and in further view of Elbsat (US 2020/0090289 A1).
As to claim 3, the combination of Jadhav and Shehri teaches “[t]he method of claim 2,” but neither Jadhav nor Shehri expressly teaches “wherein the at least one external factor comprises scheduled shut down or maintenance events for the equipment, the desired cleaning schedule being determined according to a comparison of costs associated with running the equipment past the optimum cleaning time with costs associated with adding a shut down event to accommodate the desired cleaning schedule.”
Elbsat discloses a predictive maintenance method for various equipment including exchangers (Abstract; [0056], [0063]) that includes maintenance scheduling that considers scheduled maintenance as a factor in a cost comparison that is made between running equipment past a prospective maintenance time and costs associated with adding a maintenance event to accommodate the prospective maintenance time ([0279] determination of saving loss prior to and after scheduled maintenance activities resulting in an estimated economic loss determination based on whether or not to miss a scheduled maintenance (an optimum maintenance time); [0309]-[0310]).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Elbsat’s teaching of using a cost comparison between performing a scheduled maintenance or delaying the maintenance with maintenance scheduling as an external cost comparison factor to determine a maintenance schedule with the method taught by Jadhav in which the maintenance constitutes cleaning a heat exchanger such that in combination the method includes “wherein the at least one external factor comprises scheduled shut down or maintenance events for the equipment, the desired cleaning schedule being determined according to a comparison of costs associated with running the equipment past the optimum cleaning time with costs associated with adding a shut down event to accommodate the desired cleaning schedule.”
The motivation would have been to ascertain whether or not a current scheduled maintenance/cleaning time is cost effective in order to improve overall economic efficiency of operating and maintaining the equipment as disclosed by Elbsat.
Claims 5, 21, and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Jadhav in view of Shehri as applied to claim 1 and in further view of Rodin (US 2022/0180329 A1).
As to claim 5, the combination of Jadhav and Shehri teaches “[t]he method of claim 1, wherein the equipment comprises at least one heat exchanger (Jadhav: Abstract; [0030]) and wherein determining the desired cleaning schedule comprises predicting an overall heat transfer” [efficiency] “as the indicator of fouling (Jadhav: [0040] FIG. 5 heat transfer efficiency model determines thermal (heat transfer) efficiency, [0046]), calculating a duty value of the heat exchanger (Jadhav: [0039] heat exchanger parameters include determined feed flow rates), and calculating a cost” “associated with operating the heat exchanger (Jadhav: FIG. 13 cost parameters for cleaning, for maintenance planning, for unavailability and production loss, etc.).”
Jadhav teaches does not specify that heat transfer efficiency is determined based on an overall heat transfer coefficient and therefore does not expressly teach that determining a cleaning schedule comprises predicting an “overall heat transfer coefficient.” Furthermore, while Jadhav teaches determining cost efficiency associated with operating the heat exchanger, Jadhav does not expressly teach calculating a “cost curve” associated with operating the heat exchanger.
Rodin discloses a method for determining cleaning schedules (Abstract) that includes determining an overall heat transfer coefficient ([0075] average heat transfer coefficient determined. Overall HTC encompasses average HTC since average HTC is determinative of the HTC over a duty ([0073]-[0074]) of the heat exchanger). Rodin further teaches calculating a cost curve associated with operating the heat exchanger (FIG. 9 depicting bar chart having a curve profile of costs over weeks between cleaning).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Rodin’s teaching of using overall heat transfer coefficient as a parameter for determining cleaning scheduling for a heat exchanger to the method taught by Jadhav as modified by Shehri in which heat exchanger thermal efficiency is broadly utilized to determine scheduling.
The motivation would have been to utilize a parameter that is known to be informative of heat exchanger operation efficiency to more accurately determine the need for cleaning maintenance. As such, and furthermore, the combination would amount to selecting a known design option in terms of cleaning schedule parameter selection to achieve predictable results.
It would further have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Rodin’s teaching of calculating a cost curve associated with heat exchanger operation to the method taught by Jadhav as modified by Shehri such that the combined method further includes calculating a cost curve as part of scheduling cleaning.
The motivation would have been to provide a useful trendline for determining times at which cleanings can be most cost-effectively scheduled.
As to claim 21, the combination of Jadhav and Shehri teaches “[t]he method of claim 1, wherein the output comprises a” “user interface (Jadhav: [0032] I/O interface may include user interface and/or portable computer).”
Neither Jadhav nor Shehri expressly teaches that the output interface is a graphical user interface dashboard.
Rodin discloses a method for determining cleaning schedules (Abstract) that uses an output comprising a graphical user interface dashboard (FIG. 12 output device interface 606, [0194] output device interface 606 may display images generated by the data processing system; FIG. 8 depicting an example dashboard image of fouling function and deposits complexity; [0183] virtual dashboards may be used to output personalized cleaning profile data).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Rodin’s teaching of using a graphical user interface dashboard to display output data with the method taught by Jadhav as modified by Shehri such that the combined method implements a graphical user interface for displaying the output data.
The motivation would have been to provide a user-friendly (combined source in a single screen) output to aid users in evaluating the output data as suggested by Rodin.
As to claim 24, the combination of Jadhav and Shehri teaches “[t]he method of claim 1,” but neither Jadhav nor Shehri appear to teach “wherein a fouling status is compared to a clean state for the equipment.”
Rodin discloses a method for determining cleaning schedules (Abstract) that includes comparing a fouling status to a clean state for equipment ([0076] fouling resistance determined in accordance with difference between clean state and current state).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Rodin’s teaching of comparing a fouling status to an equipment clean state to the method taught by Jadhav as modified by Shehri such that the combined method performs such a comparison.
The motivation would have been to use a verified clean state as a benchmark against which to more accurately ascertain levels of fouling as disclosed by Rodin.
Claims 6-8 are rejected under 35 U.S.C. 103 as being unpatentable over Jadhav in view of Shehri and Rodin as applied to claim 5, and in further view of Eimer (DE 19504325A1).
As to claim 6, the combination of Jadhav, Shehri, and Rodin teaches “[t]he method of claim 5,” and Jadhav and Rodin each teach using a duty value in the form of flow rate (Jadhav: [0039] Rodin: [0073]-[0074]), however neither Jadhav nor Rodin appear to teach “wherein the duty value comprises a cumulative value.”
Eimer discloses a method for determining boiler cleaning scheduling (Abstract) that includes a duty value in the form of a cumulative value (page 4, paragraph beginning with “FIG. 2 shows as a further embodiment” disclosing measuring flow volume such as when the flow rates fluctuate).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Eimer’s teaching of using a cumulative value as a duty metric to the method taught by Jadhav as modified by Shehri and Rodin such that the combined method includes a cumulative value as well as or as an alternative to a rate-base duty value.
The motivation would have been to utilize a duty parameter that conveys information regarding a load on the heat exchanger that is informative as being related to how much fluid has passed through the heat exchanger in order to more accurately determine consequent need for cleaning maintenance as suggested by Eimer.
As to claim 7, the combination of Jadhav, Shehri, Rodin, and Eimer teaches “[t]he method of claim 6, wherein the duty value comprises cumulative flow (Eimer: page 4, paragraph beginning with “FIG. 2 shows as a further embodiment” disclosing measuring flow volume such as when the flow rates fluctuate).”
As to claim 8, the combination of Jadhav, Shehri, Rodin, and Eimer teaches “[t]he method of claim 6,” and Rodin further teaches “wherein the duty value comprises cumulative impurities ([0053]-[0054] accumulation of particle and crystallization fouling determined for flow as part of fouling characterization [0050]).”
In view of the foregoing combinability of Eimer teaching of using a cumulative parameter for duty (claim 6), it would further have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Rodin’s teaching of an accumulated impurities as a duty parameter to the method taught by Jadhav as modified by Shehri, Rodin, and Eimer such that the combined method utilizes cumulative impurities as well as or as an alternative to other duty parameters in determining cleaning scheduling.
The motivation would have been to utilize a duty parameter that conveys information regarding a most significant aspect of heat exchanger load that is therefore particularly informative in terms of determining the timing for heat exchanger cleaning as suggested by Rodin.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Jadhav in view of Shehri as applied to claim 1, and in further view of Ishiyama, E. M., et al. "Scheduling cleaning in a crude oil preheat train subject to fouling: Incorporating desalter control." Applied Thermal Engineering 30.13 (2010): 1852-1862, Qi (US 2019/0331336 A1), and Klatt (US 4,466,383).
As to claim 9, the combination of Jadhav and Shehri teaches “[t]he method of claim 1,” “wherein determining the optimum cleaning schedule comprises predicting a” “temperature as the indicator of fouling (Jadhav: [0026] it is known in the art that temperature may be used as an indicator of fouling; FIG. 8, [0049] predicted feed temperatures used as fouling parameter input to fouling propensity index model), predicting an end-of-run date” “based on the predicted” “temperature (Jadhav: [0054] predictor unit 126 uses fouling propensity index for determining (predicting what is should be) remaining useful life).”
Jadhav does not describe the heat source and therefore does not expressly teach that the heat exchanger train includes “a fired heater.” It is well-known in the art that oil refinery pre-heat trains include a fired heater as well as the network of heat exchangers. For example, Ishiyama discloses a method for scheduling cleaning of heat exchangers (pages 1854-1855, 3.3. Scheduling of cleaning actions) that are part of a preheat train comprising multiple heat exchangers and a fired heater (furnace) (page 1854, Fig. 3).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Ishiyama’s teaching of a preheat train configuration comprising multiple heat exchangers and a fired heater to the method taught by Jadhav as modified by Shehri.
The motivation would have been to provide an overall operational preheat train on which the cleaning scheduling may be performed as suggested by Ishiyama.
None of Jadhav, Shehri, and Ishiyama teaches using tube skin temperature as the fouling parameter such that the combination of Jadhav and Ishiyama does not teach predicting a “tube skin temperature” as the indicator of fouling and predicting an end-of-run for the fired heater based on the predicted “tube skin temperature.”
Qi discloses a method for predicting tube fouling in a fired apparatus (fired heater) (Abstract; [0030]) that uses tube skin temperature as a fouling parameter (Abstract; FIG. 8 blocks 600 and 604; [0044]).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Qi’s teaching of using tube skin temperature as a fouling parameter for equipment that includes a fired heater to the method taught by Jadhav as modified by Shehri and Ishiyama such that that Jadhav’s disclosed fouling parameters include tube skin temperature such that in combination the method includes predicting a “tube skin temperature” as the indicator of fouling and predicting an end-of-run date for the fired heater based on the predicted “tube skin temperature.”
The motivation would have been to include a known parameter for determining fouling of a fired heater/heat exchanger to improve accuracy of fouling detection and monitoring, such as in terms of comprehensive fouling detection, and as such would amount to selecting a known design option to achieve predictable results.
The combination of Jadhav, Shehri, Ishiyama, and Qi does not appear to expressly teach “calculating cumulative production at the end-of-run date to calculate a cost curve.”
Klatt discloses a method for optimizing cleaning scheduling for heat exchangers (Abstract) that includes calculating cumulative production at the end of run date to calculate a cost curve (FIG. 2 depicting cost curve derived from cumulative operation costs (production costs) at times between sootblowing (i.e., time demarcating end-of-runs of boiler); FIGS. 5 and 6 depicting cost curves for operating cycles in which the area under the curves constitutes a cumulative operating/production cost for a cycle, col. 5 lines 23-40).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Klatt’s teaching of using cumulative production (e.g., production losses) over a cycle (at end-of-run) to generate cost curves to the method taught by Jadhav as modified by Shehri, Ishiyama, and Qi such that the combined method includes this type of per-run production and cost function/curve determination.
The motivation would have been to ascertain the per run (e.g., between scheduled cleaning operations) production efficiency to more effectively schedule cleaning operations in a manner that improves the output efficiency of heaters/heat exchangers with respect to cleaning scheduling as suggested by Klatt.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Jadhav in view of Shehri as applied to claim 1, and in further view of Ishiyama, E. M., et al. "Scheduling cleaning in a crude oil preheat train subject to fouling: Incorporating desalter control." Applied Thermal Engineering 30.13 (2010): 1852-1862.
As to claim 10, the combination of Jadhav and Shehri teaches “[t]he method of claim 1, wherein the equipment comprises a heat exchanger train comprising a plurality of heat exchangers (Jadhav: Abstract heat exchangers in refinery; FIG. 2 refinery is oil and gas refinery; [0065]-[0066]).”
Jadhav does not describe the heat source and therefore does not expressly teach that the heat exchanger train includes “a fired heater.” It is well-known in the art that oil refinery pre-heat trains include a fired heater as well as the network of heat exchangers. For example, Ishiyama discloses a method for scheduling cleaning of heat exchangers (pages 1854-1855, 3.3. Scheduling of cleaning actions) that are part of a preheat train comprising multiple heat exchangers and a fired heater (furnace) (page 1854, Fig. 3).
It would have been obvious to one of ordinary skill in the art before the effective filing date, to have applied Ishiyama’s teaching of a preheat train configuration comprising multiple heat exchangers and a fired heater to the method taught by Jadhav as modified by Shehri.
The motivation would have been to provide an overall operational preheat train on which the cleaning scheduling may be performed as suggested by Ishiyama.
Subject Matter Allowable Over Prior Art
Claim 27 would be allowable if amended to overcome the rejection of claim 27 under 101. Claims 14-20 would be allowable if amended to overcome the rejections under 101 and rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is an examiner’s statement of reasons for prior art allowability of claims 14-20 and 27:
The most pertinent prior art is represented by Jadhav (US 2022/0083716 A1), Shehri (US 2021/0041347 A1), and Rodin (US 2022/0180329 A1).
Regarding claim 14, the combination of Jadhav and Shehri teaches or otherwise renders obvious the elements of claim 1 but does not teach,
“transforming the at least one cleaning detection variable to a ratio of forward and backwards moving averages of the respective variable;
setting a number of points representing a number of days used in the respective moving average;
determining whether the ratio exceeds a specified threshold, the threshold being adjustable based on at least one sensitivity requirement;
selecting a local maximum within a cluster of the points; and
using the local maximum in determining the desired cleaning schedule,” taken in combination with the elements of claim 1.
Claim 15 is allowable by virtue of its dependence from claim 14.
Claim 27 includes substantially the same features that distinguish claim 14 from the prior arts and is allowable for the same reasons.
Regarding claim 16, the combination of Jadhav and Shehri teaches or otherwise renders obvious the elements of claim 1 and Rodin teaches “identifying cycles of the equipment (FIG. 10)” and “fitting a combination of historical cycles (FIG. 10).” The prior arts do not fairly disclose or suggest, “using a weighting strategy to apply a higher weight to more recent cycles than older cycles to prioritize fitting more recent data,” taken in combination with the other elements in claim 16 and claim 1 from which claim 16 depends.
Regarding claim 17, Jadhav in combination with Shehri and Rodin teaches the elements of claims 1 and 5 but does not teach “determining an annualized fouling cost from an overall heat transfer coefficient as the indicator of fouling, by: determining a heat duty based on mass and energy balances using a predicted overall heat transfer coefficient, inlet hot and cold side temperatures, respective inlet hot and cold side flowrates, and at least one additional physical property; and adding respective fouling costs based on fuel gas required to compensate for decreasing duty, annualized maintenance cost based on historic cost data, and emission-related costs based on a release rate of the fuel gas,” taken in combination with the elements of claims 1 and 5.
Claim 18 is allowable by virtue of its dependence from claim 17.
Regarding claim 19, the combination of Jadhav and Shehri teaches or otherwise renders obvious the elements of claim 1 but does not teach “coupling a fired heater cost curve with a tube skin temperature curve to calculate a cost per year against a fouling cycle; normalizing costs with respect to time; and predicting an end of run for at least one cleaning opportunity,” taken in combination with the elements of claim 1.
Claim 20 is allowable by virtue of its dependence from claim 19.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW W BACA whose telephone number is (571)272-2507. The examiner can normally be reached Monday - Friday 8:00 am - 5:30 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Catherine T Rastovski can be reached at (571) 270-0349. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MATTHEW W. BACA/Examiner, Art Unit 2863
/Catherine T. Rastovski/Supervisory Primary Examiner, Art Unit 2863
Prosecution Insights