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
Response to Amendment
Applicant’s submission filed 08/21/2025 includes changes to the claims, remarks and arguments related to the previous rejection. The above have been entered and considered. Claims 1-16 & 20-23 are currently pending.
Response to Arguments
With regard to the 101 rejection:
Claims 1, 11 & 12 are amended to add new limitations with other limitations deleted to broaden the claims. The previous 101rejection is moot and a newgrounds for 101 rejection are provided.
With regard to the 112(b) rejection:
Applicant does not present amended language or arguments to rejected Claims 1, 11 & 20 as to what meets the partitioning of a simulation model of the heat exchanger into multiple segments. The segments lack distinct boundaries for claimed matter and therefore the 112(b) rejection of the claims is maintained.
With regard to the 103 rejection:
Applicant has amended Claims 1, 11 & 20 to broaden the claims by removing the following limitations:
each of the multiple segments corresponding to a different one of multiple operating scenarios of the heat exchanger
a value of accumulated fouling at the fouling location based on the classified temperature data and the classified pressure drop data.
Applicant has added new limitations that require additional search and consideration:
classify the temperature data and the pressure drop data into first and second groups, the first group of data corresponding to a first scenario where the fouling location corresponds to a single segment of the simulation model, and the second group of data corresponding to a second scenario where the fouling location corresponds to multiple segments of the simulation model.
train an artificial intelligence model based on the first and second groups of data; and determine the fouling location of the heat exchanger based on the trained artificial intelligence model.
Applicant’s arguments and/or amendments with regard to Claims 1-3 have been considered in light of the previous references. The arguments and amended claims do not overcome the prior art at the time of the filing of the invention. Upon further consideration, a new ground(s) of rejection is made in view of a new combination of the prior references of Lloyd in view of the new reference of Georgin.
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- 16 & 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more in the claims than the abstract idea itself. These Claims are directed to an abstract idea, which have been found ineligible by judicial exception under Supreme Court Cases including Alice Corp. v. CLS Bank International, 573 U.S., 134 S. Ct. 2368 (2014)[hereinafter “Alice Corp.”] and Mayo Collaborative Services v. Prometheus Laboratories, Inc., 56/826 U. S. (2012) [hereinafter “Mayo”]. The Claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, as addressed below.
Eligibility Step 1: The Four Categories of Statutory Subject Matter (MPEP 2106.03).
Applied to the present application, under step 1 of the Guidance analysis, the Claims belong to the statutory class of a process (method of Claims 1-10) and a machine (apparatus of Claims 11-20).
Eligibility Step 2a: Whether a Claim is Directed to a Judicial Exception (MPEP 2106.04).
Step 2a is two prong analysis:
Prong One Asks: Does the claim recite an abstract idea?
Claims 1- 16 & 20 recite an abstract idea that is subject to a judicial exception. Claims 1-20 pertain to a judicial exception such as explained in MPEP 2106.04(a)(2) Concepts The Courts Have Identified As Abstract Ideas. In Applicant' s case the following judicial exception is applied.
MPEP 2106.04(a)(2)(III) "AN IDEA 'OF ITSELF'" This exclusion has recently been reaffirmed by the Supreme Court in the Alice Corp. decision. The application is directed to an Abstract Idea Groupings [R-07.2022].
MENTAL PROCESSES The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. MPEP 2106.04(a)(2).
MATHEMATICAL CONCEPTS The mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. MPEP 2106.04(a)(2).
Independent Claims 1, 11 & 20 recite similar limitations. The following limitations directed to the abstract idea of an anomaly detection of fouling in a shell and tube heat exchanger by identifying abnormal temperature and pressure data that deviates from expected data.
partitioning, by processing circuitry of an apparatus, a simulation model of the heat exchanger into multiple segments (partitioning the areas of the heat exchanger organizing data in support of the abstract ideal is a mental process that can be performed in a human mind).
generating, by the processing circuitry, for each of the multiple operating scenarios, temperature data and pressure drop data from the simulation model of the heat exchanger (collecting data, organizing data and using math to calculate known temperature and pressure math relationships is a mental process that can be performed with the capacity of a human mind).
classifying, by the processing circuitry, the temperature data and the pressure drop data into first and second groups (classifying is an organizing of data and is a mental process that can be performed in a human mind).
the first group of data corresponding to a first scenario where the fouling location corresponds to a single segment of the simulation model (further classifying is an organizing of data and is a mental process that can be performed in a human mind).
the second group of data corresponding to a second scenario where the fouling location corresponds to multiple segments of the simulation mod (further classifying is an organizing of data and is a mental process that can be performed in a human mind).
training, by the processing circuitry, an artificial intelligence model based on the first and second groups of data (processing without a relationship with defined parameters that can have identified complexity for an AI unique solution is merely processing of the data to determine fouling with a general recitation of AI that is not a unique solution).
determining, by the processing circuitry, the fouling location of the heat exchanger based on the trained artificial intelligence model (processing without a relationship with defined parameters that can have identified complexity for an AI unique solution is merely processing of the data to determine abstract idea where the claimed relationships can be performed in the mind).
Claims 1, 11 & 20 recite a method and product of determining a fouling location of a shell and tube heat exchanger using a simulation model of the heat exchanger. The claims are directed to a simulation model organizing and processing using mental processes to determine a diagnosed condition (e.g. fouling location of a shell and tube heat exchanger). The organizing and processing of temperature and pressure drops in different segments are comparison of the known math based thermodynamic relationships between temperature and pressure with mathematical comparisons of the changes in the temperature pressure relationship to determine an abnormality. The details of the thermodynamic mathematic computation are not explicitly claimed but are performable by the human mind with no unique complexity in the temperature and pressure drop comparisons and where no unique parameters or complexities are given that require artificial intelligence to uniquely solve the claimed scope of the abstract idea of determining a fouling location in a shell and tube heat exchanger.
Claims 1, 11 & 20 further recite a concrete element of a processing circuitry which are established elements performing their generic function. See MPEP 2106.05A Limitations that the courts have found not to be enough to qualify as "significantly more" when recited in a claim with a judicial exception.
With regard to the instant case the following similar cases to Applicant' s claimed invention are also directed to organizing, collecting, monitoring, comparing and analyzing data:
collecting, displaying, and manipulating data, Intellectual Ventures I LLC v. Capital One Fin. Corp., 850 F.3d 1332, 1340, 121 USPQ2d 1940, 1947 (Fed. Cir. 2017);
collecting information, analyzing it, and displaying certain results of the collection and analysis, Electric Power Group, LLC v. Alstom, S.A., 830 F.3d 1350, 1351, 119 USPQ2d 1739, 1739 (Fed. Cir. 2016);
creating an index, and using that index to search for and retrieve data, Intellectual Ventures I LLC v. Erie Indem. Co., 850 F.3d 1315, 1327, 121 USPQ2d 1928, 1936 (Fed. Cir. 2017);
organizing information through mathematical correlations, Digitech Image Techs., LLC v. Electronics for Imaging, Inc., 758 F.3d 1344, 1350-51, 111 USPQ2d 1717, 1721 (Fed. Cir. 2014);
And the additional non-precedential case cited in the Subject Matter Eligibility Guidance of court decisions dated March 14, 2018.
collecting, organizing and analyzing sensor data, TDE Petroleum Data Solutions v. AKM Enterprise, 555 Fed. Appx. 950 (Fed. Cir. 2016).
(2) Prong Two Asks: Does the claim recite additional elements that integrate the judicial exception into a practical application?
Claims 2, 4, 6, 10, 12, 14 & 16 reinforce the abstract concept of a Mathematical Concept by further claiming particular algorithms and mathematical comparison.
Claims 3 & 13 cite areas of the heat exchanger to be monitored but there is no particular arrangement to Particular Machine, Particular Transformation or Extra-Solution Activity with the narrowing to a particular area of a shell and tube heat exchanger.
Claims 5, 7-9 & 15 recite additional collection of data used in the determination without further providing extra-solution activity with the added or changed parameters.
Claims 1- 16 & 20 do not recite additional elements that integrate the judicial exception into practical application. The processors and memory are cited at their highest level of established tools to perform their generic functions in support of the abstract concepts of data collection and mental processes performing comparisons using known mentally calculable math correlations to generate anomaly data. There is no improvement to the functioning of a computer or its components or to another technology without reference to what is well-understood, routine, conventional activity 2106.05(d)II. There is no improvement to the functioning of a computer or it' s components or to another technology without reference to what is well-understood, routine, conventional activity.
Claims 21-23 provide a step that results from the determination that is transformative and thereby eligible subject matter.
Eligibility Step 2B: Whether a Claim Amounts to Significantly More (MPEP 2106.05).
The Claims when analyzed as a whole do not recite elements "significantly more" than just the abstract idea itself, and are comparable to items discussed in the cases mentioned above or are well-understood, routine, and conventional within the relevant art without providing elements or steps directed to the following guidance of significantly more.
Claims 1- 16 & 20 as a whole do not confine the claims to a particular useful application of the abstract idea, the claims does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as an ordered combination do not amount to significantly more than the abstract idea (see MPEP 2105.05(II)).
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 1-16 & 20-23 are rejected under 35 U.S.C. 112(a), because the specification, while claiming an artificial intelligence model and determining a fouling location of the heat exchanger based on the trained artificial intelligence model. The written disclosure does not provide any supporting disclosure on a simulation model uniquely configured for AI processing. The disclosure [0008-0009] [0065] [0117] recites a problem to be solved and recites artificial intelligence could be used in finding a fouling condition in a shell and tube heat exchanger. The disclosure does not set (i.e. in the case of k-nearest neighbor the hyper parameters need to be defined, distance metric set dis selected and weight identified). Artificial intelligence require a setting the parameters for a K-Nearest Neighbors (KNN) algorithm involves by selecting appropriate values for key hyper-parameters that influence the model's behavior and performance.
Claims 2, 13 & 19 and its dependent claims are rejected under 35 U.S.C. 112(a), as failing to comply with the scope of enablement requirement. In Applicant' s case the breadth of the claims extends beyond the disclosure of relating a square root dependency of resistance to deriving a splitting frequency response of the mechanical resonator as cited in the specification [0021].
There are many factors to be considered when determining whether there is sufficient evidence to support a determination that a disclosure does not satisfy the enablement requirement and whether any necessary experimentation is “undue.” In this case, the relevant Wand factors Examiner has considered are :
2164.01(a) Undue Experimentation Factors [R-01.2024]
(A) The breadth of the claims;
(B) The nature of the invention;
(C) The state of the prior art;
(D) The level of one of ordinary skill;
(E) The level of predictability in the art;
(F) The amount of direction provided by the inventor;
(G) The existence of working examples; and
(H) The quantity of experimentation needed to make or use the invention based on the content of the disclosure.
The disclosure does not provide additional working examples or indication of any other type of details to create an AI model. The recitation of an AI model without setting the hyper parameters and where applicant has not provided an example of a dataset or a result using a particular AI model. The examples provided by the applicant in figures 3-13 are not unique to an AI modeling but to comparative data processing of temperature vs fouling and pressure vs. fouling. The inventor has reduced to practice at the time deriving a fouling location my comparative analysis to temperatures and pressures obtained at various segments/locations, but support for an enabled AI simulation model as claimed is not supported and the public is have an unreasonable burden to develop and provide the entirety of the claimed model.
Consistent with office policy, Examiner has weighed all the evidence for and against enablement of this invention and has concluded based on guidance provided by the MPEP and case law (including the Wands factors) that there is not enough evidence in favor of the scope of the enablement of this invention.
Applicant may submit factual affidavits under 37 CFR 1.132 or cite references to show what one skilled in the art knew at the time of filing the application. A declaration or affidavit is, itself, evidence that must be considered. The weight to give a declaration or affidavit will depend upon the amount of factual evidence the declaration or affidavit contains to support the conclusion of enablement. In re Buchner, 929 F.2d 660, 661, 18 USPQ2d 1331, 1332 (Fed. Cir. 1991) (“expert' s opinion on the ultimate legal conclusion must be supported by something more than a conclusory statement”); cf. In re Alton, 76 F.3d 1168, 1174, 37 USPQ2d 1578, 1583 (Fed. Cir. 1996) (declarations relating to the written description requirement should have been considered)”.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims
particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 1-16 & 20-23 are rejected under 35 U.S.C. 112(b), as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claims 1, 11 & 20 recite a similar limitation “partitioning a simulation model of the heat exchanger into multiple segments each of the multiple segments corresponding to a different one of multiple operating scenarios of the heat exchanger”, which is unclear as the specification cites the multiple segments are not a partitioning of a software model but instead a partitioning of the monitored heat exchanger into multiple segments where a simulation model simulates operating scenarios of each of the multiple physical segments locations [0014dent] & [0072 with example segments identified as different partitioned parts of the heat exchange].
Claims 3 & 13 recite temperature data and pressure data and two heat exchanger locations a tube side or a shell side of the heat exchanger which is unclear as the locations are segments but not distinctly claimed as the segments of Claim 1. The claimed steps and elements require consistent use and association of the terms for clarity.
Claims 4 & 14 recites the multiple segments corresponds to one different class in the artificial intelligence model, which is unclear as the multiple segments are locations for obtaining the data of pressure and temperature. The data is processed/corresponds by an artificial intelligence model.
Claims 4 & 14 recite a class in the artificial intelligence model without defining what meets “a class” of the artificial intelligence model. It seems Claims 2 & 12 defines types/classes of artificial intelligence and should depend from respective Claims 2 & 12 where the term “class” is introduced
All dependent claims are rejected for their dependence on a rejected base claim.
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 1-16 & 20-22 are rejected under 35 U.S.C. 103 as being unpatentable over Huang (CN 112560359 “Huang”; translation provided for citations) in view of Najjar (US 20200408669: “Najjar”).
PNG
media_image1.png
570
960
media_image1.png
Greyscale
Claim 1. Huang discloses a method of determining a fouling location (Table 2: baffle or heat exchanger tube fouling amounts at location) [0052] of a shell and tube heat exchanger [Abstract: a simulation method of heat transfer characteristic of shell-and-tube heat exchanger under fouling state] (Table 2: monitored locations heat exchanger fluid tubes for tube fluid & shell baffles for shell fluid), the method comprising: partitioning, by processing circuitry [0047] of an apparatus a simulation model [0032: The method of the present invention adopts three-dimensional digital modeling software to establish a three-dimensional geometric model of a shell and tube heat exchanger] of the heat exchanger into multiple segments generating, by the processing circuitry [0047] temperature data and pressure drop data (Fig. 5) from the simulation model of the heat exchanger [0046: generate a three-dimensional model of the flow velocity, temperature, and pressure distribution area inside the tube side and shell side of the shell and tube heat exchanger], the fouling location (Table 2: translation provided below of locations of the baffle and the heat exchanger tube) of the heat exchanger corresponding to a respective segment in each of the multiple operating scenarios (Table 2: translation provided below of locations monitored) & (Fig. 5 Scenarios) and determining (Table 2: baffle or heat exchanger tube fouling amounts at location) [0052] based on the classified temperature data and the classified pressure drop data [0062-0063]. Huang does not explicitly disclose:
classifying, by the processing circuitry, the temperature data and the pressure drop data into first and second groups, the first group of data corresponding to a first scenario where the fouling location corresponds to a single segment of the simulation model, and the second group of data corresponding to a second scenario where the fouling location corresponds to multiple segments of the simulation model; training, by the processing circuitry, an artificial intelligence model based on the first and second groups of data; and determining, by the processing circuitry, the fouling location of the heat exchanger based on the trained artificial intelligence model.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with a diagnosis using a k-Nearest Neighbor (k-NN) algorithm as a classification technique [0028] models created with sensors at location segments sensors A-H listed in 0027 inlet, outlet, etc.]. Najjar further classifying, by the processing circuitry (Fig.5: 500)[0053], the temperature data and the pressure drop data into first and second groups [0021; first 110 and second 120 heat exchanger], the first group of data (110) corresponding to a first scenario where the fouling location corresponds to a single segment of the simulation model [0028 single heat exchanger] and the second group of data and [0132: the fan 147] corresponding to a second scenario [0028] where the fouling location corresponds to multiple segments (Fig. 1 sensor c-h) of the simulation model; training, by the processing circuitry [Fig. 5: 500] an artificial intelligence model based on the first and second groups of data (sensors a-h) [0049]; and determining, by the processing circuitry (500), the fouling location of the heat exchanger (110 & 120) based on the trained artificial intelligence model [0046-0048].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s KNN modeling on a temperature and pressure measurements and scenarios to determine a fouling diagnosis with Huang’s temperature and pressure fouling location diagnosis because KNN processing improves the quality of fouling diagnosis by providing training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claim 2. The method of claim 1. Huang, as modified, does not explicitly disclose:
the artificial intelligence model includes at least one of a k-nearest neighbors algorithm, a decision tree algorithm, or a discriminant algorithm.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with machine learning tools [0014]. Najjar further teaches the artificial intelligence model [0046-0048: Once an optimal sensor set is obtained, different machine learning methods are applied for analysis of sensor data for fouling diagnosis. These methods consist of the feature extraction, at block 315, and the classification operations, at block 320] includes at least one of a k-nearest neighbors algorithm [0048-0049] based on the multiple segments of the simulation model of the heat exchanger [0044: Then, the data Zs.sub.i corresponding to each sensor s.sub.i∈CL, which consists of the data of all classes, are clustered into M clusters using a K-means clustering algorithm, where M is equal to the number of fouling classes].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s machine learning of temperature and pressure measurements and scenarios to determine a fouling diagnosis with Huang’s, as modified, temperature and pressure fouling location diagnosis because machine learning improves the quality of fouling diagnosis by providing training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claim 3. Dependent on the method of claim 1. Huang further discloses the temperature data is for at least one of a tube side or a shell side of the heat exchanger, and the pressure drop data is for the tube side of the heat exchanger [0016: Preferably, the calculation domain described in step S2 is the area of flow velocity, temperature and pressure
distribution inside the tube side and shell side of the shell and tube heat exchanger].
Claim 4. Dependent on the method of claim 1. Huang further teaches each of the multiple segments corresponds to one different class (Fig. 5 Scenarios of different temperature and pressures)
Huang, as modified, does not explicitly disclose:
each of the multiple segments corresponds to one different class in the artificial intelligence model.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with machine learning tools [0014]. Najjar further teaches each of the multiple segments corresponds to one different class in the artificial intelligence model [0044: Then, the data Zs.sub.i corresponding to each sensor s.sub.i∈CL, which consists of the data of all classes, are clustered into M clusters using a K-means clustering algorithm, where M is equal to the number of fouling classes] in the one or more machining learning classification algorithms [0046-0048] in the one or more machining learning classification algorithms. [0046-0048: Once an optimal sensor set is obtained, different machine learning methods are applied for analysis of sensor data for fouling diagnosis. These methods consist of the feature extraction, at block 315, and the classification operations, at block 320].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s machine learning of temperature and pressure measurements and scenarios to determine a fouling diagnosis with Huang’s, as modified, temperature and pressure fouling location diagnosis because machine learning improves the quality of fouling diagnosis by providing training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claim 5. Dependent on the method of claim 1. Huang further discloses the generating includes: changing a tube inner diameter (di) and a heat transfer (λ) coefficient of one of the multiple segments [0051: λ is heat conducting coefficient and inner diameter Di are changeable variables in equation 0050 as shown by variable changes in Table 1] corresponding to the fouling location to generate the value of the accumulated fouling at the fouling location [0051]; and keeping tube inner diameters and heat transfer coefficients of other segments unchanged [0051].
Claim 6. Dependent on the method of claim 1. Huang further discloses the determining further comprises: determining, by the processing circuitry [0047], the fouling location (Table 2: baffle or heat exchanger tube fouling amounts at location) [0052] of the heat exchanger (Fig. 3) [0052] based on features extracted from a dynamic response of the simulation model of the heat exchanger [0046] & [0062-0063].
Claim 7. Dependent on the method of claim 6. Huang, as modified, does not explicitly disclose:
the dynamic response of the simulation model is obtained by inputting a step or sinusoidal form of an input signal that is a gas flow rate, a tube inlet temperature, or a shell inlet temperature.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with machine learning tools [0014]. Najjar further teaches the dynamic response of the simulation model is obtained by inputting a step or sinusoidal form [0038] of an input signal that is a gas flow rate [0014] [0035: Heat exchanger fouling or fouling of the secondary heat exchanger 120 is modeled as a function of the flow impedance (ZC) at the cold-side that increases and in turn reduces the air flow. Equivalently, this lowers the overall heat transfer coefficient and thus lowers the heat transfer and reduces the efficiency of both heat exchanges 110, 120].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s impedance function input with Huang’s, as modified, modeling of fouling location diagnosis because inputting a sinusoidal time series function to a learning process improves the quality of fouling diagnosis by providing time series training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claim 8. Dependent on the method of claim 6. Huang, as modified the features extracted from the dynamic response of the simulation model include at least one of a rate of change [0057-0060: Step 5 Considering the diversity of flow problems in engineering practice and the closedness of numerical calculations, the turbulent kinetic energy k and dissipation rate ε of the standard k-ε turbulence model satisfy the following expressions. YM is the contribution of the pulse expansion to the whole diffusion rate in the non-compressible onflow], a time constant (k)[0060] of the simulation model (Step 5).
Claim 9. Dependent on the method of claim 8. wherein the output signal is a tube outlet temperature [0062: As shown in Figure 5, the temperature at the heat exchanger outlet], a shell outlet temperature, or a tube pressure drop [0046] & [0003].
Claim 10. Dependent on the method of claim 6. Huang, as modified, does not explicitly disclose:
the features extracted from the dynamic response of the simulation model are generated by feeding an entire output signal of the simulation model to a deep learning algorithm.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with machine learning tools [0014]. Najjar further teaches the features extracted from the dynamic response of the simulation model (315) are generated by feeding an entire output signal of the simulation model to a deep learning algorithm (320) [0046: Once an optimal sensor set is obtained, different machine learning methods are applied for analysis of sensor data for fouling diagnosis. These methods consist of the feature extraction, at block 315, and the classification operations, at block 320].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s machine learning of temperature and pressure measurements and scenarios to determine a fouling diagnosis with Huang’s, as modified, temperature and pressure fouling location diagnosis because machine learning improves the quality of fouling diagnosis by providing training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claim 11. Huang discloses an apparatus [0008: Use 3D digital modeling software (e.g. requires apparatus of a processor) to establish a solid domain 3D model of a shell and tube heat exchanger] for determining a fouling location of a shell and tube heat exchanger [Abstract: a simulation method of heat transfer characteristic of shell-and-tube heat exchanger under fouling state] (Table 2: monitored locations heat exchanger fluid tubes for tube fluid & shell baffles for shell fluid), the apparatus comprising processing circuitry [0047] [0008] configured to: partition a simulation model [0032: The method of the present invention adopts three-dimensional digital modeling software to establish a three-dimensional geometric model of a shell and tube heat exchanger]of the heat exchanger into multiple segments (Fig. 5: four scenario segments) (Fig. 5: four scenario segments) [0062-0063: broken down to scenarios at different output temperatures vs fouling]; generate temperature data and pressure drop data from the simulation model of the heat exchanger [0046: generate a three-dimensional model of the flow velocity, temperature, and pressure distribution area inside the tube side and shell side of the shell and tube heat exchanger].
Huang does not explicitly disclose:
classify the temperature data and the pressure drop data into first and second groups, the first group of data corresponding to a first scenario where the fouling location corresponds to a single segment of the simulation model, and the second group of data corresponding to a second scenario where the fouling location corresponds to multiple segments of the simulation model train an artificial intelligence model based on the first and second groups of data; and determine the fouling location of the heat exchanger based on the trained artificial intelligence model.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with a diagnosis using a k-Nearest Neighbor (k-NN) algorithm as a classification technique [0028] models created with sensors at location segments sensors A-H listed in 0027 inlet, outlet, etc.]. Najjar further classifying, by the processing circuitry (Fig.5: 500)[0053], the temperature data and the pressure drop data into first and second groups [0021; first 110 and second 120 heat exchanger], the first group of data (110) corresponding to a first scenario where the fouling location corresponds to a single segment of the simulation model [0028 single heat exchanger] and the second group of data and [0132: the fan 147] corresponding to a second scenario [0028] where the fouling location corresponds to multiple segments (Fig. 1 sensor c-h) of the simulation model; training, by the processing circuitry [Fig. 5: 500] an artificial intelligence model based on the first and second groups of data (sensors a-h) [0049]; and determining, by the processing circuitry (500), the fouling location of the heat exchanger (110 & 120) based on the trained artificial intelligence model [0046-0048].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s KNN modeling on a temperature and pressure measurements and scenarios to determine a fouling diagnosis with Huang’s temperature and pressure fouling location diagnosis because KNN processing improves the quality of fouling diagnosis by providing training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claim 12. Dependent on the apparatus of claim 11. Huang, as modified, does not explicitly disclose:
the artificial intelligence model includes at least one of a k-nearest neighbors algorithm, a decision tree algorithm, or a discriminant algorithm.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with machine learning tools [0014]. Najjar further teaches the artificial intelligence model [0046-0048: Once an optimal sensor set is obtained, different machine learning methods are applied for analysis of sensor data for fouling diagnosis. These methods consist of the feature extraction, at block 315, and the classification operations, at block 320] includes at least one of a k-nearest neighbors algorithm [0048-0049] based on the multiple segments of the simulation model of the heat exchanger [0044: Then, the data Zs.sub.i corresponding to each sensor s.sub.i∈CL, which consists of the data of all classes, are clustered into M clusters using a K-means clustering algorithm, where M is equal to the number of fouling classes].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s machine learning of temperature and pressure measurements and scenarios to determine a fouling diagnosis with Huang’s, as modified, temperature and pressure fouling location diagnosis because machine learning improves the quality of fouling diagnosis by providing training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claim 13. Dependent on the apparatus of claim 11. Huang further discloses the temperature data is for at least one of a tube side or a shell side of the heat exchanger, and the pressure drop data is for the tube side of the heat exchanger [0016: Preferably, the calculation domain described in step S2 is the area of flow velocity, temperature and pressure
distribution inside the tube side and shell side of the shell and tube heat exchanger].
Claim 14. Dependent on the apparatus of claim 11. Huang, as modified, does not explicitly disclose:
each of the multiple segments corresponds to one different class in the artificial intelligence model.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with machine learning tools [0014]. Najjar further teaches each of the multiple segments corresponds to one different class in the artificial intelligence model
[0044: Then, the data Zs.sub.i corresponding to each sensor s.sub.i∈CL, which consists of the data of all classes, are clustered into M clusters using a K-means clustering algorithm, where M is equal to the number of fouling classes] in the one or more machining learning classification algorithms [0046-0048] in the one or more machining learning classification algorithms. [0046-0048: Once an optimal sensor set is obtained, different machine learning methods are applied for analysis of sensor data for fouling diagnosis. These methods consist of the feature extraction, at block 315, and the classification operations, at block 320].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s machine learning of temperature and pressure measurements and scenarios to determine a fouling diagnosis with Huang’s, as modified, temperature and pressure fouling location diagnosis because machine learning improves the quality of fouling diagnosis by providing training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claim 15. Dependent on the apparatus of claim 11. Huang further discloses the processing circuitry [0047] is further configured to: change a tube inner diameter (di) and a heat transfer (λ) coefficient of one of the multiple segments [0051: λ is heat conducting coefficient and inner diameter Di are changeable variables in equation 0050 as shown by variable changes in Table 1] [0051]; and keeping tube inner diameters and heat transfer coefficients of other segments unchanged [0051].
Claim 16. Dependent on the apparatus of claim 11. Huang further discloses the processing circuitry [0047] is further configured to: determine the fouling location of the heat exchanger (Table 2: shell baffles and fluid tubes)[0052] based on features extracted from a dynamic response of the simulation model of the heat exchanger [0052: The equivalent thermal conductivity of the heat exchange tubes and baffles in the fouling state is calculated. According to the heat transfer per unit length of the cylinder and the heat transfer per unit area of the multilayer flat wall, the equivalent thermal conductivity of the heat exchange tubes and baffles of the shell and tube heat exchanger in the fouling state can be solved. The equivalent thermal conductivity of the heat exchange tubes and baffles of the shell and tube heat exchanger in the fouling state (as shown in Table 2) is obtained and used as the material property of the simulation calculation].
Claim 20. Huang discloses a program executable to perform [0008: Use 3D digital modeling software (e.g. requires apparatus of a processor) to establish a solid domain 3D model of a shell and tube heat exchanger]: partitioning a simulation model of a heat exchanger [0032: The method of the present invention adopts three-dimensional digital modeling software to establish a three-dimensional geometric model of a shell and tube heat exchanger] into multiple segments (Fig. 5: four scenario segments), temperature data and pressure drop data [0046] from the simulation model of the heat exchanger [0052] & [0063], the fouling location (Table 2: monitored locations heat exchanger fluid tubes for tube fluid & shell baffles for shell fluid)[0052], of the heat exchanger (Fig. 3) corresponding to a respective segment in each of the multiple operating scenarios (Fig. 6: for each scenario) [0063: By analyzing the regular characteristics of the internal flow field temperature of the shell and tube heat exchanger as the fouling thickness changes, combined with the tube and shell flow field temperature cloud diagrams, we can provide effective reference and reference for fouling heat exchangers. If necessary, the temperature change of a certain point can be retrieved at any time in the post-processing module, or monitoring of a certain point can be set up during the calculation process to achieve real-time monitoring of the point source, thereby improving the pertinence and accuracy of the result analysis].
Huang does not explicitly disclose:
a non-transitory computer-readable storage medium storing a program executable by at least one processor that is configured for classifying the temperature data and the pressure drop data into first and second groups, the first group of data corresponding to a first scenario where a fouling location corresponds to a single segment of the simulation model, and the second group of data corresponding to a second scenario where the fouling location corresponds to multiple segments of the simulation model training an artificial intelligence model based on the first and second groups of data; and determining the fouling location of the heat exchanger based on the trained artificial intelligence model.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with machine learning tools [0014]. Najjar further teaches a non-transitory computer-readable storage medium (503) storing a program [0060: The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of embodiments herein] executable by at least one processor (501)[0055] & [0065] that is configured for classifying, by the processing circuitry (Fig.5: 500)[0053], the temperature data and the pressure drop data into first and second groups [0021; first 110 and second 120 heat exchanger], the first group of data (110) corresponding to a first scenario where the fouling location corresponds to a single segment of the simulation model [0028 single heat exchanger] and the second group of data and [0132: the fan 147] corresponding to a second scenario [0028] where the fouling location corresponds to multiple segments (Fig. 1 sensor c-h) of the simulation model; training, by the processing circuitry [Fig. 5: 500] an artificial intelligence model based on the first and second groups of data (sensors a-h) [0049]; and determining, by the processing circuitry (500), the fouling location of the heat exchanger (110 & 120) based on the trained artificial intelligence model [0046-0048].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s KNN modeling on a temperature and pressure measurements and scenarios to determine a fouling diagnosis with Huang’s temperature and pressure fouling location diagnosis because KNN processing improves the quality of fouling diagnosis by providing training of classifiers indicative of a plurality of fouling conditions associated with the heat exchanger [0005 Najjar].
Claims 21-22. Dependent on the method of claim 1. Huang, as modified, does not explicitly disclose:
repairing the heat exchange based on the determined fouling location of the heat exchanger the repairing includes removing fouling of the heat exchanger based on the determined fouling location.
Najjar teaches detecting fouling provide limited efficiency and accuracy due to the large amount of data and limited analysis capabilities, that utilizes algorithms of optimal sensor selection and fouling diagnosis in conjunction with machine learning tools [0014]. Najjar further teaches repairing the heat exchange based on the determined fouling location of the heat exchanger [0035].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Najjar’s maintenance schedule to correct fouling when a fouling condition and level is determined with Huang’s, as modified, fouling determination of a heat exchanger because time efficient removal of the fouling substance improves system reliability and maintainability [Najjar 0035].
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Huang in view of Najjar in further view of Sheptunov (US 20220412677: “Sheptunov”).
Sheptunov teaches a method to clean heat exchanger systems by determining a fouling level of a heat exchanger system based on measured performance parameters of the heat exchanger system. Sheptunov further teaches the repairing [0030] is performed while the heat exchanger remains in operation [0141].
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to use Sheptunov’s operational cleaning of a fouled heat exchanger once a fouling condition is determined with Huang’s, as modified, fouled heat exchanger determination because a cleaning schedule and method provide minimized overall
operational cost and system downtime improving system reliability and cost efficiency [Sheptunov Abstract].
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Monica S Young whose telephone number is (303)297-4785.
The examiner can normally be reached M-F 08:30-05:30 MST. 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 Au