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 .
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 17-32 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim(s) recite(s) the abstract idea of a mathematical algorithm for ascertaining the health of a pump (i.e., use of the recited estimation model and damage relevance model).
This judicial exception is not integrated into a practical application because no improvement to the underlying pump is achieved through the performance of the algorithm.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the recitation of the evaluation unit, database, machine learning, and training datasets amounts to the recitation of general-purpose computer elements in the performance of the mathematical algorithm and do not serve to amount to the recitation of significantly more than the abstract idea itself (see Alice Corp. v. CLS Bank International, 573 U.S. 208 (2014)). The recitation of generating a recommendation associated with a maintenance measure does not serve to amount to significantly more than the recitation of the abstract idea itself because such a step amounts to the extension of the algorithm through performance of a mental activity step, because no specific action is required to be performed in response to the recommendation, and because the recommendation itself is generic and non-specific.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 17-23 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Hu et al., A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics, Sensors, 2013 [hereinafter “Hu”].
Regarding Claim 17, Hu discloses a method for evaluating a necessary maintenance measure of a machine [Abstract – “Oil sand pumps are widely used in the mining industry for the delivery of mixtures of abrasive solids and liquids. Because they operate under highly adverse conditions, these pumps usually experience significant wear. Consequently, equipment owners are quite often forced to invest substantially in system maintenance to avoid unscheduled downtime. In this study, an approach combining relevance vector machines (RVMs) with a sum of two exponential functions was developed to predict the remaining useful life (RUL) of field pump impellers.”], comprising:
determining one or more influencing variables relevant to wear or damage of a machine component [Abstract – “To handle field vibration data, a novel feature extracting process was proposed to arrive at a feature varying with the development of damage in the pump impellers. A case study involving two field datasets demonstrated the effectiveness of the developed method. Compared with standalone exponential fitting, the proposed RVM-based model was much better able to predict the remaining useful life of pump impellers.”];
transmitting the one or more influencing variables to an evaluation unit; receiving the one or more influencing variables by way of the evaluation unit [Section 3.1. Data Collection – “Field data were collected from the inlet and outlet of slurry pumps operating in an oil sand mine. Vibration signals using the same sampling frequency rate (51.2 kHz) were obtained from four accelerometers mounted at four different pump locations. These four accelerometers were named as casing 1, casing 2, casing 3, and casing 4, respectively, in Figure 2. Data collection began immediately after all of the components inside the pump had been renewed. It was continued intermittently for around three months with one sampling per hour until the pump’s impeller wore out sufficiently to need replacement. In total, the pump was subjected to 904 measurement hours. The increased vibration levels in certain components of the pump indicated the level of degradation of the pumps, so the vibration signals could be used to monitor the health of the pump system. Data cleaning was done by manually removing outliers exceeding a predefined threshold.”];
ascertaining a risk of failure and/or a likelihood of failure of at least one machine component and/or of the machine by way of an estimation model to which the one or more influencing variables are supplied as input variables [Page 12666 – “Section 3 presents a prediction of the deterioration trend and RUL in a field oil sand pump derived from vibration-based degradation signals.”Section 3.4. RVM Learning Process and Model Fitting – “In contrast, in this study, instead of failure thresholds, alert thresholds for pump impellers, beyond which alarms of the pump health are issued and the pump impellers may fail, were set on the basis of our empirical model and pump degradation trend.”]; and
generating a recommendation associated with a maintenance measure by way of the evaluation unit on the basis of the ascertained risk of failure and/or the likelihood of failure, wherein the machine is pump [Page 12665 – “In the oil-mining sector, equipment owners need to be aware when their pumps require an overhaul or when the related pump components will shortly need to be replaced to avoid unplanned pump downtime. To reduce potential costs, it is of great practical importance to have available a method to monitor the condition of the pump that is capable of determining when it should be overhauled or replaced, or how long its useful life is expected to be.”Section 3.4. RVM Learning Process and Model Fitting – “In contrast, in this study, instead of failure thresholds, alert thresholds for pump impellers, beyond which alarms of the pump health are issued and the pump impellers may fail, were set on the basis of our empirical model and pump degradation trend.” One having ordinary skill in the art would have understood the alarm to indicate the need to perform pump maintenance.].
Regarding Claim 18, Hu discloses that the evaluation unit ascertains the likelihood of failure of the machine from likelihoods of failure of relevant components of the machine [Section 3.4. RVM Learning Process and Model Fitting – “In contrast, in this study, instead of failure thresholds, alert thresholds for pump impellers, beyond which alarms of the pump health are issued and the pump impellers may fail, were set on the basis of our empirical model and pump degradation trend.”].
Regarding Claim 19, Hu discloses that the estimation model comprises a damage relevance model that describes a relevance of the one or more influencing variables on possible damage and/or wear and enables an estimate of current advancement of wear and/or degree of damage of a component and/or the machine [3.4. RVM Learning Process and Model Fitting – “The pairs of feature data {STDr, xr} associated with the sparse dataset were labeled as Relevance Vectors (RVs) [33].”See Fig. 7(b) and Page 12676 – “The future evolution of degradation was predicted by extrapolating the fitted model along the inspection file number and the degradation trajectories were traced up to a pre-defined failure threshold; thus simultaneously the mean values of the remaining useful life (RUL) were obtained.”].
Regarding Claim 20, Hu discloses that the damage relevance model of the evaluation unit is based on a machine learning algorithm to which data about a performed maintenance measure of the machine/of a machine component are provided as training datasets via an input in addition to damage-relevant influencing variables [Section 3.1. Data Collection – “Field data were collected from the inlet and outlet of slurry pumps operating in an oil sand mine. Vibration signals using the same sampling frequency rate (51.2 kHz) were obtained from four accelerometers mounted at four different pump locations. These four accelerometers were named as casing 1, casing 2, casing 3, and casing 4, respectively, in Figure 2. Data collection began immediately after all of the components inside the pump had been renewed.”3.4. RVM Learning Process and Model Fitting – “The RVM learning process was performed on the pair of vectors [z,x] , where the input vector x was constructed from successive inspection file numbers. The target vector z was constructed by generating the corresponding random numbers that follow the Gaussian distribution with mean values equal to a serial of STD values and variance values equal to a certain pre-defined value. The detailed flowchart for the RUL estimation is shown in Figure 7a. At each inspection file number xj , j = 1,..., J , the target values z {z1, z2, ... , zj} indicating the pump degradation information were assumed to be known up to xj. To train the RVM model, a Gaussian kernel was used as the mapping feature space and the value of kernel width was determined using a one-dimensional search method from 30 to 80 with a step length of 0.5 with a view to obtaining the optimized RVM training process with the smallest root mean square error (RMS).”].
Regarding Claim 21, Hu discloses that one training dataset comprises a likelihood of failure and/or risk of failure for one or more components and/or the machine as estimated by a member of maintenance staff when assessing the machine and/or the component [3.4. RVM Learning Process and Model Fitting – “The future evolution of degradation was predicted by extrapolating the fitted model along the inspection file number and the degradation trajectories were traced up to a pre-defined failure threshold; thus simultaneously the mean values of the remaining useful life (RUL) were obtained. … In conventional practice, the failure thresholds are set by the users on the basis of heuristically determined safe operational limits.”].
Regarding Claim 22, Hu discloses that a correction factor is describable as a time-dependent function, and the correction factor decreases over time [See the confidence bounds of Fig. 7.Page 12676 – “The correspondence variance vector, {σ1 , σ2, ..., σr} of the predictors associated with the selected RVs can be calculated by Equations (13) and (14). Then the sum of two exponential functions was used to fit the RUL confidence interval curves based on the vector {σ*,x*}. The future evolution of RUL confidence interval was predicted by extrapolating the fitted model for the RUL confidence interval along the inspection file number. In this study, the lower and upper RUL confidence bounds RULl(xj) and RULu(xj) were estimated by the “two sigma” rule, i.e., a 95.45% confidence level.”].
Regarding Claim 23, Hu discloses that the training datasets are stored in a database and are retrievable by the evaluation unit or the damage relevance model when required [Section 3.1. Data Collection – “Field data were collected from the inlet and outlet of slurry pumps operating in an oil sand mine. Vibration signals using the same sampling frequency rate (51.2 kHz) were obtained from four accelerometers mounted at four different pump locations. These four accelerometers were named as casing 1, casing 2, casing 3, and casing 4, respectively, in Figure 2. Data collection began immediately after all of the components inside the pump had been renewed. It was continued intermittently for around three months with one sampling per hour until the pump’s impeller wore out sufficiently to need replacement. In total, the pump was subjected to 904 measurement hours. The increased vibration levels in certain components of the pump indicated the level of degradation of the pumps, so the vibration signals could be used to monitor the health of the pump system. Data cleaning was done by manually removing outliers exceeding a predefined threshold.”3.4. RVM Learning Process and Model Fitting – “The RVM learning process was performed on the pair of vectors [z,x] , where the input vector x was constructed from successive inspection file numbers. The target vector z was constructed by generating the corresponding random numbers that follow the Gaussian distribution with mean values equal to a serial of STD values and variance values equal to a certain pre-defined value. The detailed flowchart for the RUL estimation is shown in Figure 7a. At each inspection file number xj , j = 1,..., J , the target values z {z1, z2, ... , zj} indicating the pump degradation information were assumed to be known up to xj. To train the RVM model, a Gaussian kernel was used as the mapping feature space and the value of kernel width was determined using a one-dimensional search method from 30 to 80 with a step length of 0.5 with a view to obtaining the optimized RVM training process with the smallest root mean square error (RMS).”].
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.
Claim(s) 24-32 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hu et al., A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics, Sensors, 2013 and Sun et al., Composite-Graph-Based Sparse Subspace Clustering for Machine Fault Diagnosis 2020, IEEE, 5.1.2020 [hereinafter “Sun”].
Regarding Claim 24, Hu fails to disclose that the training datasets are stored in the database for different machines and components, and the different machines and/or components are combined to form different clusters, and a similarity between the different machines and/or components and/or a similarity between their relevant influencing variables and/or the similarity between their machine application are taken into consideration as criteria for clustering.
However, Sun discloses the use of dataset clustering in order to distinguish between datasets corresponding to different device components in order to assess component states [See section V. Case Studies (C). Comparison]. It would have been obvious to use such an approach when interpreting device data in order to effectively determine the state of a particular device component.
Regarding Claim 25, Hu fails to disclose that the damage relevance model for the model training accesses the training datasets of at least the majority of the machines and/or components of a cluster to which the machine currently under consideration is assigned.
However, Sun discloses the use of dataset clustering in order to distinguish between datasets corresponding to different device components in order to assess component states [See section V. Case Studies (C). Comparison]. It would have been obvious to access an appropriate dataset when interpreting device data in order to effectively determine the state of a particular device component.
Regarding Claim 26, the combination would disclose that the damage relevance model is reset after machine maintenance has been performed and/or after a failure of the machine or of a component of the machine and then retrained with all training datasets available for the machine or the component in the assigned machine and/or component cluster [Section 3.1. Data Collection of Hu – “Data collection began immediately after all of the components inside the pump had been renewed.].
Regarding Claim 27, Hu discloses that at least one influencing variable characterizes the loading duration of a machine component or of the machine and/or the operating point of the machine and/or the operating time/downtime of the machine/component and/or a switching frequency of the machine and/or component and/or an ambient or medium temperature of the machine [Abstract – “To handle field vibration data, a novel feature extracting process was proposed to arrive at a feature varying with the development of damage in the pump impellers. A case study involving two field datasets demonstrated the effectiveness of the developed method. Compared with standalone exponential fitting, the proposed RVM-based model was much better able to predict the remaining useful life of pump impellers.”].
Regarding Claim 28, Hu discloses that the evaluation unit, rather than supplying a time-dependent influencing variable, supplies an influencing variable integrated over time to the damage relevance model as an input variable [Page 12673 – “the energy V(T ) was calculated by integrating the frequency within the narrow spectrum band”].
Regarding Claim 29, Hu discloses that one or more influencing variables are acquired during the machine uptime online [Section 3.1. Data Collection – “Field data were collected from the inlet and outlet of slurry pumps operating in an oil sand mine. Vibration signals using the same sampling frequency rate (51.2 kHz) were obtained from four accelerometers mounted at four different pump locations. These four accelerometers were named as casing 1, casing 2, casing 3, and casing 4, respectively, in Figure 2. Data collection began immediately after all of the components inside the pump had been renewed. It was continued intermittently for around three months with one sampling per hour until the pump’s impeller wore out sufficiently to need replacement. In total, the pump was subjected to 904 measurement hours. The increased vibration levels in certain components of the pump indicated the level of degradation of the pumps, so the vibration signals could be used to monitor the health of the pump system. Data cleaning was done by manually removing outliers exceeding a predefined threshold.”].
Regarding Claim 30, Hu discloses that the machine or a separate measuring unit ascertain one or more influencing variables of the machine through a one-off measurement or estimate, in connection with further characteristic information about the one or more influencing variables [Section 3.1. Data Collection – “Field data were collected from the inlet and outlet of slurry pumps operating in an oil sand mine. Vibration signals using the same sampling frequency rate (51.2 kHz) were obtained from four accelerometers mounted at four different pump locations. These four accelerometers were named as casing 1, casing 2, casing 3, and casing 4, respectively, in Figure 2. Data collection began immediately after all of the components inside the pump had been renewed. It was continued intermittently for around three months with one sampling per hour until the pump’s impeller wore out sufficiently to need replacement. In total, the pump was subjected to 904 measurement hours. The increased vibration levels in certain components of the pump indicated the level of degradation of the pumps, so the vibration signals could be used to monitor the health of the pump system. Data cleaning was done by manually removing outliers exceeding a predefined threshold.”].
Regarding Claim 31, Hu discloses that the generation of a recommendation for a maintenance measure takes into consideration a flexibly definable risk tolerance value [Section 3.4. RVM Learning Process and Model Fitting – “In contrast, in this study, instead of failure thresholds, alert thresholds for pump impellers, beyond which alarms of the pump health are issued and the pump impellers may fail, were set on the basis of our empirical model and pump degradation trend.”].
Regarding Claim 32, the combination would disclose a system comprising: an evaluation unit; one or more machines to be monitored; a database configured to store training datasets, wherein the evaluation unit contains a program the instructions of which, when executed, bring about the method as claimed in claim 31 [Section 3.1. Data Collection of Hu – “Field data were collected from the inlet and outlet of slurry pumps operating in an oil sand mine. Vibration signals using the same sampling frequency rate (51.2 kHz) were obtained from four accelerometers mounted at four different pump locations. These four accelerometers were named as casing 1, casing 2, casing 3, and casing 4, respectively, in Figure 2. Data collection began immediately after all of the components inside the pump had been renewed. It was continued intermittently for around three months with one sampling per hour until the pump’s impeller wore out sufficiently to need replacement. In total, the pump was subjected to 904 measurement hours. The increased vibration levels in certain components of the pump indicated the level of degradation of the pumps, so the vibration signals could be used to monitor the health of the pump system. Data cleaning was done by manually removing outliers exceeding a predefined threshold.”].
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Kale et al., Machine Learning Based Dynamic Cause Maps for Condition Monitoring and Life Estimation, IEEE, 2018
Pennel et al., Detecting Failures and Optimizing Performance in Artificial Lift Using Machine Learning Models, SPE, 2018
US 20210048809 A1 – MULTI TASK LEARNING WITH INCOMPLETE LABELS FOR PREDICTIVE MAINTENANCE
US 20150148919 A1 – METHOD AND APPARATUS FOR ARTIFICIALLY INTELLIGENT MODEL-BASED CONTROL OF DYNAMIC PROCESSES USING PROBABILISTIC AGENTS
US 20200134510 A1 – ITERATIVE CLUSTERING FOR MACHINE LEARNING MODEL BUILDING
US 20180197106 A1 – TRAINING DATA SET DETERMINATION
US 20210199110 A1 – SYSTEMS AND METHODS FOR FLUID END EARLY FAILURE PREDICTION
US 20210304059 A1 – METHOD FOR SELECTING DATASETS FOR UPDATING AN ARTIFICIAL INTELLIGENCE MODULE
US 20220075704 A1 – PERFORM PREEMPTIVE IDENTIFICATION AND REDUCTION OF RISK OF FAILURE IN COMPUTATIONAL SYSTEMS BY TRAINING A MACHINE LEARNING MODULE
US 20220024474 A1 – COMPUTER-IMPLEMENTED METHOD FOR MACHINE LEARNING FOR OPERATING A VEHICLE COMPONENT, AND METHOD FOR OPERATING A VEHICLE COMPONENT
US 20200265331 A1 – SYSTEM FOR PREDICTING EQUIPMENT FAILURE EVENTS AND OPTIMIZING MANUFACTURING OPERATIONS
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KYLE ROBERT QUIGLEY whose telephone number is (313)446-4879. The examiner can normally be reached 11AM-9PM EST.
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, Arleen Vazquez can be reached at (571) 272-2619. 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.
/KYLE R QUIGLEY/Primary Examiner, Art Unit 2857