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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/01/2025 was considered by the examiner.
Response to Amendment
Applicant has submitted the following:
Claims 12-15, 17-18, and 20-21 are pending examination;
Claims 1-11 remain cancelled;
Claims 16 and 19 are newly cancelled;
Claims 12-15, and 17 are newly amended.
Response to Arguments
Applicant's arguments filed 12/01/2025 have been fully considered but they are not persuasive.
Applicant has amended claims 12, 17, and cancelled claim 19. The rejection of claim 12, 17, and 19 under 35 USC 112, and the objection to claim 17, is withdrawn.
Applicant argues that newly amended independent claims 12 and 17 involves “a transformation or reduction of data” and therefore is patentable.
Examiner respectfully disagrees. The amended independent claims amounts to mental processes and/or mathematical calculation. The transformation or reduction of data is not a transformation of a particular article into a different state (MPEP 2106.05(c): “For data, mere "manipulation of basic mathematical constructs [i.e.,] the paradigmatic ‘abstract idea,’" has not been deemed a transformation.”). (see detailed action under claim rejections 35 USC 101, below).
Applicant argues that the prior art does not teach all of the limitations of the recited claims. Specifically, Applicant argues that none of the prior art teaches the newly amended limitations of independent claim 12:
“determining a time interval between an issued warning and an occurrence of a first fault after the start time, wherein the time interval is selected based on the first type and of a second type and wherein different first and second types define different time intervals”; and
“determining most probable technical root causes of the failure or fault by correlating the determined time intervals with the predefined cause categories”
Further, Applicant argues that none of the prior art teaches the newly amended limitations of independent claim 17:
“determining a time interval between an issued warning and an occurrence of a first fault after the start time, wherein the time interval is selected based on the first type and of a second type and wherein different first and second types define different time intervals”; and
“calculating probabilities of the determined technical root causes and associating the probabilities with the fault sources”
Regarding claim 12, previously cited Wang teaches an analogous method of predicting failure of components, comprising:
determining a time interval between an issued warning and an occurrence of a first fault after the start time ([0176] lines 1-7, “the longitudinal event and alarm pattern extraction module 1312 extracts information from the event and alarm log for a first time period, the alarm metadata for the same first time period, weather turbine failure data for the same first time period, and cohorts determined by the WT cohort for model development module 1314 in generating the feature matrix.”), wherein the time interval is selected (Fig. 9, steps 906 and 914; [0134] lines 1-3, “In step 914, the trigger module 512 may compare the output of the selected failure prediction model to a threshold to determine if trigger conditions are satisfied 914.”, lines 8-18, “There may be different trigger thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. In various embodiments, there may be different trigger thresholds depending on the amount of damage that may be caused to the asset by failure, other assets by failure, the electrical grid, infrastructure, property and/or life. There may be different trigger thresholds based on the selected model (e.g., based on sensitivity, accuracy, amount of lead time, predicted time of failure, and/or the like).”) based on the first type and of a second type and wherein different first and second types define different time intervals ([0121] “The trigger module 516 may establish thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. Each threshold may be compared to an output of one or more selected models. Thresholds may be established based on the performance of the selected model in order to provide an alarm based on likelihood (e.g., confidence) of prediction, seriousness of fault, seriousness of potential effect of the fault (e.g., infrastructure or life threatened), lead time of fault, and/or the like”.); and
determining most probable technical root causes of the failure or fault by correlating the determined time intervals with the predefined cause categories ([0042] “Each model may be evaluated to determine accuracy of the model and the length of time prior to predicted failure at the desired level of accuracy. As such, the component failure prediction system 104 may be used to generate and evaluate multiple models using the same historical sensor data but each with different lengths of time prior to predicted failure in order to identify at least one model with an acceptable accuracy at an acceptable prediction time before component failure is expected to occur.”; [0202] lines 4-9, “the report and alert generation module 518 provides different views including risk factors for forecasting. The report and alert generation module 518 may also allow a customizable view of event patterns to assist in making decisions to correct a root problem (e.g., predicted failure), and improve uptime and energy throughput.”; [0200] lines 1-3, “FIGS. 22 and 23 may be used for an end user to facility root cause analysis which may be useful for prescription analytics.”). (See detailed action under 35 USC 103, below).
Regarding claim 17, previously cited Spiro teaches an analogous method of determining faults, comprising:
calculating probabilities of the determined technical root causes and associating the probabilities with the fault sources ([0074] lines 1-, “[0074] In examples described herein, data fusion system 1 can allow a user, such as an engineer or mechanic, to analyse information and identify underlying trends, patterns, behaviours and/or precursors which allow the engineer or mechanic to make more informed decisions. Such information can allow an engineer or mechanic to determine the most effective maintenance to perform on a machine. Additionally, when a fault or anomaly has developed in a complex machine, an engineer or mechanic may use the data fusion system 1 to obtain information about a root cause of an anomaly or fault.”; [0026] “The risk model may be a machine learning model configured to receive the statistical metrics and log metrics as inputs, and to output fault probabilities corresponding to one or more fault types occurring in the first machine within a second period.”; [0154] lines 9-14, “A first type of weighted average risk model 6 uses weights in the form of probabilities of a fault developing to calculate an risk scores in the form of estimated probabilities of a corresponding fault type occurring in an associated machine 15, sub-system 18 of the machine, or a group of sub-systems 18.”).
Further, previously cited Wang teaches an analogous method of predicting failure of components, comprising:
determining a time interval between an issued warning and an occurrence of a first fault after the start time ([0176] lines 1-7, “the longitudinal event and alarm pattern extraction module 1312 extracts information from the event and alarm log for a first time period, the alarm metadata for the same first time period, weather turbine failure data for the same first time period, and cohorts determined by the WT cohort for model development module 1314 in generating the feature matrix.”), wherein the time interval is selected (Fig. 9, steps 906 and 914; [0134] lines 1-3, “In step 914, the trigger module 512 may compare the output of the selected failure prediction model to a threshold to determine if trigger conditions are satisfied 914.”, lines 8-18, “There may be different trigger thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. In various embodiments, there may be different trigger thresholds depending on the amount of damage that may be caused to the asset by failure, other assets by failure, the electrical grid, infrastructure, property and/or life. There may be different trigger thresholds based on the selected model (e.g., based on sensitivity, accuracy, amount of lead time, predicted time of failure, and/or the like).”) based on the first type and of a second type and wherein different first and second types define different time intervals ([0121] “The trigger module 516 may establish thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. Each threshold may be compared to an output of one or more selected models. Thresholds may be established based on the performance of the selected model in order to provide an alarm based on likelihood (e.g., confidence) of prediction, seriousness of fault, seriousness of potential effect of the fault (e.g., infrastructure or life threatened), lead time of fault, and/or the like”.) (See detailed action under 35 USC 103, below).
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 12-15, 17-8, and 20-21 are rejected under 35 U.S.C. 101 because the claimed invention in each of these claims is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Specifically, representative Claim 12 recites:
“A method for event monitoring in a converter, comprising:
recording in a database temporal information relating to messages pertaining to a fault or a warning for a predetermined time period after a start time,
evaluating the messages for a combination of faults or warnings of at least a first type and of a second type, wherein the first fault type or warning type depends on a type of the converter, and the second fault type or warning type comprises user-defined faults and warnings,
determining a time interval between an issued warning and an occurrence of a first fault after the start time, wherein the time interval is selected based on the first type and of a second type and wherein different first and second types define different time intervals
training a machine learning algorithm and categorizing with the trained learning algorithm fault events into predefined cause categories associated with different time intervals, and
calculating probabilities of the determined technical root causes and associated the probabilities with the fault sources.”
The claim limitations considered to fall within in the abstract idea are highlighted in bold font above; 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. Claim 12 recites a process and is therefore 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 portion of claim 12 comprises process steps that fall within the abstract idea judicial exception. Specifically, under the 2019 Revised Patent Subject matter Eligibility Guidance, the highlighted subject matter falls within the mental processes category.
Individually and collectively, the steps:
“recording in a database temporal information”;
“evaluating the messages for a combination of faults or warnings of at least a first type and of a second type”;
“determining a time interval between an issued warning and an occurrence of a first fault after the start time”;
“training a machine learning algorithm”;
“categorizing with the trained algorithm fault events into predefined cause categories”;
“training the artificial intelligence to indicate one or more fault sources”; and
“calculating probabilities of the determined technical root causes and associated the probabilities with the fault sources”
may be performed as mental processes and/or mathematical calculations. Recording in a database is collecting information, which may be performed as mental processes. Evaluating the messages, determining a time interval, and categorizing the fault events each are analyzing information, which may be performed as mental processes. Training a machine learning and training the artificial intelligence algorithm each are, under broadest reasonable interpretation, analysis, which may be performed as mental processes, and/or mathematical operations. Calculating probabilities is a mathematical calculation.
Similar limitations comprise the mental processes type abstract idea recited by independent claim 17.
Step 2A, Prong Two of the analysis entails determining whether a claim includes additional elements that integrate the recited judicial exception (e.g., abstract idea) into a practical application. In view of the various considerations encompassed by the Step 2A, Prong Two analysis, claim 1 does not include additional elements that integrate the recited abstract idea into a practical application. Based on the individual and collective limitations of claim 1, applying a broadest reasonable interpretation, the most significant 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 any combination appear to integrate the abstract idea to technologically improve any aspect of a system that may be used to implement the highlighted steps such a generic computer. Any alleged improvement would be an improvement in the steps which may be performed as mental processes and/or mathematical calculations, and are not patent eligible (MPEP 2106.05(a).II “However, it is important to keep in mind that an improvement in the abstract idea itself (e.g. a recited fundamental economic concept) is not an improvement in technology.”.)
Regarding application of the judicial exception with, or by use of, a particular machine, none of the additional elements in any combination amount to a particular machine. Additional elements including “a converter” is recited generically.
Regarding effectuation of a transformation or reduction of a particular article to a different state or thing, the claim includes no such transformation or reduction. Instead, the claim as a whole entails collecting information, performing analysis, and performing mathematical calculations.
Similar analysis applies to independent claim 17.
The above additional elements, considered individually and in combination with the claim elements reciting an abstract idea do not reflect an improvement to other technology or technical field, and, therefore, do not integrate the judicial exception into a practical application. Therefore, the claims are directed to a judicial exception and require further analysis under Step 2B.
Regarding Step 2B, independent claims 12 and 17, the additional limitation of Generating user defined messages is considered extra solution activity and does not amount to significantly more than the judicial exception.
Independent claims 12 and 17 are therefore not patent eligible.
Dependent claims 13-15, 18, and 20-21 provide additional features/steps which are part of an expanded process that includes the abstract idea of the independent claims (Step 2A, Prong One). None of dependent claims13-15, 18, and 20-21 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 the same reasons as discussed with regards to the independent claims.
The dependent claims 13-15, 18, and 20-21 therefore are also ineligible subject matter.
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) 12-15, 17-18, and 20-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kinomura (US 20200169205 A1, previously cited) in view of Spiro et al. (US 20190287014 A1, previously cited) and Wang et al. (US 20200201950 A1, previously cited).
Regarding claim 12, Kinomura teaches A method for event monitoring (Abstract, abnormality detection unit 120) in a converter (power conversion device 100 and power conversion unit 110), comprising:
recording in a database ([0061] “The data storage unit 145 stores a set of log data of combination of a value of the first index and a value of the second index. The data storage unit 145 stores log data under the scan control as one set (hereinafter, referred to as “scan data”). Hereinafter, one set of scan data is referred to as a “scan data set”.”) temporal information relating to messages pertaining to a fault or a warning ([0096]-[0098] “X[k]: Latest value of third index”, “X[k−1]: Value of third index obtained immediately before”, “X[k−2]: Value of third index obtained two times before”) for a predetermined time period after a start time ([0037] “A second abnormality detection unit 160 detects an abnormality in the controlled object 10 based on a relation between a present value of a third index associated with a condition of the motor 12 driving the controlled object 10 and a trend value derived from past values of the third index acquired during a period from a predetermined time before to a time of acquisition of the present value of the third index.”; [0180] “When the determination result in operation S76 is “there is no abnormality”, the second abnormality detection unit 160 returns the processing to operation S71. Subsequently, until the determination result in operation S76 is “abnormality exists”, the acquisition of the value of the third index and the abnormality determination are repeated.”; [0087] “The buffer 162 temporarily stores the latest value of the third index and past values of the third index acquired over a predetermined time period before acquisition of the latest value of the third index.”),
evaluating the messages for a combination of faults or warnings of at least a first type and of a second type ([0041] lines 6-9, “The hybrid mode is a mode where an abnormality in the controlled object 10 is detected based on a determination criterion set using both the user input and the stored log data.”), wherein the first fault type or warning type depends on a type of the converter ([0140] lines 1-6, “As shown in FIG. 7, the first abnormality detection unit 140 first executes operation S11. In operation S11, the scan control unit 148 starts the scan control (controls the power conversion unit 110 to cause the power conversion unit 110 to generate AC power so as to change the first index and provide the AC power to the motor 12)”), and the second fault type or warning type comprises user-defined faults and warnings ([0041] lines 1-3, “The manual mode is a mode where an abnormality in the controlled object 10 is detected based on a determination criterion set in accordance with a user input.”),
training a machine learning algorithm (Fig. 10) and categorizing with the trained learning algorithm fault events into predefined cause categories ([0168] lines 5-12, “In operation S63, the model building unit 220 builds, based on machine-learning using the log data stored in the data storage unit 210, a neural network that detects an abnormality in the controlled object 10 in accordance with an input including the combination of the value of the first index and the value of the second index. For example, the model building unit 220 builds or updates the neural network based on so-called deep learning.”). The detection of abnormality (i.e. “abnormality” or “no abnormality”) is the categorization of fault events into predefined cause categories) .
Kinomura does not teach the method, comprising:
determining a time interval between an issued warning and an occurrence of a first fault after the start time, wherein the time interval is selected based on the first type and of a second type and wherein different first and second types define different time intervals
categorizing with the trained learning algorithm fault events into predefined cause categories associated with different time intervals
calculating probabilities of the determined technical root causes and associated the probabilities with the fault sources
Spiro teaches an analogous method of determining faults (Abstract), comprising:
calculating probabilities of the determined technical root causes and associated the probabilities with the fault sources (Fig. 1; [0074] lines 1-11, “In examples described herein, data fusion system 1 can allow a user, such as an engineer or mechanic, to analyse information and identify underlying trends, patterns, behaviours and/or precursors which allow the engineer or mechanic to make more informed decisions. Such information can allow an engineer or mechanic to determine the most effective maintenance to perform on a machine. Additionally, when a fault or anomaly has developed in a complex machine, an engineer or mechanic may use the data fusion system 1 to obtain information about a root cause of an anomaly or fault.”)
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Kinomura to include the calculation of Spiro to indicate the most probable root cause and source of fault because it would yield advantageous results of determining where and in what manner a fault or failure has occurred, thereby enabling a faster diagnosis of the fault and a faster response in correcting the fault.
Kinomura in view of Spiro does not teach the method, comprising:
determining a time interval between an issued warning and an occurrence of a first fault after the start time, wherein the time interval is selected based on the first type and of a second type and wherein different first and second types define different time intervals
categorizing with the trained learning algorithm fault events into predefined cause categories associated with different time intervals
Wang teaches an analogous method of predicting failure of components (Abstract; [0002] Detection and prediction of failure in one or more components of an asset of an electrical network has been difficult. Detection of a failure of a component of an asset is tedious and high in errors. In this example, an asset is a device for generating or distributing power in an electrical network. Examples of assets can include, but is not limited to, a wind turbine, solar panel power generator, converter, transformer, distributor, and/or the like. Given that detection of a failure of a component of an asset may be difficult to determine, increased accuracy of prediction of future failures compounds problems.), comprising:
determining a time interval between an issued warning and an occurrence of a first fault after the start time ([0176] lines 1-7, “the longitudinal event and alarm pattern extraction module 1312 extracts information from the event and alarm log for a first time period, the alarm metadata for the same first time period, weather turbine failure data for the same first time period, and cohorts determined by the WT cohort for model development module 1314 in generating the feature matrix.”), wherein the time interval is selected (Fig. 9, steps 906 and 914; [0134] lines 1-3, “In step 914, the trigger module 512 may compare the output of the selected failure prediction model to a threshold to determine if trigger conditions are satisfied 914.”, lines 8-18, “There may be different trigger thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. In various embodiments, there may be different trigger thresholds depending on the amount of damage that may be caused to the asset by failure, other assets by failure, the electrical grid, infrastructure, property and/or life. There may be different trigger thresholds based on the selected model (e.g., based on sensitivity, accuracy, amount of lead time, predicted time of failure, and/or the like).”) based on the first type and of a second type and wherein different first and second types define different time intervals ([0121] “The trigger module 516 may establish thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. Each threshold may be compared to an output of one or more selected models. Thresholds may be established based on the performance of the selected model in order to provide an alarm based on likelihood (e.g., confidence) of prediction, seriousness of fault, seriousness of potential effect of the fault (e.g., infrastructure or life threatened), lead time of fault, and/or the like”.). The selection of the models, which includes the determination of lead time and predicted time to failure, is the determining of the time interval, and the different triggers with their corresponding thresholds, which are based on such criteria as the seriousness of the fault and the component or group it corresponds to, and which correspond to different models (and thus different intervals), are the first and second type; and
categorizing with the trained learning algorithm fault events into predefined cause categories associated with different time intervals ([0134] lines 8-18, “There may be different trigger thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. In various embodiments, there may be different trigger thresholds depending on the amount of damage that may be caused to the asset by failure, other assets by failure, the electrical grid, infrastructure, property and/or life. There may be different trigger thresholds based on the selected model (e.g., based on sensitivity, accuracy, amount of lead time, predicted time of failure, and/or the like).”).
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Kinomura in view of Spiro to include the time intervals of Wang because it would yield predictable results of the fault event types being associated with the time interval of the fault.
Regarding claim 13, Kinomura in view of Spiro and Wang teaches The method of claim 12, wherein the log data are used after a start of the converter (Kinomura: [0085] lines 1-7, “The third index acquisition unit 161 may acquire the value of the third index from outside the power conversion device 100 through an external input terminal. For example, the third index acquisition unit 161 may acquire the detection value associated with the driving speed or driving force of the motor 12 directly from a sensor located outside the power conversion device 100.”). One of ordinary skill in the art would recognize that the detection based off of measured values while the converter is in operation, is the log data used after the start of the converter.
Regarding claim 14, Kinomura in view of Spiro and Wang teaches The method of claim 12, wherein the status messages, warning messages or fault messages are associated with the one or more fault sources (Spiro: [0154] lines 9-14, “A first type of weighted average risk model 6 uses weights in the form of probabilities of a fault developing to calculate an risk scores in the form of estimated probabilities of a corresponding fault type occurring in an associated machine 15, sub-system 18 of the machine, or a group of sub-systems 18.”; [0053] lines 14-21, “The message log corresponding to a machine, such as a ship or construction machinery, records messages generated by controllers, processors or similar devices which are integrated into the component sub-systems of the machine. The messages may include a date and time, an identifier of a component sub-system, and message content such as, for example, warning information of information identifying a fault.”). The estimated probabilities of a corresponding fault type occurring in an associated machine, sub-system, or group of sub-systems, based off of messages including component information, is the association with one or more fault sources.
Regarding claim 15, Kinomura in view of Spiro and Wang teaches The method of claim 14, further comprising calculating a probability for the association of the status messages, warning messages or fault messages with the one or more fault sources (Spiro: [0154] lines 9-14, “A first type of weighted average risk model 6 uses weights in the form of probabilities of a fault developing to calculate an risk scores in the form of estimated probabilities of a corresponding fault type occurring in an associated machine 15, sub-system 18 of the machine, or a group of sub-systems 18.”; [0053] lines 14-21, “The message log corresponding to a machine, such as a ship or construction machinery, records messages generated by controllers, processors or similar devices which are integrated into the component sub-systems of the machine. The messages may include a date and time, an identifier of a component sub-system, and message content such as, for example, warning information of information identifying a fault.”).
Regarding claim 17, Kinomura teaches A method for event monitoring (Abstract, abnormality detection unit 120) in a converter (power conversion device 100 and power conversion unit 110), comprising:
recording historical fault event data of converters of a similar type as the converter in a database ([0189] lines 1-9, “The first abnormality detection unit 140 may further include the data storage unit 145 configured to store a set of the log data of combination of a value of the first index and a value of the second index, the upper limit setting unit 151 may set the upper limit of the correlation profile based on the log data stored in the data storage unit 145, and the lower limit setting unit 152 may set the lower limit of the correlation profile based on the log data stored in the data storage unit 145”);
training a machine learning algorithm (Fig. 10) to categorize the fault event data into predefined cause categories ([0168] lines 5-12, “In operation S63, the model building unit 220 builds, based on machine-learning using the log data stored in the data storage unit 210, a neural network that detects an abnormality in the controlled object 10 in accordance with an input including the combination of the value of the first index and the value of the second index. For example, the model building unit 220 builds or updates the neural network based on so-called deep learning.”). The detection of abnormality (i.e. “abnormality” or “no abnormality”) is the categorization of fault events into predefined cause categories;
during operation of the converter after the successful start ([0085] lines 1-7, “The third index acquisition unit 161 may acquire the value of the third index from outside the power conversion device 100 through an external input terminal. For example, the third index acquisition unit 161 may acquire the detection value associated with the driving speed or driving force of the motor 12 directly from a sensor located outside the power conversion device 100.”). One of ordinary skill in the art would recognize that the detection based off of measured values while the converter is in operation, is the log data used after the start of the converter., detecting fault event messages indicating a fault or a warning (Fig. 5, step S05), with the fault or warning being associated with a first type of fault or warning related to a type of the converter and a second type of fault or warning related to a user-defined fault or warning ([0041] lines 6-9, “The hybrid mode is a mode where an abnormality in the controlled object 10 is detected based on a determination criterion set using both the user input and the stored log data.”);
Kinomura does not teach the method, comprising:
after a successful start of the converter, determining protocol data during a predetermined time period during which no fault is detected,
detecting fault event messages indicating a fault or a warning, with the fault event messages having a time stamp and an identification and the identification including a message type, a text or a source of a fault event message
determining a time interval between an issued warning and an occurrence of a first fault after the start time, wherein the time interval is selected based on the first type and of a second type and wherein different first and second types define different time intervals,
determining most probable technical root causes of the failure or fault by correlating a sequence of the fault event messages with the recorded fault data using artificial intelligence, and
calculating probabilities of the determined technical root causes and associating the probabilities with the fault sources.
Spiro teaches an analogous method of determining faults (Abstract), comprising:
after a successful start of the converter, determining protocol data during a predetermined time period during which no fault is detected,
([0180] lines 7-21, “during normal operation, corresponding sensors 19 of the first and second engines produce parameter curves 59 which are substantially the same. In practice, a pair of corresponding parameter curves 59 will fluctuate by small amounts such that the parameter curves 59 are not precisely identical. However, if a difference between the parameter curves 59 exceeds a threshold amount, this may indicate a fault developing with one of the engines. The threshold may be based on historical data, for example, three times the historic standard deviation of the relevant parameter. Alternatively, the threshold may by a relative threshold, for example, if the ratio of the parameter values measure from first and second engines is outside a range centred on a value of one. The second statistical criterion 137.sub.2 may be met immediately that the threshold deviation has been exceeded.”)
detecting fault event messages indicating a fault or a warning, with the fault event messages having a time stamp and an identification and the identification including a message type, a text or a source of a fault event message ([0143] The database 7 also includes a fault log 17 corresponding to each machine 15. Each fault log 17 is a computer readable log which includes a number of fault objects 56, and each fault object includes fault data 57 specifying a time and a type of a fault (for example a fault ID code), and fault resolution data 58 specifying an end time or duration of the fault and, optionally, a maintenance task object 55 corresponding to a maintenance task which resolved the fault.). The fault data having specified time is the messages having a time stamp. The fault data having a fault ID code is the identification, including a text.
determining most probable technical root causes of the failure or fault by correlating a sequence of the fault event messages with the recorded fault data (Fig. 1; [0074] lines 1-11, “In examples described herein, data fusion system 1 can allow a user, such as an engineer or mechanic, to analyse information and identify underlying trends, patterns, behaviours and/or precursors which allow the engineer or mechanic to make more informed decisions. Such information can allow an engineer or mechanic to determine the most effective maintenance to perform on a machine. Additionally, when a fault or anomaly has developed in a complex machine, an engineer or mechanic may use the data fusion system 1 to obtain information about a root cause of an anomaly or fault.”) using artificial intelligence ([0026] “The risk model may be a machine learning model configured to receive the statistical metrics and log metrics as inputs, and to output fault probabilities corresponding to one or more fault types occurring in the first machine within a second period.”; [0027] lines 3-4, “The machine learning model may be an artificial neural network.”)
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Kinomura to include the determination of Spiro to indicate the most probable root cause and source of fault because it would yield advantageous results of determining where and in what manner a fault or failure has occurred, thereby enabling a faster diagnosis of the fault and a faster response in correcting the fault.
Kinomura in view of Spiro does not teach the method, comprising:
determining a time interval between an issued warning and an occurrence of a first fault after the start time, wherein the time interval is selected based on the first type and of a second type and wherein different first and second types define different time intervals.
Wang teaches an analogous method of predicting failure of components (Abstract; [0002] Detection and prediction of failure in one or more components of an asset of an electrical network has been difficult. Detection of a failure of a component of an asset is tedious and high in errors. In this example, an asset is a device for generating or distributing power in an electrical network. Examples of assets can include, but is not limited to, a wind turbine, solar panel power generator, converter, transformer, distributor, and/or the like. Given that detection of a failure of a component of an asset may be difficult to determine, increased accuracy of prediction of future failures compounds problems.), comprising:
determining a time interval between an issued warning and an occurrence of a first fault after the start time ([0176] lines 1-7, “the longitudinal event and alarm pattern extraction module 1312 extracts information from the event and alarm log for a first time period, the alarm metadata for the same first time period, weather turbine failure data for the same first time period, and cohorts determined by the WT cohort for model development module 1314 in generating the feature matrix.”), wherein the time interval is selected (Fig. 9, steps 906 and 914; [0134] lines 1-3, “In step 914, the trigger module 512 may compare the output of the selected failure prediction model to a threshold to determine if trigger conditions are satisfied 914.”, lines 8-18, “There may be different trigger thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. In various embodiments, there may be different trigger thresholds depending on the amount of damage that may be caused to the asset by failure, other assets by failure, the electrical grid, infrastructure, property and/or life. There may be different trigger thresholds based on the selected model (e.g., based on sensitivity, accuracy, amount of lead time, predicted time of failure, and/or the like).”) based on the first type and of a second type and wherein different first and second types define different time intervals ([0121] “The trigger module 516 may establish thresholds for different components, component types, groups of components, groups of component types, assets, and/or asset types. Each threshold may be compared to an output of one or more selected models. Thresholds may be established based on the performance of the selected model in order to provide an alarm based on likelihood (e.g., confidence) of prediction, seriousness of fault, seriousness of potential effect of the fault (e.g., infrastructure or life threatened), lead time of fault, and/or the like”.). The selection of the models, which includes the determination of lead time and predicted time to failure, is the determining of the time interval, and the different triggers with their corresponding thresholds, which are based on such criteria as the seriousness of the fault and the component or group it corresponds to, and which correspond to different models (and thus different intervals), are the first and second type.
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Kinomura in view of Spiro to include the time intervals of Wang because it would yield predictable results of the fault event types being associated with the time interval of the fault.
Regarding claim 18, Kinomura in view of Spiro and Wang teaches The method of claim 17, wherein the artificial intelligence is a cloud application (Kinomura: server 200; Wang: [0045] lines 6-15, “Examples of systems, environments, and/or configurations that may be suitable for use with system include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems or devices, and the like.”), the method further comprising detecting with the artificial intelligence an output fault (Kinomura: [0168] lines 5-12, “In operation S63, the model building unit 220 builds, based on machine-learning using the log data stored in the data storage unit 210, a neural network that detects an abnormality in the controlled object 10 in accordance with an input including the combination of the value of the first index and the value of the second index. For example, the model building unit 220 builds or updates the neural network based on so-called deep learning.”).
Regarding claim 20, Kinomura in view of Spiro and Wang teaches Event monitoring of a converter, wherein the event monitoring comprises artificial intelligence (Kinomura: Fig. 10) and log file data from the converter (Kinomura: log data) are stored in a cloud (Kinomura: server 200; Wang: [0045] lines 6-15, “Examples of systems, environments, and/or configurations that may be suitable for use with system include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems or devices, and the like.”), wherein the event monitoring is performed using a method as set forth in claim 12.
Regarding claim 21, Kinomura in view of Spiro and Wang teaches Event monitoring of a converter, wherein the event monitoring comprises artificial intelligence (Kinomura: Fig. 10) and log file data from the converter (Kinomura: log data) are stored in a cloud (Kinomura: server 200; Wang: [0045] lines 6-15, “Examples of systems, environments, and/or configurations that may be suitable for use with system include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems or devices, and the like.”), wherein the event monitoring is performed using a method as set forth in claim 17.
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 BRIAN GEISS whose telephone number is (571)270-1248. The examiner can normally be reached Monday - Friday 7:30 am - 4:30 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 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.
/B.B.G./Examiner,
Art Unit 2857
/Catherine T. Rastovski/Supervisory Primary Examiner, Art Unit 2857