Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
2. A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office Action has been withdrawn pursuant to 37 CFR 1.114.
Claim Rejections - 35 USC § 103
3. 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.
4. 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.
5. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
6. Claims 1-3, 9, 12-17 and 20-21 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent No. 8103463 (“Kalgren”) in view of U.S. Patent No. 10925192 (“Campiano”).
Regarding claim 1, KALGREN teaches A method (for example, an “electronic system prognostic health monitoring system” as taught per FIG. 1 and further clarified beginning at column 6 line 4, and see also Methodology 1 as a restatement of how the framework generally operates, per column 7 line 49 – column 8 line 12), comprising:
receiving, by a system, a plurality of parameter measurements associated with a power converter system comprising a power converter (monitoring of sensor values per FIG. 1 step 1200, where the monitored device is “to the electric power converter, or the device under test (DUT)” (per column 6 line 30 (but also column 7 line 31 clarifying that the health assessment is “for the power converter”)), wherein the plurality of parameter measurements comprises a first set of system measurements and a second set of failure precursor measurements (where the sensor-obtained values are used to obtain performance metrics per FIG. 1 step S1300,which may constitute the recited “first set” of measurements, and further per column 7 lines 21-22, “diagnostic features” are extracted from the monitored sensor-obtained values (which are compared later using a diagnostic model to essentially see if the performance as monitored sufficiently measures up with a normal health state, which is clarified in the paragraph to follow starting at column 7 line 10));
inputting, by the system, the first set of system measurements into a first machine learning algorithm to generate expected failure precursor measurement information (where the sensor-obtained values are used to obtain performance metrics per FIG. 1 step S1300, and both the values and the metrics are used by a performance model to perform a classifying “that relates performance metrics with monitoring values for each data class” (column 7 lines 1-5), where the cited-to portion clarifies that the model may explicitly be a “neural network” (i.e., “machine learning algorithm” as recited), where using the class as inferred, an expected norm associated with the class can be obtained using a class-specific diagnostic model (column 7 lines 10-20), which the Examiner equates with “expected failure precursor measurement information” as recited);
inputting, by the system, the expected failure precursor measurement information and the second set of failure precursor measurements into a second machine learning algorithm to generate component failure prediction information (per column 7 lines 21-31, discussing the generation of “a health assessment” for a power converter, for example, which involves a neural network (i.e., “machine learning algorithm” as recited) and a comparison of “diagnostic features” (as extracted from monitored values per column 7 lines 21-22) with “measured performance history with the trained diagnostic model for each class”).
As discussed above, Kalgren performs a health assessment, e.g. per the cited portions and specifically FIG. 1 step S1700. The reference further teaches, per step S1900 that the generated health assessment is reported, which may be understood to be an action, the substance of which, is “based on” the health assessment. As such, Kalgren alone may be sufficient to teach the further limitation for performing, by the system, one or more actions based on the generated component failure prediction information. However, to the extent that Kalgren alone is not sufficient, the Examiner further relies upon CAMPIANO to teach what Kalgren may otherwise lack, see e.g., Campiano ...
Applicants’ claims further require the additional limitations wherein performing the one or more actions comprises minimizing a current draw for a component within the power converter system that is identified by the component failure prediction information and wherein performing the one or more actions also comprises increasing a speed of a fan within the power converter system to cool the compartment within the power converter system that is identified by the component failure prediction information, which Campiano also teaches:
Regarding an action comprising minimizing a current draw for a component within the power converter system, see e.g., column 3 lines 25-35 discussing measures taken in response to a performance forecasting indication that there is a risk for excessive heat, such as to “reduce the amount of heat generated by the computer system, such as by reducing its clock speed, reducing its use of peripheral devices, reducing the amount of capacity demanded from the computer system, and combinations or conjunctions thereof.” The Examiner reasons that these are measures that reactively minimize a current draw by downshifting power consumption within the electrical system.
Regarding an action comprising increasing a speed of a fan within the power converter system to cool the identified predicted failure area, see e.g., column 3 lines 35-42 discussing measures taken in response to a performance forecasting indication that there is a risk for excessive heat, such as to “increase the amount of cooling generated by the cooling system, such as by increasing the amount of airflow, increasing the amount of fan speed, increasing the amount of cooling capacity devoted to the computer system.”
Both Kalgren and Campiano are similarly directed in how they monitor values from a device for processing using machine learning techniques, such that the result is a determination as to whether the device is soon to fail or the like. Hence, the aforementioned references are similarly directed and therefore analogous. It would have been obvious to one of ordinary skill in the art to incorporate many of the overt triggered actions that Campiano contemplates in light of an imminent failure detection into a reference such as Kalgren’s, with a reasonable expectation of success, to provide for a logical next step in meaningfully utilizing the detected imminent failure to improve operations in a manner of ways (going constructively beyond Kalgren’s mere indication output).
Regarding claim 2, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein the first machine learning algorithm is a first neural network, wherein the second machine learning algorithm is a second neural network (Kalgren: where the sensor-obtained values are used to obtain performance metrics per FIG. 1 step S1300, and both the values and the metrics are used by a performance model to perform a classifying “that relates performance metrics with monitoring values for each data class” (column 7 lines 1-5), where the cited-to portion clarifies that the model may explicitly be a “neural network”, and also per column 7 lines 21-31, discussing the generation of “a health assessment” for a power converter, for example, which involves a neural network). The motivation to combine the references is as discussed above in relation to claim 1.
Regarding claim 3, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein receiving the plurality of parameter measurements comprises: receiving the first set of system measurements from one or more first sensors of the power converter system; and receiving the second set of failure precursor measurements from one or more second sensors of the power converter system (Kalgren: monitoring of sensor values per FIG. 1 step 1200, where the monitored device is “to the electric power converter, or the device under test (DUT)”, where in accomplishing this monitoring many sensors are plainly contemplated, see e.g., Kalgren’s column 6 lines 22-25 and especially column 20 lines 5-27). The motivation to combine the references is as discussed above in relation to claim 1.
Regarding claim 9, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein performing the one or more actions comprises providing the component failure prediction information to a back-end computing system (Kalgren’s column 8 lines 39-48 discussing “a third party hardware or software module”, which the Examiner equates with the recited back-end computing system). The motivation to combine the references is as discussed above in relation to claim 1.
Regarding claim 12, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein the component failure prediction information indicates one or more probabilities of failure for one or more components of the power converter system (Kalgren’s column 7 lines 31-34 discussing “The health assessment identifies the source of the fault by isolating down to a component or a group of components, probability of overall system failure”, and column 21 line 50 – column 22 line 3 discussing “... For a prognostics implementation, the automated reasoning algorithm can be trained on evidenced features that progress through a failure. In such cases, the probability of failure, as defined by some measure of the "ground truth", trains the predictive algorithm based on the input features and desired output prediction. ...”). The motivation to combine the references is as discussed above in relation to claim 1.
Regarding claim 13, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein the component failure prediction information indicates a probability of failure for the power converter system (Kalgren’s column 7 lines 31-34 discussing “The health assessment identifies the source of the fault by isolating down to a component or a group of components, probability of overall system failure”, and column 21 line 50 – column 22 line 3 discussing “... For a prognostics implementation, the automated reasoning algorithm can be trained on evidenced features that progress through a failure. In such cases, the probability of failure, as defined by some measure of the "ground truth", trains the predictive algorithm based on the input features and desired output prediction. ...”). The motivation to combine the references is as discussed above in relation to claim 1.
Regarding claim 14, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein the component failure prediction information indicates a remaining useful life estimation of the power converter (Kalgren’s “remaining useful life” prediction/estimate per column 1 line 25 and column 7 line 34). The motivation to combine the references is as discussed above in relation to claim 1.
Regarding claim 15, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein performing the one or more actions based on the generated component failure prediction information comprises: triggering an action to modify a mode of operation of the power converter (Campiano’s column 4 lines 8-19 discussing the alteration of operations, e.g. as discussed in relation to claim 1 as well, where such an alteration is a triggered action to modify a mode of operation, e.g. particularly as discussed in relation to claim 1’s limitation for minimizing current draw and the equivalent examples that Campiano teaches (e.g., reducing clock speed, reducing peripheral device use, reducing demand from the computer system), and where lines 8-19 specifically mention that a user can take these actions with respect to the system/components and/or operations can be restrained until the user does so (either of which is a triggered action as recited)). The motivation to combine the references is as discussed above in relation to claim 1.
Regarding claim 16, the claim includes the same or similar limitations as claim 1 discussed above, and is therefore rejected under the same rationale. The Examiner notes that the instant claim explicitly recites active instances of a power converter and a power converter control system (which otherwise performs the steps discussed above in relation to claim 1’s method). The art as has been cited to explicitly teaches the monitoring and managing of a power converter, and the Examiner has provided a citation to that effect per claim 1. Hence, the Examiner believes the citations and rationale provided above per claim 1 sufficiently and fully read on the instant claim.
Regarding claim 17, the claim includes the same or similar limitations as claim 2 discussed above, and is therefore rejected under the same rationale.
Regarding claim 20, the claim includes the same or similar limitations as claim 1 discussed above, and is therefore rejected under the same rationale. The Examiner notes that the instant claim explicitly recites active instances of a non-transitory computer-readable medium having processor executable instructions stored thereon to otherwise essentially perform the same steps discussed above in relation to claim 1’s method. Kalgren’s column 19 line 22 – column 20 line 4 discusses the various hardware architecture environments to implement its framework, which necessarily require a memory to store the executable instructions needed to perform for example its FIG. 1 and related teachings.
Regarding claim 21, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations for performing an additional training of the first and second machine learning algorithm (Kalgren’s column 7 lines 17-20 discussing periodic model updating, which the Examiner believes would involve further training, and also Campiano’s model refreshing, also could involve further training, per column 11 lines 3-16), based on enablement information comprising user input (Campiano’s column 11 lines 3-16 discussing refreshing the model based on a “selected duration of time” (i.e., a user’s input that enables periodic model refresh and hence model retraining on a prescribed schedule)). The motivation for combining the references is as discussed above in relation to claim 1.
7. Claims 4-5 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Kalgren in view of Campiano and further in view of U.S. Patent Application Publication No. 2007/0219749 (“Jayabalan”).
Regarding claim 4, Kalgren in view Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein the power converter comprises a rectifier ... wherein the rectifier comprises a plurality of first semiconductor devices ... wherein the second set of failure precursor measurements are measurements associated with the plurality of first semiconductor devices and a plurality of second semiconductor devices (Kalgren’s predictive framework relating to device failure, specifically discussed as relating to power converters as the Examiner noted in relation to claim 1, encompasses a developed understanding of semiconductors and their failure, and measurements relating thereto, such that it helps the framework perform prognostic health monitoring functions (column 22 lines 44-56), thereby reading on the capacity to encompass first and second pluralities of semiconductor devices for example). That said, Kalgren etc. are silent as to the further limitation wherein the power converter also comprises ... an inverter, and rather, the Examiner relies upon JAYABALAN to teach what they otherwise lack, see e.g., Jayabalan’s comparable monitoring and diagnosis framework specifically directed to power systems and converters (Abstract, [0003]), where specifically the power conversion systems are explicitly characterized as featuring rectifier and inverter components per [0036].
The references are similarly directed to monitoring and diagnosis of fault/degradation/failure in same/similar device types, namely power converters, and are therefore analogous. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to extend Kalgren’s modified framework for monitoring and diagnosis to encompass power system converters having components therein, as Jayabalan contemplates, such that the benefits provided in component monitoring and diagnostic/prognostic analysis could be extended concretely and explicitly to other and more wider range of subcomponents involved in the same type/class of device, e.g. per Jayabalan’s breadth.
Regarding claim 5, Kalgren in view of Campiano and further in view of Jayabalan teach the method of claim 4, as discussed above. The aforementioned references teach the additional limitations wherein the component failure prediction information indicates degradation of one or more semiconductor devices from the plurality of first semiconductor devices or the plurality of second semiconductor devices (Kalgren: column 1 lines 21-30 discussing “degradation assessor”, see also lines 34-44 and 54-57 discussing degradation of device as determined based on measures of diagnostic features, the devices are explicitly inclusive of semiconductor characterization as discussed above per claim 4). The motivation to combine the references is as discussed above in relation to claim 4.
Regarding claim 18, the claim includes the same or similar limitations as claim 4 discussed above, and is therefore rejected under the same rationale.
Regarding claim 19, the claim includes the same or similar limitations as claim 5 discussed above, and is therefore rejected under the same rationale.
9. Claims 6-8 are rejected under 35 U.S.C. 103 as being unpatentable over Kalgren in view of Campiano and further in view of U.S. Patent Application Publication No. 2022/0351744 (“Krishnan”).
Regarding claim 6, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references teach the involvement of infrastructure featuring a back-end system, e.g. see Kalgren’s column 8 lines 39-48 discussing “a third party hardware or software module”, which the Examiner equates with the recited back-end computing system. That said, Kalgren etc. do not sufficiently teach the further limitations for providing, by the system and to a back-end computing system, a request for the first machine learning algorithm and the second machine learning algorithm, wherein the back-end computing system performs initial training of the first machine learning algorithm and the second machine learning algorithm; and receiving, by the system and from the back-end computing system, the first machine learning algorithm and the second machine learning algorithm. Rather, the Examiner relies upon KRISHNAN to teach what Kalgren etc. otherwise lack, see e.g., Krishnan’s comparable framework for device monitoring and fault diagnosis or the like, where per Krishnan’s FIGs. 5A-5B a model is developed centrally and then transmitted to endpoints where local copies are maintained.
The references are similarly directed to monitoring and diagnosis of fault/degradation/failure in devices/machinery, and are therefore analogous. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Krishnan’s federated learning and master/local modelling aspect into a framework such as Kalgren as modified, with a reasonable expectation of success, such that a breadth of service and support can be provided over many devices and vendors, as amassed from many different endpoints, as Krishnan contemplates, but without some of the data volume and communication reliability challenges that could exist as discussed per Krishnan’s [0016].
Regarding claim 7, Kalgren in view of Campiano and further in view of Krishnan teach the method of claim 6, as discussed above. The aforementioned references teach the additional limitations further comprising: performing, by the system, additional training of the first machine learning algorithm based on obtaining a plurality of training measurements from one or more sensors of the power converter system (Campiano’s column 11 lines 3-16 discussing refreshing the model based on a determination that the model should be rebuilt, e.g. because accuracy/error suggests it based on the most recent application of the model, which the Examiner reasons would be understood by one of ordinary skill in the art to be model drift and would warrant retraining as Campiano’s portion cited here teaches). The motivation to combine the references is as discussed above in relation to claim 6.
Regarding claim 8, Kalgren in view of Campiano and further in view of Krishnan teach the method of claim 6, as discussed above. The aforementioned references teach the additional limitations wherein the request indicates a particular type of the power converter that is within the power converter system (it reasons that the model as requested should fit the subject matter to be modelled). The motivation to combine the references is as discussed above in relation to claim 6.
10. Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Kalgren in view of Campiano and further in view of U.S. Patent Application Publication No. 2004/0130868 (“Schwartz”).
Regarding claim 10, Kalgren in view of Campiano teach the method of claim 1, as discussed above. The aforementioned references contemplate monitoring devices to determine failure states that may be pending/imminent and then providing an action or remedy as recourse. See, e.g., the rejection of claim 1, above. That said, Kalgren etc. do not specifically teach the additional limitation wherein performing the one or more actions comprises increasing a speed of a fan within the power converter system. Rather, the Examiner relies upon SCHWARTZ to teach what Kalgren etc. otherwise lack, see e.g., Schwartz’s [0027] discussing the increasing of a fan speed to address imminent failure of a power converter.
The references are similarly directed to monitoring and diagnosis of fault/degradation/failure in the same class of devices/machinery, and are therefore analogous. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to extend Kalgren’s framework as modified to encompass an action such as Schwartz teaches, with a reasonable expectation of success, such that a failure situation that all the references appear to contemplate (i.e., power converter imminent failure) can be addressed using controllable elements known in the state of the art, per Schwartz.
Conclusion
11. The prior art made of record and not relied upon is considered pertinent to Applicants’ disclosure:
US 20140201571 A1
US 20180373300 A1
US 6198245 B1
US 20110078513 A1
CN 113204461 A
Non-Patent Literature “12 PCB Thermal Management Techniques to Reduce PCB Heating”
Non-Patent Literature “A review of the state-of-the-art in electronic cooling”
12. Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHOURJO DASGUPTA whose telephone number is (571) 272-7207. The examiner can normally be reached M-F 8am-5pm CST.
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, Tamara Kyle can be reached at 571 272 4241. 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.
/SHOURJO DASGUPTA/Primary Examiner, Art Unit 2144