IP Library › Granted Patent US 12,379,984
Granted Patent B2
US 12,379,984 · App. 18/129,594 · Granted Aug 5, 2025

Remaining useful life determination for power electronic devices

Inventors: Hiroshi Ukegawa (South Lyon, MI); Raymond P. Viviano (Hazel Park, MI); Shailesh N. Joshi (Ann Arbor, MI); Qian Yang (Vernon, CT); Krishna Pattipati (Storrs, CT)
Assignees: Toyota Motor Engineering & Manufacturing North America, Inc.; University of Connecticut
G06F11/0751G06F11/008G06F11/0721G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,379,984
App. No.
18/129,594
Granted
Aug 5, 2025
Kind
B2
Abstract

Systems, methods, and other embodiments described herein relate to predicting anomalous operation of a device and an associated remaining useful life (RUL) estimation. In one embodiment, a method includes acquiring usage information about the operation of an electronic device. The method includes determining whether the usage information indicates the presence of an anomaly in the operation of the electronic device according to an anomaly model. The method includes, responsive to detecting the anomaly, determining a remaining useful life (RUL) for the electronic device according to a RUL model. The method includes providing the RUL estimate.

Claims (38)

1. A correlation system for monitoring health of an electronic device, comprising:

one or more processors;

a memory communicably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to:

acquire usage information about operation of the electronic device;

determine whether the usage information indicates a presence of an anomaly in the operation of the electronic device according to an anomaly model;

responsive to detecting the anomaly, determine a remaining useful life (RUL) for the electronic device according to a RUL model that implements a self-organizing map (SOM) and interacting multiple models (IMMs) that are extended Kalman filters, the SOM determines a state of health (SOH) for the usage information and the IMMs predict future values of the SOH at future time points according to the usage information; and

provide the RUL including mitigating failure of the electronic device according to the RUL by adapting operation of the electronic device that is a vehicle to limit one or more of a charging rate, and an advanced driving assistance system (ADAS), including adjusting operating parameters of the electronic device that restrict behaviors of the vehicle.

2. The correlation system of claim 1 , wherein the instructions to determine whether the usage information indicates the presence of the anomaly include instructions to apply the anomaly model that implements partial-least squares regression-cumulative sum (PLS-CUSUM) over the usage information, the anomaly model being trained according to early-life operating characteristics of the electronic device.

3. The correlation system of claim 2 , wherein the instructions to apply the anomaly model include instructions to iterative apply the anomaly model over the usage information as the electronic device operates to predict operating values of the electronic device and accumulate a residual according to a covariance between the operating values and observed values, and

wherein the instructions to determine whether the usage information indicates the presence of the anomaly include instructions to determine when the residual that is accumulated satisfies an anomaly threshold.

4. The correlation system of claim 1 , wherein the instructions to provide the RUL include instructions to mitigate the failure of the electronic device by one or more of displaying an alert within the vehicle and adapting operation of the vehicle to limit functionality of at least one system of the vehicle.

5. The correlation system of claim 4 , wherein the instructions to apply the RUL model include instructions to select one of the extended Kalman filters for producing the future values of the SOH according to a posterior probability for each of the extended Kalman filters.

6. The correlation system of claim 4 , wherein the IMMs separately model degradation of the electronic device according to different ones of the extended Kalman filters.

7. The correlation system of claim 1 , wherein the instructions to acquiring the usage information includes collecting signals from one or more sensors associated with the electronic device, the signals being time-series data and indicating one or more of: drain-to-source voltage, drain-to-source resistance, temperature, thermal resistance, and gate-leakage current.

8. The correlation system of claim 1 , wherein the electronic device is one of a power control unit (PCU), an electronic control unit (ECU), an insulated-gate bipolar transistor (IGBT), a metal-oxide-semiconductor field-effect transistor (MOSFET), an inverter, and a converter.

9. A non-transitory computer-readable medium for monitoring health of an electronic device and including instructions that, when executed by one or more processors, cause the one or more processors to:

acquire usage information about operation of the electronic device;

determine whether the usage information indicates a presence of an anomaly in the operation of the electronic device according to an anomaly model;

responsive to detecting the anomaly, determine a remaining useful life (RUL) for the electronic device according to a RUL model that implements a self-organizing map (SOM) and interacting multiple models (IMMs) that are extended Kalman filters, the SOM determines a state of health (SOH) for the usage information and the IMMs predict future values of the SOH at future time points according to the usage information; and

provide the RUL including mitigating failure of the electronic device according to the RUL by adapting operation of the electronic device that is a vehicle to limit one or more of a charging rate, and an advanced driving assistance system (ADAS), including adjusting operating parameters of the electronic device that restrict behaviors of the vehicle.

10. The non-transitory computer-readable medium of claim 9 , wherein the instructions to determine whether the usage information indicates the presence of the anomaly include instructions to apply the anomaly model that implements partial-least squares regression-cumulative sum (PLS-CUSUM) over the usage information, the anomaly model being trained according to early-life operating characteristics of the electronic device.

11. The non-transitory computer-readable medium of claim 10 , wherein the instructions to apply the anomaly model include instructions to iterative apply the anomaly model over the usage information as the electronic device operates to predict operating values of the electronic device and accumulate a residual according to a covariance between the operating values and observed values, and

wherein the instructions to determine whether the usage information indicates the presence of the anomaly include instructions to determine when the residual that is accumulated satisfies an anomaly threshold.

12. The non-transitory computer-readable medium of claim 9 , wherein the instructions to provide the RUL include instructions to mitigate the failure of the electronic device by one or more of displaying an alert within the vehicle and adapting operation of the vehicle to limit functionality of at least one system of the vehicle.

13. The non-transitory computer-readable medium of claim 12 , wherein the instructions to apply the RUL model include instructions to select one of the extended Kalman filters for producing the future values of the SOH according to a posterior probability for each of the extended Kalman filters.

14. A method, comprising:

acquiring usage information about operation of an electronic device;

determining whether the usage information indicates a presence of an anomaly in the operation of the electronic device according to an anomaly model;

responsive to detecting the anomaly, determining a remaining useful life (RUL) for the electronic device according to a RUL model that implements a self-organizing map (SOM) and interacting multiple models (IMMs) that are extended Kalman filters, the SOM determines a state of health (SOH) for the usage information and the IMMs predict future values of the SOH at future time points according to the usage information; and

providing the RUL including mitigating failure of the electronic device according to the RUL by adapting operation of the electronic device that is a vehicle to limit one or more of a charging rate, and an advanced driving assistance system (ADAS), including adjusting operating parameters of the electronic device that restrict behaviors of the vehicle.

15. The method of claim 14 , wherein determining whether the usage information indicates the presence of the anomaly includes applying the anomaly model that implements partial-least squares regression-cumulative sum (PLS-CUSUM) over the usage information, the anomaly model being trained according to early-life operating characteristics of the electronic device.

16. The method of claim 15 , wherein applying the anomaly model is iterative over the usage information as the electronic device operates to predict operating values of the electronic device and accumulate a residual according to a covariance between the operating values and observed values, and

wherein determining whether the usage information indicates the presence of the anomaly includes determining when the residual that is accumulated satisfies an anomaly threshold.

17. The method of claim 14 , wherein mitigating the failure of the electronic device includes one or more of displaying an alert within the vehicle and adapting operation of the vehicle to limit functionality of at least one system of the vehicle.

18. The method of claim 17 , wherein applying the RUL model includes selecting one of the extended Kalman filters for producing the future values of the SOH according to a posterior probability for each of the extended Kalman filters.

19. The method of claim 17 , wherein the IMMs separately model degradation of the electronic device according to different ones of the extended Kalman filters.

20. The method of claim 14 , wherein acquiring the usage information includes collecting signals from one or more sensors associated with the electronic device, the signals being time-series data and indicating one or more of: drain-to-source voltage, drain-to-source resistance, temperature, thermal resistance, and gate-leakage current, and

wherein the electronic device is one of a power control unit (PCU), an electronic control unit (ECU), an insulated-gate bipolar transistor (IGBT), a metal-oxide-semiconductor field-effect transistor (MOSFET), an inverter, and a converter.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 19, 2025
From: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.
To: MIRISE TECHNOLOGIES CORPORATION; TOYOTA JIDOSHA KABUSHIKI KAISHA; DENSO CORPORATION
Reel/Frame 072054/0490 →
CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT APPLICATION NUMBER AND TITLE PREVIOUSLY RECORDED ON REEL 063552 FRAME 0471. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded May 24, 2023
From: YANG, QIAN; PATTIPATI, KRISHNA
To: UNIVERSITY OF CONNECTICUT
Reel/Frame 063745/0101 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 5, 2023
From: UKEGAWA, HIROSHI; VIVIANO, RAYMOND P.; JOSHI, SHAILESH N.
To: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.
Reel/Frame 063552/0484 →
Continuity (2)
Provisional Application 63386564 · Dec 8, 2022
Related Publication 20240193025A1 · Jun 13, 2024
References Cited (65)
US 7271608B1 · Vermeire et al. · 2007 [cited by applicant]
US 8103463B2 · Kalgren et al. · 2012 [cited by applicant]
US 8600685B2 · Kalgren et al. · 2013 [cited by applicant]
US 9494657B2 · Khan et al. · 2016 [cited by applicant]
US 9933338B2 · Noda et al. · 2018 [cited by applicant]
US 10090798B2 · Watanabe et al. · 2018 [cited by applicant]
US 10354462B1 · Zhang et al. · 2019 [cited by applicant]
US 10410116B2 · Husain et al. · 2019 [cited by applicant]
US 10560047B2 · Joshi et al. · 2020 [cited by applicant]
US 10605854B2 · Sathik et al. · 2020 [cited by applicant]
US 10650616B2 · Zhang et al. · 2020 [cited by applicant]
US 10672199B2 · Landolsi et al. · 2020 [cited by applicant]
US 10692302B2 · Dede et al. · 2020 [cited by applicant]
US 11099551B2 · Ristovski et al. · 2021 [cited by applicant]
US 11474146B2 · Degrenne et al. · 2022 [cited by applicant]
US 20080141072A1 · Kalgren · 2008 [cited by examiner]
US 20180276546A1 · Joshi et al. · 2018 [cited by applicant]
US 20190250205A1 · Sarwar et al. · 2019 [cited by applicant]
US 20190278684A1 · Dede et al. · 2019 [cited by applicant]
US 20210215760A1 · McMenemy et al. · 2021 [cited by applicant]
US 20210341911A1 · Joshi et al. · 2021 [cited by applicant]
US 20220004182A1 · Natsumeda et al. · 2022 [cited by applicant]
US 20220100187A1 · Isik et al. · 2022 [cited by applicant]
US 20220107630A1 · Zope · 2022 [cited by examiner]
US 20220270189A1 · Wetherbee et al. · 2022 [cited by applicant]
US 20240210936A1 · Ukegawa · 2024 [cited by examiner]
WO 2012151150A1 · 2012 [cited by applicant]
Singleton II, Rodney K. et al., Extended Kalman Filtering for Remaining-Useful-Life Estimation of Bearings, 2014, IEEE (Year: 2014). [cited by examiner]
Zhou, Funa et al., Average Accumulative Based Time Variant Model for Early Diagnosis and Prognosis of Slowly Varying Faults, 2018, Sensors (Year: 2018). [cited by examiner]
Yang, Qian et al., Incipient Residual-Based Anomaly Detection in Power Electronic Devices, 2022, IEEE (Year: 2022). [cited by examiner]
Liao, Linxia et al., Review of Hybrid Prognostics Approaches for Remaining Useful Life Prediction of Engineered Systems, and an Application to Battery Life Prediction, 2014, IEEE (Year: 2014). [cited by examiner]
Lei, Yaguo et al., A Model-Based Method for Remaining Useful Life Prediction of Machinery, 2016, IEEE (Year: 2016). [cited by examiner]
Kabir et al., “A review of data-driven prognostics in power electronics”, 2012 IEEE 35th International Spring Seminar on Electronics Technology, 2012, pp. 189-192. [cited by applicant]
Celaya et al., “Prognostics approach for power MOSFET under thermal-stress aging”, 2012 IEEE Proceedings Annual Reliability and Maintainability Symposium, 2012, pp. 1-6. [cited by applicant]
Ni et al., “Overview of real-time lifetime prediction and extension for SiC power converters”, IEEE Transactions on Power Electronics, 2019, pp. 7765-7794, vol. 35, No. 8. [cited by applicant]
Lall et al., “Prognostics health management of electronic systems under mechanical shock and vibration using kalman filter models and metrics”, IEEE Transactions on Industrial Electronics, 2012, pp. 4301-4314, vol. 59, … [cited by applicant]
Sutharssan et al., “Data analysis techniques for real-time prognostics and health management of semiconductor devices”, 18th IEEE European Microelectronics & Packaging Conference, 2011, pp. 1-7. [cited by applicant]
Haque et al., “Prognosis of power mosfet in continuous time framework”, 2017 IEEE Applied Power Electronics Conference and Exposition (APEC), 2017, pp. 2269-2275. [cited by applicant]
Zheng et al., “A relevance vector machine-based approach for remaining useful life prediction of power mosfets”, 2014 IEEE Prognostics and System Health Management Conference (PHM-2014 Hunan), 2014, pp. 642-646. [cited by applicant]
Ni et al., “Review of sic mosfet based three-phase inverter lifetime prediction”, 2017 IEEE Applied Power Electronics Conference and Exposition (APEC), 2017, pp. 1007-1014. [cited by applicant]
Lelis et al., “Basic mechanisms of thresholdvoltage instability and implications for reliability testing of sic mosfets”, IEEE Transactions on Electron Devices, 2014, pp. 316-323, vol. 62, No. 2. [cited by applicant]
Celaya et al., “Towards prognostics of power mosfets: Accelerated aging and precursors of failure”, National Aeronautics and Space Administration Moffett Field CA Ames Research, Tech. Rep., 2010. [cited by applicant]
Pugalenthi et al., “Prognosis of power mosfet resistance degradation trend using artificial neural network approach”, Microelectronics Reliability, 2019, p. 113467, vol. 100. [cited by applicant]
Shenoy et al., “Differential power processing for increased energy production and reliability of photovoltaic systems”, IEEE Transactions on Power Electronics, 2012, pp. 2968-2979, vol. 28, No. 6. [cited by applicant]
Dusmez et al., “Remaining useful lifetime estimation for power mosfets under thermal stress with ransac outlier removal”, IEEE Transactions on Industrial Informatics, 2017, pp. 1271-1279, vol. 13, No. 3. [cited by applicant]
Bayerer et al., “Model for power cycling lifetime of igbt modules-various factors influencing lifetime,” 5th international conference on integrated power electronics systems, VDE, 2008, pp. 1-6. [cited by applicant]
Li et al., “A framework for model-based diagnostics and prognostics of switched-mode power supplies”, Annual Conference of the PHM Society, 2014, vol. 6, No. 1. [cited by applicant]
Saha et al., “Towards prognostics for electronics components,” 2009 IEEE Aerospace conference, 2009, pp. 1-7. [cited by applicant]
Saha et al., “Accelerated aging with electrical overstress and prognostics for power mosfets”, 2011 IEEE Energy Tech., 2011, pp. 1-6. [cited by applicant]
Dusmez et al., “Remaining useful lifetime estimation for degraded power mosfets under cyclic thermal stress”, 2015 IEEE Energy Conversion Congress and Exposition (ECCE), 2015, pp. 3846-3851. [cited by applicant]
Jensen et al., “A method for online stator insulation prognosis for inverter-driven machines”, IEEE Transactions on Industry Applications, 2018, pp. 5897-5906, vol. 54, No. 6. [cited by applicant]
Al-Mohamad et al., “A hybrid system-level prognostics approach with online rul forecasting for electronics-rich systems with unknown degradation behaviors”, Microelectronics Reliability, 2020, p. 113676, vol. 111. [cited by applicant]
Li et al., “A prognostic methodology for power mosfets under thermal stress using echo state network and particle filter,” Microelectronics Reliability, 2018, pp. 350-354, vol. 88. [cited by applicant]
Witczak et al., “Remaining useful life prediction of mosfets via the takagi-sugeno framework”, Energies, 2021, p. 2135, vol. 14, No. 8. [cited by applicant]
Gultekin et al., “High- and low-frequency accelerated stress tests for aging assessment of mosfet parameters,” 2021 IEEE International Electric Machines & Drives Conference (IEMDC), 2021, pp. 1-4. [cited by applicant]
Kohonen et al., “The self-organizing map,” Proceedings of the IEEE, 1990, pp. 1464-1480, vol. 78, No. 9. [cited by applicant]
Pan et al., “A hybrid dbn-som-pf-based prognostic approach of remaining useful life for wind turbine gearbox,” Renewable Energy, 2020, pp. 138-154, vol. 152. [cited by applicant]
Krishna et al., “Genetic k-means algorithm,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1999, pp. 433-439, vol. 29, No. 3. [cited by applicant]
Likas et al., “The global k-means clustering algorithm”, Pattern Recognition, 2003, pp. 451-461, vol. 36, No. 2. [cited by applicant]
Arthur et al., “k-means++: the advantages of careful seeding”, Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, Society for Industrial and Applied Mathematics,2007, pp. 1027-1035. [cited by applicant]
Luo et al., “Model-based prognostic techniques applied to a suspension system,” IEEE Transactions on Systems, Man, and Cybernetics—Part A: Systems and Humans, 2008, pp. 1156-1168, vol. 38, No. 5. [cited by applicant]
Saxena et al., “On applying the prognostic performance metrics,” Annual Conference of the PHM Society, 2009, vol. 1, No. 1. [cited by applicant]
Lai et al., “Multi-Dimensional Self Attention based Approach for Remaining Useful Life Estimation”, Preprint submitted to Elsevier, Dec. 13, 2022. [cited by applicant]
McMenemy et al., “A Machine Learning Approach for Adaptive Classification of Power MOSFET Failures,” 2019 IEEE Transportation Electrification Conference and Expo (ITEC), 2019, pp. 1-8. [cited by applicant]
Rigamonti et al., “A Self-Organizing Map-Based Monitoring System for Insulated Gate Bipolar Transistors Operating in Fully Electric Vehicle”, Annual Conference of the Prognostics and Health Management Society 2015, 2015… [cited by applicant]