Remaining useful life determination for power electronic devices

Inventors

UKEGAWA, Hiroshi • Viviano, Raymond P. • Joshi, Shailesh N. • Yang, Qian • Pattipati, Krishna

Assignees

Denso Corp • Toyota Motor Corp • Mirise Technologies Corp • University of Connecticut

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.

Core Innovation

A correlation system for monitoring health of an electronic device acquires usage information about operation of the electronic device and determines whether the usage information indicates a presence of an anomaly in the operation of the electronic device according to an anomaly model. The anomaly model is used to drive a subsequent remaining useful life evaluation.

Responsive to detecting the anomaly, the system determines a remaining useful life (RUL) for the electronic device according to a RUL model. The RUL model implements a self-organizing map (SOM) and interacting multiple models (IMMs) that are extended Kalman filters, where 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.

The RUL is provided to mitigate failure by adapting operation of the electronic device that is a vehicle. The system limits 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. In some implementations, an in-vehicle alert is displayed and operation is adapted to limit functionality of at least one vehicle system.

Claims Coverage

The document includes three independent claims that cover a correlation system, a non-transitory computer-readable medium, and a method. Across the independent claims, there are three main inventive feature groupings: anomaly-driven RUL estimation using a SOM plus IMMs implemented as extended Kalman filters, anomaly detection using an anomaly model, and failure mitigation by adapting vehicle operation.

The independent claims consistently require acquiring usage information, determining an anomaly according to an anomaly model, then computing RUL using a RUL model with a SOM for SOH determination and IMMs implemented as extended Kalman filters for future SOH prediction. The RUL output is used to mitigate failure by adapting vehicle operation, including limiting charging rate and restricting vehicle behaviors through ADAS-related operating-parameter adjustments.

Stated Advantages

Documented Applications