Toyota Motor Engineering & Manufacturing North America, Inc.

University of Connecticut

Weiqiang Chen

Shailesh N Joshi

Ali M Bazzi

Lingyi Zhang

Ercan Mehment Dede

Krishna Pattipatti

Krishna R Pattipati

Donald Mcmenemy

Systems and methods for detecting an anomaly in a power semiconductor device are disclosed. A system includes a server computing device and one or more local components communicatively coupled to the server computing device. Each local component includes sensors positioned adjacent to the power semiconductor device for sensing properties thereof. Each local component receives data corresponding to one or more sensed properties of the power semiconductor device from the sensors and transmits the data to the server computing device. The server computing device utilizes the data, via a machine learning algorithm, to generate a set of eigenvalues and associated eigenvectors and select a selected set of eigenvalues and associated eigenvectors. Each local component conducts a statistical analysis of the selected set of eigenvalues and associated eigenvectors to determine that the data is indicative of the anomaly.

Distributed architecture for fault monitoring

To predict a failure condition in a power module of a vehicle, it is determined whether a discontinuity in statistical data characterizing physical measurements of the power module meets a threshold criterion. Responsive to the discontinuity meeting the threshold criterion, a data offset in the physical measurements is computed at the discontinuity. A shift correction is applied to the physical measurements in accordance with the computed data offset responsive to a determination that the discontinuity is attributable to a restart of the power module. Other statistical data characterizing the shift-corrected physical measurements are computed and the statistical data and the other statistical data are provided to a machine learning processor that predicts the failure condition in the power module.

Mitigating data offsets for machine learning

Systems and methods for detecting a fault or model mismatch are disclosed. A system includes a processor, a memory, and one or more sensors. The sensors may detect data associated with an electronic device. The memory may store processor executable instructions to: compute Tand Q statistics, over a time period, and apply a model mismatch and fault detection logic based on the Tand Q statistics. The model mismatch and fault detection logic may: count consecutive instances where a Tstatistic exceeds a Tthreshold via a Tcounter, update a probability of fault based on the Tcounter, count consecutive instances where a Q statistic exceeds a Q threshold via a Q counter, update a probability of model mismatch based on the Q counter, and detect one of a fault or a model mismatch based on a probability of fault threshold and a probability of model mismatch threshold.

Systems and methods for detecting a fault or a model mismatch

A system includes a vehicle having an electronic device, a sensor designed to detect sensor data corresponding to at least one property of the electronic device, an output device designed to output data, and a vehicle network access device designed to transmit the sensor data. The system also includes a machine learning server separate from the vehicle and having a machine learning processor designed to receive the sensor data, and generate, using a machine learning algorithm, a model of the electronic device. The machine learning processor is also designed to determine that a fault is likely to occur with the electronic device by conducting a T squared statistical analysis of the sensor data using the model, and generate a signal to be transmitted to the vehicle network access device when the fault is likely to occur and output information indicating that the fault is likely to occur.

Fault diagnosis using distributed PCA architecture

A system includes an electronic device and a sensor to detect sensor data corresponding to the electronic device. The system also includes a machine learning processor that receives the sensor data and generates a model of the electronic device to determine a T squared threshold and a Q threshold using a machine learning algorithm. The machine learning processor also performs a T squared analysis of the electronic device by comparing a T squared value to the T squared threshold, and a Q analysis of the electronic device by comparing a Q value to the Q threshold. The machine learning processor also determines that the model is faulty when the T squared value is less than the T squared threshold and the Q value is greater than or equal to the Q threshold, and generates a new model or updates the model when the model is determined to be faulty.

Growing community of inventors

Willington, CT, United States of America

Weiqiang Chen