Distributed architecture for fault monitoring

A method of detecting an anomaly in a power semiconductor device, the method comprising:

• receiving sensed data, by a local component of a distributed system, the local component comprising one or more sensors positioned adjacent to the power semiconductor device, the one or more sensors, the sensed data corresponding to sensed properties of the power semiconductor device comprising a device cycling current, a change in device temperature, a normalized junction-to-ambient thermal resistance, a power step, a device maximum junction temperature, a device minimum junction temperature, a Vcold measurement, a Vhot measurement, and a Von measurement;
• designating, by the local component of the distributed system, a first portion of the sensed data as testing data and a second portion of the sensed data as training data;
• transmitting, by the local component of the distributed system, the training data to a server computing device of the distributed system, wherein the server computing device is remotely located from the local component;
• processing, by the server computing device of the distributed system, the training data through one or more of a machine learning algorithm, a fault diagnostic algorithm, and a fault prognostic algorithm to generate a set of eigenvalues and associated eigenvectors based on the properties;
• selecting, by the server computing device of the distributed system, a selected set of eigenvalues and associated eigenvectors;
• and
• statistically analyzing, by the processing device of the local component of the distributed system, the selected set of eigenvalues and associated eigenvectors to determine whether the testing data is indicative of the anomaly.

A method of detecting an anomaly in a power semiconductor device, the method comprising:

• receiving sensed data, by a local component of a distributed system, the local component comprising one or more sensors positioned adjacent to the power semiconductor device, the one or more sensors, the sensed data corresponding to properties of the power semiconductor device comprising a device cycling current, a change in device temperature, a normalized junction-to-ambient thermal resistance, a power step, a device maximum junction temperature, a device minimum junction temperature, a Vcold measurement, a Vhot measurement, and a Von measurement;
• designating a first portion of the sensed data as testing data and a second portion of the sensed data as training data;
• transmitting the training data to a server computing device that is remotely located from the processing device;
• receiving processed data from the server computing device, the processed data comprising information generated as a result of an application of one or more of a machine learning algorithm, a fault diagnostic algorithm, and a fault prognostic algorithm to the sensed data;
• and
• statistically analyzing the processed data to determine whether the testing data is indicative of the anomaly.