Abstract: 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.

Abstract: Systems and methods of testing the health of vehicular power devices are disclosed herein. A method may include producing operating points as a function of cycling current (Ids) and voltage drain to source (Vds) when a subject device is conducting current. The method may further include determining a mean of moving distribution to adapt a center of the moving distribution contrasted with a plurality of known healthy devices. The method may also include indicating an imminent fault in the subject device based upon a discontinuity among operating points above a threshold.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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 T2 and Q statistics, over a time period, and apply a model mismatch and fault detection logic based on the T2 and Q statistics. The model mismatch and fault detection logic may: count consecutive instances where a T2 statistic exceeds a T2 threshold via a T2 counter, update a probability of fault based on the T2 counter, 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.

Abstract: Systems and methods of auto-encoder behavior modelling of vehicle components are described herein. A method for electronic device health prediction may include encoding input data into a reduced feature set via an auto-encoder as part of an artificial neural network. The method may further include decoding the reduced feature set. The method may also include reading the reduced feature set as output. The method may still further include encoding features of a subject device and other devices, wherein at least one of the other devices is designated as a healthy device. The method may additionally include associating the features of the other devices with a healthy device cluster based on a threshold distance. The method may also additionally include associating the features of the subject device with the healthy device cluster, wherein the subject device is flagged as faulty based upon exceeding the threshold distance from the healthy device cluster.

Abstract: Systems and methods of testing the health of vehicular power devices are disclosed herein. A method may include producing operating points as a function of cycling current (Ids) and voltage drain to source (Vds) when a subject device is conducting current. The method may further include determining a mean of moving distribution to adapt a center of the moving distribution contrasted with a plurality of known healthy devices. The method may also include indicating an imminent fault in the subject device based upon a discontinuity among operating points above a threshold.

Abstract: Systems and methods for fault detection and diagnosis in a machine. The method includes selecting fault characteristic frequencies of faults, implementing the fault characteristic frequencies as modulating signals, receiving a feedback signal from at least one sensor associated with a machine, applying active modulation using the modulating signals to the feedback signal to obtain modulated signals, and monitoring for a low-frequency fault indicative component from the modulated signals.

Abstract: 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.

Abstract: 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 T2 and Q statistics, over a time period, and apply a model mismatch and fault detection logic based on the T2 and Q statistics. The model mismatch and fault detection logic may: count consecutive instances where a T2 statistic exceeds a T2 threshold via a T2 counter, update a probability of fault based on the T2 counter, 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.

Abstract: 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.

Abstract: Systems and methods for fault detection and diagnosis in a machine. The method includes selecting fault characteristic frequencies of faults, implementing the fault characteristic frequencies as modulating signals, receiving a feedback signal from at least one sensor associated with a machine, applying active modulation using the modulating signals to the feedback signal to obtain modulated signals, and monitoring for a low-frequency fault indicative component from the modulated signals.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A computer-implemented method for estimating a rotor speed of an alternating current (AC) machine is provided. The method includes determining a stator flux signal based on signals of voltage and current inputs to the AC machine, and determining a rotor flux signal of the AC machine based on the determined stator flux signal. The method includes determining an electrical angle signal based on the determined rotor flux signal, and deriving an electrical frequency signal from the determined electrical angle signal. Subsequently, the method includes sampling the derived electrical frequency signal at a predetermined sampling rate, and storing a predetermined number of sample values. The method further includes evaluating a median value of the predetermined set of electrical frequency sample values, determining a slip frequency value of the AC machine, and determining the rotor speed of the AC machine by subtracting the slip frequency value from the electrical frequency median value.

Abstract: A method for minimizing power losses in an alternating current (AC) machine is provided. The method includes determining a first rotor flux signal based on signals of voltage and current inputs to the AC machine, and extracting a ripple component of the rotor flux signal. The method further includes determining a power compensating value that corresponds to a stored energy value of the AC machine, determining a second rotor flux signal that serves to minimize power losses, and providing the second rotor flux signal to a power inverting unit that adjust accordingly the voltage and current input signals provided to the AC machine.

Abstract: A computer-implemented method for estimating a rotor speed of an alternating current (AC) machine is provided. The method includes determining a stator flux signal based on signals of voltage and current inputs to the AC machine, and determining a rotor flux signal of the AC machine based on the determined stator flux signal. The method includes determining an electrical angle signal based on the determined rotor flux signal, and deriving an electrical frequency signal from the determined electrical angle signal. Subsequently, the method includes sampling the derived electrical frequency signal at a predetermined sampling rate, and storing a predetermined number of sample values. The method further includes evaluating a median value of the predetermined set of electrical frequency sample values, determining a slip frequency value of the AC machine, and determining the rotor speed of the AC machine by subtracting the slip frequency value from the electrical frequency median value.