System and method for eccentricity severity estimation of induction machines using a sparsity-driven regression model
View Patent ↗A fault detection system of eccentricity severity of an induction machine including a rotor and stator is provided. The fault detection system includes a sensor interface configured to acquire sensor signals from sensors arranged at predetermined positions of the induction machine, wherein the sensor signals are indicative of an eccentricity level of a rotor of the induction machine, a memory coupled with a processor. The memory stores training data sets and instructions implementing a learning-based fault detection method for the induction machine. The instructions include steps of generating an eccentricity feature matrix from the sensor signals, where in the sensor signals include load torque, rotor speed, vibration acceleration of the rotor, vibration speed of the rotor, and current spectral of the stator or the induction machine, determining an eccentricity level of the induction machine based on the eccentricity feature matrix using the learning-based fault detection method, wherein the learning-based fault detection method is configured to find the eccentricity level from learning-based eccentricity feature matrix data sets.
1 . A fault detection system for an induction machine including a rotor and stator, comprising:
a sensor interface configured to acquire sensor signals from multiple types of sensors, wherein the sensor signals are indicative of operational parameters of the induction machine;
a memory configured to store instructions implementing a sparsity-driven regression model for the induction machine, wherein the sparsity-driven regression model is trained for predicting an eccentricity level of the induction machine; and
a processor configured to execute the instructions to:
generate an eccentricity feature matrix for the induction machine based on the sensor signals;
determine the eccentricity level of the induction machine based on the-eccentricity feature matrix and the sparsity-driven regression model;
generate one or more control commands based on the determined eccentricity level; and
control the induction machine based on the generated one or more control commands.
2 . The fault detection system of claim 1 , wherein the eccentricity level is defined in terms of operating conditions of the induction machine, wherein the operating conditions include load applied to the induction machine, rotating speed of the rotor, vibration, and current spectral feature of the stator.
3 . The fault detection system of claim 1 , wherein the sensor interface is configured to acquire the sensor signals iteratively for a predetermined time period.
4 . The fault detection system of claim 2 , wherein eccentricity-associated frequency domains of the current spectral feature are determined at approximately a half of an operation frequency of the induction machine and approximately one and a half of the operation frequency.
5 . The fault detection system of claim 4 , wherein the current spectral feature corresponds to a 90 Hz frequency component.
6 . The fault detection system of claim 1 , wherein the sensors include gap sensors and acceleration sensors.
7 . The fault detection system of claim 1 , wherein all elements of the eccentricity feature matrix are normalized to have mean and unit variance.
8 . The fault detection system of claim 1 , wherein the fault detection system is included as part of a maintenance system of a user.
9 . The fault detection system of claim 1 , wherein when the determined eccentricity level of the induction machine is equal to or greater than a critical threshold level, the processor is configured to transmit a control signal to a controller of the induction machine via a network to stop operating the induction machine.
10 . A computer implemented method for controlling an induction machine, comprising:
acquiring measurements indicative of operational parameters of the induction machine;
generating an eccentricity feature matrix for the induction machine based on the measurements, wherein the eccentricity feature matrix comprises a plurality of parameters of a state of an operation of the induction motor;
determining an eccentricity level of the induction machine based on the eccentricity feature matrix and a sparsity driven regression model that is trained for predicting the eccentricity level of the induction machine;
generating one or more control commands based on the determined eccentricity level; and
controlling the induction machine based on the generated one or more control commands.