Method for Estimating Bearing Fault Severity for Induction Motors

A method for estimating a severity of a bearing fault in an induction motor, wherein the method uses a processor coupled to a memory storing a set of filters, each filter is configured to extract a fault current of a fault frequency from the stator current, the set of filters includes a first filter to extract a first fault current of a first fault frequency and a second filter to extract a second fault current of a second fault frequency;

• a set of quantitative models, each quantitative model is configured to relate the fault current of the fault frequency to a mutual inductance variation for the fault frequency, the set of quantitative models includes a first quantitative model to relate a magnitude of the first fault current to a first mutual inductance variation for the first fault frequency and a second quantitative model to relate the second fault current to a second mutual inductance variation for the second fault frequency;
• and at least one fault severity classifier for estimating a severity of the fault in the induction motor for each of the fault frequency based on the mutual inductance variation for the fault frequency, wherein the processor is coupled with stored instructions implementing the method, wherein the instructions, when executed by the processor carry out steps of the method, comprising:
• accepting measurements of a stator current during an operation of the induction motor;
• extracting the first fault current from the stator current using the first filter, determining the first mutual inductance variation from the first fault current using the first quantitative model, and classifying the first mutual inductance variation with the fault severity classifier to determine the severity of a first type of fault in the induction motor;
• extracting the second fault current from the stator current using the second filter, determining the second mutual inductance variation from the second fault current using the second quantitative model, and classifying the second mutual inductance variation with the fault severity classifier to determine the severity of a second type of fault in the induction motor;
• and
• outputting one or combination of the severity of the first type of fault in the induction motor and the severity of the second type of fault in the induction motor.

A non-transitory computer readable storage medium embodied thereon a program executable by a processor for performing a method, the storage medium stores a set of filters, each filter is configured to extract a fault current of a fault frequency from the stator current, the set of filters includes a first filter to extract a first fault current of a first fault frequency and a second filter to extract a second fault current of a second fault frequency;

• a set of quantitative models, each quantitative model is configured to relate the fault current of the fault frequency to a mutual inductance variation for the fault frequency, the set of quantitative models includes a first quantitative model to relate a magnitude of the first fault current to a first mutual inductance variation for the first fault frequency and a second quantitative model to relate the second fault current to a second mutual inductance variation for the second fault frequency;
• and at least one fault severity classifier for estimating a severity of the fault in the induction motor for each of the fault frequency based on the mutual inductance variation for the fault frequency, the method comprising:
• accepting measurements of a stator current during an operation of the induction motor;
• extracting the first fault current from the stator current using the first filter, determining the first mutual inductance variation from the first fault current using the first quantitative model, and classifying the first mutual inductance variation with the fault severity classifier to determine the severity of a first type of fault in the induction motor;
• extracting the second fault current from the stator current using the second filter, determining the second mutual inductance variation from the second fault current using the second quantitative model, and classifying the second mutual inductance variation with the fault severity classifier to determine the severity of a second type of fault in the induction motor;
• and
• outputting one or combination of the severity of the first type of fault in the induction motor and the severity of the second type of fault in the induction motor.