Abstract A method for detecting a departure from normal operation of an electric motor comprises obtaining a set of normal current measurements for a motor being monitored; forming clusters of the normal current measurements; training a neural network auto-associator using the set of normal current measurements; making current measurements for the motor in operation; comparing the input and output of the auto-associator; and indicating abnormal operation whenever the current measurements deviate more than a predetermined amount from the normal current measurements. The method models a set of normal current measurements for the motor being monitored, and indicates a potential failure whenever measurements from the motor deviate significantly from a model. The model takes the form of an neural network auto-associator which is "trained"--using clusters of current measurements collected while the motor is known to be in a normal operating condition--to reproduce the inputs on the output. A new set of FFT's of current measurements are classified as "good" or "bad" by first transforming the measurement using a Fast Fourier Transform (FFT) and an internal scaling procedure, and then applying a subset of the transformed measurements as inputs to the neural network auto-associator. A decision is generated based on the difference between the input and output of the network.
A method for detecting a departure from normal operation of an electric motor, comprising: obtaining a set of current measurements for a motor being monitored during a training phase, said motor being known to be operating normally; processing said set of current measurements so as to provide current measurement training vectors; forming clusters of said current measurement vectors during said training phase; applying said clusters of current measurement vector to a neural network auto-associator and training said neural network auto-associator using said set of normal current measurements; making a set of operational current measurements for said motor in actual operation; processing said of operational current measurements so as to provide an operational current measurement vector; applying said operational current measurement vector to said neural network auto-associator; comparing said set of current measurements with the output of said neural network auto-associator; and indicating abnormal operation whenever said comparing produces a result in accordance with predetermined criteria.
Claim 2
Independent Claim
155 words
A method for detecting a departure from normal operation of an electric motor, comprising: obtaining a set of current measurements for a motor being monitored during a training phase, said motor being known to be operating normally; processing said set of current measurements so as to provide current measurement training vectors; forming clusters of said current measurement vectors during said training phase; applying said clusters of current measurement vector to a neural network auto-associator and training said neural network auto-associator using said set of normal current measurements; making a set of operational current measurements for said motor in actual operation; processing said of operational current measurements so as to provide an operational current measurement vector; applying said operational current measurement vector to said neural network auto-associator; comparing said set of current measurements with the output of said neural network auto-associator; and indicating abnormal operation whenever said comparing produces a result in accordance with predetermined criteria.
Claim 3
Dependent Claim
35 words
A method for detecting a departure from normal operation of an electric motor in accordance with claim 1, wherein said processing steps comprise deriving a set of frequency spectral components by Fast Fourier Transform (FFT).
Claim 4
Dependent Claim
33 words
A method for detecting a departure from normal operation of an electric motor in accordance with claim 2, wherein said processing steps comprise scaling said frequency spectral components in accordance with predetermined weights.
Claim 5
Dependent Claim
36 words
A method for detecting a departure from normal operation of an electric motor in accordance with claim 3, wherein said processing steps comprise segmenting said current measurements prior to deriving said set of frequency spectral components.