×

Radial basis function neural network autoassociator and method for induction motor monitoring

  • US 5,640,103 A
  • Filed: 05/22/1996
  • Issued: 06/17/1997
  • Est. Priority Date: 06/30/1994
  • Status: Expired due to Fees
First Claim
Patent Images

1. 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.

View all claims
  • 0 Assignments
Timeline View
Assignment View
    ×
    ×