Abstract: The present invention relates to fault detection in a large population of motors of a common motor type. Initially, a plurality of motors of a common motor type is tested to obtain a first residual based on selected measured operating parameters. A second residual is then developed for each individual motor comprising the plurality of motors. If the difference between the first and second residuals exceeds a selected threshold, the motor generating the second residual is defective and removed from the plurality of motors and the threshold is adjusted to reflect the removal of the defective motor from the plurality of motors. The first residual may be used to monitor the operation of motors not included in the original plurality of motors to detect impending failure.

Abstract: The present invention relates to a model based fault detection system and method for monitoring and predicting maintenance requirements of electric motors. Since, the method and system of the present invention is software based and utilizes data obtained from no-intrusive measurements, implementation costs are significantly less than prior art maintenance methods.The system comprises computer means coupled to sensors which provide continuous real-time information of the input voltage and current and motor speed. The system and method utilize a multivariable experimental modeling algorithm to obtain a mathematical description of the motor. The algorithm compares the modeled result with a measured result and quantifies the comparison in terms of a residual which is generated by subtracting the respective signals. A diagnostic observer analyzes the residual and determines if the motor is fault free or operating in a manner other than fault free.