MODEL BASED FAULT DETECTION SYSTEM FOR ELECTRIC MOTORS

摘要

PURPOSE: A model based fault detection system is provided to monitor and predict maintenance requirements of electric motors and can reduce costs by software and data obtained from measurements. CONSTITUTION: A model based fault detection system for electric motors includes sensors coupled to motor which provide continuous real time information of the input voltage and current and motor speed, computer means coupled to sensors, and a multi variable experimental modeling algorithm to obtain a mathematical description of the motor. Reliable 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. Upon detection of the impending fault, the diagnostic observer evaluates the measured variables of the motor, determines the deviation from the reference value and develops a diagnosis of the likely failed or failing component. Another model is particularly useful in the manufacture of fractional horsepower electric motors and especially in the performance of quality control testing.