Stator Fault Detection in the Induction Motor by Measuring the Components Temperatures

In this article the operational status of the induction motor is determined by measuring temperature of its components. This process consists of four sections: 1-Thermal resistance model 2- Electrical model 3-Modeling of short circuit fault in stator windings and 4- Neural network which presents motor parameters and operational status compatible with corresponding learning data. In thermal resistance model, we use physical and geometrical properties of motor components to formulate thermal resistance of each component of the motor. In electrical model, electrical losses are calculated by electrical variables. In neural network the temperature of the motor components is used as input data and stator current as target data. In fault modeling section, we had two groups of stator currents; currents that are due to phase to phase short circuit and the ones that are caused by turn to turn short circuit in the stator. All three groups (two faults plus one normal) are used as input data in the electrical model of the motor and the model gives us corresponding temperatures as output. These temperatures were used for training network (temperatures as input data and stator current as target data) in the neural network. After measuring temperatures of the components and using them as inputs to neural network, the corresponding stator current (target data) is estimated. The estimated current with minimum distance from the three groups determines the motor status. All the stator currents referred to this paper were validated by experimental measurements.

کلیدواژه ها:

Induction motor ، Thermal resistance model ، Short circuit fault in stator winding