Fault Identification in Induction Motor Using Lab View

Fault detection method for induction motors using LabView is done. The aim is to identify faults in the motor and classify them into different categories such as bearing faults, broken rotor bars, and stator faults. Mechanical and electromechanical systems are mostly propelled by electrical motors in today's manufacturing sectors. Due to the improved performance characteristics of AC induction motors compared to DC motors, industrial automation is now often carried out using them. The induction motor accounts for almost 50% of all electrical power usage worldwide. Because it has essential qualities including automatically self-starting, not requiring a permanent magnet, brushes, commutator rings, or position sensors, induction motors are 90% used in industry. The key benefit of an induction motor is that its speed can be readily controlled due to its strong starting torque, superior speed regulation, and sustained overload capacity. The proposed method uses LabView for data acquisition and signal processing, and a support vector machine (SVM) for classification. The SVM is trained using features extracted from the motor current signal, such as statistical parameters and wavelet coefficients. The proposed method is evaluated on a 3-phase induction motor with different fault scenarios, and the results show that it can detect and classify faults with high accuracy. The proposed method has the advantage that it does not require any additional sensors or hardware, and it can be easily integrated into existing motor control systems.