Fault detection in three phase induction motor using artificial intelligence

Artificial intelligence (AI) techniques have proved their ability in detection of incipient faults in electrical machines. In this project, the fault diagnosis of three phase induction motors is studied detailed in unbalance voltage and stator inter turn fault using simulation models and neural networks have been used to train the data using Radial Basis Function Neural Network (RBFNN) in MATLAB with Graphical User Interface Development Environment (GUIDE) structured. Nowadays artificial intelligence is implemented to improve traditional techniques. The results can be obtained instantaneously after it analyzes the input data of the motor. The increased in demand has greatly improved the approach of fault detection in polyphase induction motor. Data is taken from the experiment checking the induction motor fault and is simulated into MATLAB using RBFNN. The first stage is to collect the data by experimental and simulating a Simulink model using MATLAB. Three Simulink model will be created where each of the model represent the motor condition. The result of the simulation will then be the data used to create an ANN.The second stage creates and trains an ANN. From the data obtained during the first section, a target output will determine the motor condition whether the motor is in a healthy state or fault occurred. In the third stage the development Graphical User Interface (GUI) is carried out this system. The GUI is developed by using MATLAB for the purpose of evaluating and testing the ANN. The purpose of this final year project, the development of Fault Detection in Three-Phase Induction Motor Using Artificial Intelligence is to satisfy the increased in demand to improve the approach of fault detection in polyphase induction motor. Artificial intelligence is implemented to improve traditional techniques, as the results can be obtained instantaneously after it analyzes the input data of the motor where it can be accomplished without an expert