Three-Phase Induction Motors Faults Recognition and Classification Using Neural Networks and Response Surface Models

[摘要] Three-phase induction motors are very robust machines and can be exposed to a wide variety of environmental and operating conditions, what can result in a number of failures during their use. The early detection of faults can prevent these electric motors degradation or even complete breakdown. In this work, five neural networks models with a decision structure, and five response surface models to classify the engine data operating in normal condition or in four failures conditions that can occur in an induction motor: voltage supply unbalance, initial stator coil windings short circuit, mechanical faults, and broken bars are proposed. The proposed technique utilizes current information and it is robust to load variations. The results show the good performance of the implemented model and its ability to identify the faults established for the proposed work...

[学科分类] 自动化工程

[关键词] Three-phase induction motors ;Fault detection ;Neural networks ;Response surface