The paper deals with the analysis of an artificial neural network(ANN) approach suitable for online faults detection of inductionmachines. The aim of this paper is to develop an alternative withrespect to traditional fault detector techniques that overcomes thelimitations of present technology. After an analytical discussion abouttheoretical principles and relations used for the diagnosis ofelectrical machines failures, a simple ANN algorithm is presented andtested. The results prove the feasibility of to tool arranged by meansof artificial neural network for a fast and accurate detection of statorfaults in induction machines. Furthermore a good accuracy of the resultshave been achieved notwithstanding the great simplicity of the algorithmwith respect to a complete model arranged by a space vector analysis
展开▼