Electric Motor Bearing Diagnosis Based on Vibration Signal Analysis and Artificial Neural Networks Optimized by the Genetic Algorithm

The artificial neural networks (ANN) by their capacities of training, classification, and decision, give a solution to bearing diagnosis problem by the automatic classification of the vibratory signals corresponding to the various states the machines. They are intended to increase the precision(accuracy) and to reduce errors caused by subjective human judgments. However it is important to note that the ANNs in the aids to diagnosis must be set for optimum performance. The non-existence of predefined rules for ANNs parameters setting (number of hidden neurons in each hidden layers etc.) obstruct the achievement of optimal performances. The use of genetic algorithm (GA) can solve this problem by the parameters and structure optimization of ANN. This paper discusses the use of the ANN multilayer Perceptron (MLP), for the diagnosis of electric motor bearings, by the automatic classification of the various operating conditions the machine. The signals taken from the experimental test rig are processed by using various methods of signal processing. The calculated indicators were used to build the patterns vector, which is used for the following to train and test of the network. The GA are used to search(optimize) the structure and the various parameters of the network, which simplifies the neural network structure and makes the training process more efficient and giving the best performances of the network.