Neuronowy detektor uszkodzeń łożysk tocznych

Early detection of rolling bearing faults in induction motors is very important task in the exploitation of electrical motors due to the consequences of the their damage. In the article the possibility of the neural networks application for the detection of bearing faults (such as: balls, outer and inner races) in induction motors is presented. The training and test of the neural network used data obtained from the experiments carried out on a set of specially made bearing damage. To the test used amplitudes of the characteristics frequency obtained from the spectral analysis of the mechanical vibrations and the envelope analysis.