Experimental study of intelligent fault diagnosis based on maximum likelihood estimation features and artificial neural networks

The rotating machinery is a common class of machinery in the industry. The root cause of faults in the rotating machinery is often faulty rolling element bearings. This paper presents a novel technique using artificial neural network learning for automated diagnosis of localized faults in rolling element bearings. The inputs of this technique are a number of features (maximum likelihood estimation values), which are extracted from the vibration signals of the test data. Effectiveness and novelty of this proposed method are illustrated by using the experimentally obtained the bearing vibration data based on laboratory application that are inner and outer race bearing faultvibration measurements consists of radial vibration measurements taken on the bearing housing of the machinery fault simulator test rig with a known inner and outer race bearing faults. The results show that the accuracy of the proposed approach is 100% by using radial basis function and multi-layer perceptron neural networks, even though it uses only two features

Experimental study of intelligent fault diagnosis based on maximum likelihood estimation features and artificial neural networks Keywords:

Experimental study , Intelligent bearing fault diagnosis , Maximum likelihood estimation feature , artificial neural network learning