Degradation process prediction for rotational machinery based on hybrid intelligent model

Bearings are among the most critical and precise components in rotational machinery. The condition and health of bearings play an important role in the functionality and performance of rotational machinery. Since a neural network ensemble approach shows significantly improved generalization performance and outperforms those of a single neural network, one novel selective neural network ensemble model is developed for bearing degradation process prediction. An improved particle swarm optimization with simulated annealing is proposed to select the optimal subset formed by accurate and diverse networks and obtain a better ability to escape from the local optimum. An experimental setup to perform fatigue testing on ball bearings and several simulations are explored in order to validate the developed prediction model. Experimental results show that degradation process prediction based on the explored selective neural network ensemble model provides a means of enhancing the monitoring of ball bearings' condition, and the results of this model are superior in comparison with the results of a single neural network. This selective neural network ensemble model can be used as one excellent predictive maintenance tool in plants. (C) 2011 Elsevier Ltd. All rights reserved.