Wear Faults Prediction Model Based on SVR Optimized by ABC
Deng Jianqiu;Zhao Jianzhong;Chen Hong;Cong Linhu;Department of Ordnance Science & Technology,Navy Aeronautical University;The Ninth Research Laboratory,No.713 Research Institute,China Shipbuilding Industry Corporation;
In order to improve the prediction accuracy of wear faults, we propose a wear faults prediction model(ABC-SVR), which is based on support vector machine for regression(SVR) optimized by artificial bee colony(ABC) algorithm and aims at the parameter optimization issue in regard to support vector machine for regression. The model reconstructs the time series of wear faults according to chaos theory, and then takes the wear faults prediction accuracy as the optimization objective; it finds the optimal SVR parameters by ABC algorithm, and builds prediction model of wear faults. Finally, we use simulative contrasting experiment to test the performance of the model. Simulation results show that compared with other models in the experiment, ABC-SVR solves SVR parameter optimization problem, and can describe the complicated change rules of wear faults, as well as improves the accuracy of wear faults prediction.
【CateGory Index】： TP18