Charging and discharging device reliability prediction based on neural network

WANG Chong-fang, HE Tong-neng, WANG Ze-kai

(College of Information and Engineering, Zhejiang University of Technology, Hangzhou 310023, China)

Abstract: Aiming at achieving a more accurate charging and discharging device reliability prediction the issue was discussed, By studying the role and relationship of all elements of the overall equipment efficiency (OEE), the available efficiency (AE) was selected as the target of charging and discharging device reliability prediction. Meanwhile, because of limitations of the traditional reliability prediction methods, a reliability prediction method based on the neural network was proposed. During establishing the BP neural network, each function module of the charging and discharging device was considered. Then, the appropriate parameters were selected as the neural network input. By increasing the number of neurons in the hidden layer was expected to improve the accuracy of the method. After selecting the appropriate parameters and sample data, the simulation experiment was conducted. The results indicated that using this method for charging and discharging device reliability could be expected to achieve good results.

Key words: reliability prediction; charging and discharging device; overall equipment efficiency (OEE); availability efficiency (AE); neural network