GAI Qiang(盖强)1, LIU Yong（刘勇）1, ZHAO Hong-yu（赵宏宇）2
(1. Department of Naval Gun, Dalian Naval Academy, Dalian 116018, China; 2. Department of International Military Exchange, Dalian Naval Academy, Dalian 116018, China)
Abstract： Due to the fact that in ship maintenance process, the method of determining the number of spare parts is not scientific and the actual operation is complicated, this paper analyzes four major factors affecting the number of ship spare parts, including number of main planned operations, total times of disassembling in maintenance, accumulated working time and mean time between failures. It also establishes a spare parts demand forecast model based on the affecting factors and radial-basis function (RBF) neural network. Finally, the paper provides forecast examples and makes a comparison between the examples and back propagation (BP) neural network forecast result. The comparison results show that the forecast based on RBF neural network is simple and the forecast result fits the actual situation and fitting effect is better than that based on BP.
Key words：spare parts forecast; neural network; equipment support
CLD number： TP183 Document code： A
Article ID： 1674-8042(2013)02-0167-03 doi： 10.3969/j.issn.1674-8042.2013.02.016
References
[1] CAO Jing. How to set up the reserves of system spare parts. Chengdu: Southwest Jiaotong University, 2008: 11-12.
[2] YANG Bo-wen, LIU Fei, LIU Kan. Assessment method of missile maintenance parts needs based on reliability. Microcomputer & Its Application, 2011, 30(7): 94-95.
[3] LI Shi-ting, ZHU Bo, CHEN Li-sheng. Decision making study based on reliability on optimum storage quantity of concomitant maintenance spare parts of marine navigation. China Shiprepair, 2005,(1): 36-38.
[4] JI Hong. Research on the optimization method of inventory and allocation of ship spare parts. Master's thesis, Dalian: Dalian Maritime University, 2010: 1-2.
[5] LI Han, ZHOU Dong-jun, ZHANG Feng. Demand forecast for air-launched missile spare based on BP neural network. Journal of Naval Aeronautical and Astronautical University, 2010, 25(4): 457-461.
[6] BI Yi-ming, WANG Han-gong. Research on the consumption standard model of weapon’s equipment spare. Journal of the Academy of Equipment Command & Technology, 2004, 15(1): 1-4.
[7] YANG Shan, WANG Shao-hong, WANG Ji-fang. Fault diagnosis of gas turbine based on BP nerve network. Microcomputer Information, 2010, (22): 107-108, 177.
[8] HAN Li-qun. Education of nerve network. Beijing: Publishing House of Peiking University of Post and Telecommunication. 2007: 127.
[9] Gori M, Tesi A. On the problem of local minima in back propagation. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1992, 14(1): 76-86.
[10] ZHANG De-feng. Application of Matlab in nerve network simulation. Beijing: China Machine Press, 2009: 182-184.
[full text view]
