对比版基于组合式改进BP网络的设备托管与租赁风险预测模型..doc

基于组合式改进BP网络的设备托管与租赁风险预测模型 摘要：设备有偿托管与租赁是现代化服务业的重要服务业务，针对个体设备闲置、区域有所需求、租赁调度不合理的问题，将有偿托管与租赁风险管理的样本数据和模糊神经网络相结合，并根据改进BP神经网络确定网络的输入和输出向量，对有偿托管与租赁管理进行组合式风险预测，并利用实例测算对比，结果表明：预测结果与实际情况比较吻合。运用MATLAB数据软件实现神经网络风险预测仿真，仿真结果表明预测误差较小，输出向量与实际风险矩阵结果接近。指出其在判断有偿托管与租赁管理风险状况、分析有偿托管与租赁管理风险的主要来源、提出企业规避有偿托管与租赁管理风险的对策方面有较大的应用价值。 关键词：设备托管；租赁服务；改进BP算法；故障诊断；神经网络；预警模型 中国分类号：F224.10 文献标示码：A Equipment trust and Rental problem Risk Pre-warning Model based on Modular Combined Improved BP neural network Tian Ying1 Zhong Wei-qing1 Wang Cheng1、2 (1 Liaoning Technical University,Fuxin,123000, China；2 Jilin coal industry group, Changchun, P.R.China) Abstract: Equipment paid hosting and leasing is an important services modern service industry, Aiming at the faults occurring currently ,individual equipment idle, areas of demand, leasing scheduling unreasonable。Combined paid hosting and leasing risk management sample data and fuzzy neural network, confirmed input and output vector of network according to the improve BP network and diagnosed the fault of paid hosting and leasing risk management。The diagnosis is consistent with the reality. Use MATLAB to simulate neural network fault diagnosis and the simulation results show that the diagnosis error is small, output vector and the actual fault matrix results are approximate. It have great application value for the judge paid hosting and lease management risk, analyse paid hosting and lease management risk main origin, proposed enterprise avoid paid hosting and lease management risk. Keywords: Equipment trust ; Rental ;improve BP algorithm; Fault diagnosis ; neural network; Early warning model 设备有偿托管与租赁是现代化服务业的重要服务业务，针对大矿业服务需求，区域范围内个体设备闲置、调度、配置、租赁分散，业务实施过程中存在设备使用到期未能及时归还、设备调度不通畅、租赁单位提前违约不租赁等现象，这对于煤矿生产中分秒必争的生产工艺来说，必将产生运营及生产的风险。 The equipment collocation with payment and leasing is an important modern service business. For the requirement of the mining service,there exists many phenomena such as,leaving the equipment unused,controlling ,allocat