本文已被：浏览 1700次 下载 2926次
Received:July 15, 2011 Revised:August 22, 2011
Received:July 15, 2011 Revised:August 22, 2011
中文摘要: 将HJPSO算法引入BP神经网络中并建立优化的BP网络模型，克服了标准BP网络在实际应用预测中易陷入局部极小点、收敛速度慢的缺点。通过本模型对汽车齿轮热处理进行了预测研究。研究结果表明优化后的BP网络比标准BP网络具有较高的预测能力和稳定性。
中文关键词: BP神经网络 粒子群算法 Hooke-Jeeves模式搜索法 齿轮热处理 预测
Abstract:The neural network model based on Hooke-Jeeves Particle Swarm Optimization(HJPSO) is proposed in this paper for overcoming some shortcomings of BP neural network that is slow at the convergence rate and easy to trap in local minimum.This improved model has utilized prediction of gear heat treatment.The experimental data shows the effect of the improved BP neural model is much better than standard BP neural network in term of the predicting ability and stability.
keywords: BP neural network PSO algorithm Hooke-Jeeves pattern search method gear heat treatment prediction
文章编号： 中图分类号： 文献标志码：
基金项目:国家自然科学基金(60963002);江西省教育厅青年科学基金(GJJ11165)
引用文本：
韩月娇,董华.HJPSO-BP算法在齿轮热处理预测中的应用.计算机系统应用,2012,21(4):193-197
HAN Yue-Jiao,DONG Hua.Predictive Application of Gear Heat Treatment Based on HJPSO-BP Algorithm.COMPUTER SYSTEMS APPLICATIONS,2012,21(4):193-197
韩月娇,董华.HJPSO-BP算法在齿轮热处理预测中的应用.计算机系统应用,2012,21(4):193-197
HAN Yue-Jiao,DONG Hua.Predictive Application of Gear Heat Treatment Based on HJPSO-BP Algorithm.COMPUTER SYSTEMS APPLICATIONS,2012,21(4):193-197
