改进粒子群优化BP的数控机床热误差预测研究  

Study in Thermal Error Prediction of NC Machine Tool Based on Improved Particle Swarm Algorithm Optimized Back Propagation

作　　者：袁媛[1] 秦波[1,2] 秦岩[3] 王春暖[1] 吴庆朝 张文兴[2] 

机构地区：[1]包头职业技术学院,内蒙古包头014010 [2]内蒙古科技大学机械工程学院,内蒙古包头014030 [3]浙江大学信息学部控制科学与工程学系,浙江杭州310000

出　　处：《机床与液压》2015年第13期63-66,共4页Machine Tool & Hydraulics

基　　金：内蒙古自然科学基金重大项目(2011ZD08)

摘　　要：由于BP存在网络结构选取基于经验、易陷入局部最优、收敛速度慢等缺陷,致使基于BP的数控机床热误差预测模型精度不高,对此提出了一种改进粒子群优化BP的数控机床热误差预测建模的新方法。通过改进标准粒子群算法中粒子的位置与速度更新策略,以此寻找BP神经网络最优的阈值和权值,在此基础上建立数控机床热误差预测模型。仿真实验结果表明:与标准的BP神经网络和支持向量机相比,改进粒子群优化BP神经网络的数控机床热误差预测模型精度更高、泛化能力更强。Since the selection means of structures of back propagation （BP） neural network having some drawbacks such as, heavily based on human experience, low convergence rate, easy to fall into local optimization and slow speed of covergency, which caused low thermal error predictive accuracy to exist in numerical control （NC） machine tool based on the BP, therefor, a new predic- tive error modelling method based on improved particle swarm optimized BP neural network was proposed. By a updating strategy of par- ticle position and speed based on the improved standard particle swarm alogrithm, the optimized threshold and weight of the BP neural network were found. On basis of it, the thermal error predictive model for NC machine tool was built. The simulation experimental re- suits show that the proposed thermal error predictive method has a higher predictive accuracy, better generalization ability as compared with standard algorithms of BP neural network and support vector machine.

关 键 词：改进粒子群算法 BP神经网络 数控机床 热误差预测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]