基于GA-BP神经网络的数控插齿机热误差建模  

Thermal error modeling of CNC gear shaper based on GA-BP neural network

作　　者：李淋 谭人铭 汪静姝 LI Lin;TAN Renming;WANG Jingshu(College of Mechanical Engineering,Chongqing University of Technology,Chongqing 400054,China)

机构地区：[1]重庆理工大学机械工程学院,重庆400054

出　　处：《重庆理工大学学报（自然科学）》2022年第7期126-131,共6页Journal of Chongqing University of Technology：Natural Science

基　　金：国家重点研发计划(2019YFB1703700);重庆市技术创新与应用发展专项重点项目(cstc2019jscx-mbdxX0045);重庆市技术创新与应用发展专项重点项目(cstc2019jscx-mbdxX0016)。

摘　　要：热误差作为影响数控插齿机加工精度的重要因素之一,而目前有关插齿机的热误差补偿相关资料欠缺。提出基于GA-BP神经网络的机床热误差优化建模方法,针对插齿机减少其热误差,提高加工精度。针对神经网络算法较多,但补偿效果仍存差距,因此比较了遗传算法(GA)和BP神经网络算法,介绍GA-BP神经网络模型的具体步骤,以YKS5132DX3型数控插齿机为实验对象,获得了敏感点温度和主轴X、Y方向的热误差值,在此基础上,建立BP神经网络热误差预测模型和GA-BP网络热误差优化模型。实验结果表明:与BP神经网络热误差模型相比,GA-BP神经网络热误差模型的预测精度更高,残差变化幅度较平稳,稳健性强。Thermal error is one of the important factors affecting the machining accuracy of CNC gear shaper, and the relevant data about thermal error compensation of gear shaper are lacking at present. In this paper, a modeling method of thermal error optimization based on GA-BP neural network is proposed to reduce the thermal error of gear shaper, and improves the machining accuracy. There are many neural network algorithms, but there is still a gap in compensation effect. Therefore, this paper compares genetic algorithm(GA) and BP neural network algorithm, and introduces the specific steps of GA-BP neural network model. To taking YKS5132 DX3 CNC gear shaper as the experimental object, the sensitive point temperature and the thermal error value of spindle XY direction are obtained. BP neural network thermal error prediction model and GA-BP network thermal error optimization model are established. Experimental results show that compared with BP neural network thermal error model, GA-BP neural network thermal error model has higher prediction accuracy, more stable residual variation range and stronger robustness.

关 键 词：BP神经网络 GA-BP神经网络 数控插齿机 稳健性 

分 类 号：TH161.4[机械工程—机械制造及自动化]