GA-BP神经网络在轧辊磨床中心架支撑头定位精度预测中的应用  

Application of GA-BP Neural Network in Prediction of Positioning Accuracy of Supporting Heads of Roll Grinder Center Rests

作　　者：郭强 吴怀超[1] 王静 黄鹏 GUO Qiang;WU Huai-chao;WANG Jing;HUANG Peng(College of Mechinical Engineering,Guizhou University,Guizhu Guiyang 550025,China)

机构地区：[1]贵州大学机械工程学院,贵州贵阳550025

出　　处：《机械设计与制造》2021年第12期174-177,182,共5页Machinery Design & Manufacture

基　　金：贵州省科技重大专项(黔科合重大专项字[2019]3016号);贵州省科技创新人才团队项目(黔科合平台人才[2020]5020);贵州大学培育项目(贵大培育[2019]02号);贵州省高层次创新型人才培养计划项目(黔科合平台人才[2016]5659)。

摘　　要：轧辊磨床中轧辊磨床中心架支撑头的定位精度是决定轧辊的加工精度重要因素。通过对现有轧辊磨床中心架研究,发现现有轧辊磨床中心架的定位精度已无法满足生产需求。针对现有轧辊磨床中心架定位精度低的问题,提出对轧辊磨床中心架支撑头进行预测定位,在BP神经网络的基础上,引入遗传算法(GA),利用遗传算法优化BP神经网络的权值和阈值,提高神经网络的训练精度,加快网络收敛,运用优化后的BP神经网络对轧辊磨床中心架支撑头的升降部件的定位精度进行预测。仿真结果表明,GA-BP神经网络比BP神经网络的预测准确度高7%左右,迭代次数缩减一半,预测结果到达要求。The positioning accuracy of supporting heads of center rests of roll grinder is an important element to determine the processing accuracy of rolls. Through the research of the existing center rests of roll grinder, the author finds that the existing center rests of roll grinder cannot meet the need of production. Therefore, the paper puts forward a method of predicting and locating supporting heads of roll grinder center rests aiming at the problem of low positioning accuracy of the existing center rests of roll grinder. On the basis of back propagation(BP)neural network, genetic algorithm(GA)is introduced to optimize weights and thresholds of BP neural networks, so as to improve the training accuracy of the neural network and accelerate convergence of the network.The positioning accuracy of lifting parts of supporting heads of roll grinder’s center rests is predicted by using the optimized BP neural network. The simulating result shows that the prediction accuracy of GA-BP neural network is about 7% higher than that of BP neural network, the number of iterations is reduced by half, and the predicted result meets the requirements.

关 键 词：轧辊磨床中心架 神经网络 遗传算法 定位精度 

分 类 号：TH16[机械工程—机械制造及自动化] C930[经济管理—管理学]