基于混沌神经网络的钻削力在线预测  

On-line Prediction of Drilling Force Based on Chaotic Neural Network

作　　者：陈菁瑶[1,2] 苗鸿宾[1,2] 刘兴芳[1,2] 刘娜[1] CHEN Jing-yao;MIAO Hong-bin;LIU Xing-fang;LIU Na(School of Mechanical and Power Engineering,North University of China,Taiyuan 030051,China;Shanxi Province Deep Hole Machining Center,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学机械与动力工程学院,太原030051 [2]中北大学山西省深孔加工工程技术研究中心,太原030051

出　　处：《组合机床与自动化加工技术》2018年第3期110-113,共4页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：山西省回国留学人员项目基金(2015-077)

摘　　要：针对深孔加工中钻削力和扭矩测量难的问题以及BP神经网络本身存在的缺陷,利用混沌遗传算法优化的BP神经网络对深孔钻削时产生的钻削力和扭矩进行在线预测。通过混沌遗传算法优化BP神经网络的初始权值和阈值,用优化后得到的最优解作为BP网络算法的初始权值和阈值。以BTA钻削为例,通过实验获得不同钻头直径,转速和进给量条件下的多组轴向力和扭矩。利用MATLAB建立优化后的BP神经网络预测模型,对轴向力和扭矩进行预测分析。并与传统BP神经网络获得的预测结果进行对比。结果表明,利用混沌遗传算法优化的BP神经网络模型很好的克服了传统BP网络收敛速度慢、易陷入局部最小值的缺陷,预测结果更加准确,为钻削力和扭矩的在线预测提供了新的思路。For the problem of drilling force and torque measurement in drilling process and defects of BP neural networks itself,the chaotic neural network is used to predict drilling force and torque.The chaotic genetic algorithm is used to optimize the initial weights and thresholds of BP neural networks in this article.The chaotic variable is added to the genetic algorithm to improve the global search ability and convergence speed of the genetic algorithm.The optimal solution obtained by the chaotic genetic algorithm is used as the initial weight and threshold of the BP network algorithm.Taking BTA drilling as an example,several groups of axial forces and torques are obtained through experiments under different bit diameters,speeds and feed rates.The optimized BP neural network prediction model is established by using MATLAB,and the axial force and torque are predicted and analyzed.The prediction results are compared with those obtained by the traditional BP neural network.The results show that optimized BP neural network can overcome the defects existing in traditional BP network such as slow convergence rate and easy to fall into local minimum,require more accurate prediction results,and provides a new idea for online prediction of drilling force and torque.

关 键 词：BTA钻削 轴向力 扭矩 BP神经网络 混沌遗传算法 预测 

分 类 号：TH122[机械工程—机械设计及理论] TG65[金属学及工艺—金属切削加工及机床]