基于差分进化小波神经网络的刀具磨损状态识别  

State Recognition of Tool Wear Based on Differential Evolution Wavelet Neural Networks

作　　者：陈静[1] 王武[1] 毛林 

机构地区：[1]许昌学院电气信息工程学院,许昌461000 [2]许继集团电网公司,许昌461000

出　　处：《机械设计与制造》2012年第7期176-178,共3页Machinery Design & Manufacture

基　　金：河南省教育厅自然科学研究资助项目(2011B470005);河南省科技厅科技攻关计划资助项目(112102210339)

摘　　要：提出应用小波神经网络进行刀具磨损状态识别的方法,给出了具体的识别流程。构建了小波神经网络,并实现了差分进化对网络参数的优化。通过检测加工现场的切削力和切削声音信号,将其进行信号处理后作为小波神经网络的训练样本,将差分进化应用于小波神经网络结构和参数的优化中,最终实现刀具磨损状态的识别。仿真结果表明差分进化小波神经网络能够有效避免神经网络不收敛的缺点,提高学习速度,采用差分进化小波神经网络进行刀具磨损状态识别,具有较高的诊断精度和效率。The new method of tool wear stated recognition was proposed with application of wavelet neural networks with specific recognition flow being provided.The three layer wavelet neural network was constructed and optimized with differential evolution algorithm.Cutting force and cutting noise signal was monitored in control field and processed as training samples for wavelet neural networks,the differential evolution was applied to structural and parametric optimization of the wavelet neural networks to realize the recognition of tool wear state.Simulation result shows the new method can avoid normal neural networks with convergence quality and enhance learning speed,also the diagnosis precision and efficiency was improved.

关 键 词：小波神经网络 差分进化算法 刀具磨损 状态识别 仿真 

分 类 号：TH16[机械工程—机械制造及自动化] TG71[金属学及工艺—刀具与模具]