摘要
为提高微铣刀磨损在线监测系统的预测精度,尝试通过主成分分析法对微铣削振动信号的时域和频域特征进行降维,将降维后的特征输入改进型BP神经网络模型,实现微铣刀磨损特征分类。结果表明,提出的微铣刀在线监测方法能够准确识别微铣刀的各种磨损状态,此外,和其它分类算法相比,提出的基于遗传算法的BP神经网络模型在分类精度和计算效率方面具有综合优势,对微铣刀磨损的其它在线监测方法具有一定的指导意义和借鉴价值。
In order to improve the prediction accuracy of the on-line monitoring system of micro milling tool wear,this paper attempts to reduce the dimension of the time-domain and frequency-domain features of micro milling vibration signal by principal component analysis,and input the reduced dimension features into the improved BP neural network model to realize the wear feature classification of micro milling cutter.The results show that the on-line monitoring method of micro milling cutter proposed in this paper can accurately identify various wear states of micro milling tool.In addition,compared with other classification algorithms,the BP neural network model based on genetic algorithm proposed in this paper has a comprehensive advantage in classification accuracy and calculation efficiency,which has certain guiding significance and reference value for other on-line monitoring methods of micro milling cutter wear.
作者
王二化
刘颉
WANG Er-hua;LIU Jie(Changzhou City Lab of Intelligent Technology for Advanced Manufacturing Equipment,Changzhou College of Information Technology,Changzhou Jiangsu 213164,China;School of Hydropower and Information Engineering,Huazhong University of Science and Technology,Wuhan 430074,China)
出处
《组合机床与自动化加工技术》
北大核心
2021年第1期114-117,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家关键基础研究计划项目(2011CB706803)
常州市高端制造装备智能化技术重点实验室(CM20183004)
江苏省青蓝工程中青年学术带头人
常州信息职业技术学院“1+1+1”协同培育工程建设项目。