基于BP神经网络的外圆磨削颤振在线识别和监测方法  

On-line identification and monitoring method for external grinding flutter based on BP neural network

作　　者：朱欢欢 李厚佳[1] 张梦梦 谭绍东 迟玉伦[3] ZHU Huanhuan;LI Houjia;ZHANG Mengmeng;TAN Shaodong;CHI Yulun(Higher Vocational Technical College,Shanghai University of Engineering Science,Shanghai 200437,China;Department of Manufacturing Engineering,Shanghai Technician School,Shanghai 200437,China;College of Mechanical Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海工程技术大学高等职业技术学院,上海200437 [2]上海市高级技工学校制造工程系,上海200437 [3]上海理工大学机械工程学院,上海200093

出　　处：《金刚石与磨料磨具工程》2022年第1期104-111,共8页Diamond & Abrasives Engineering

摘　　要：为提高机床磨削加工过程中对颤振现象识别的能力,提出一种基于BP(back propagation)神经网络模型的颤振识别方法。通过对加工过程中传感器采集到的高频声发射信号以及振动信号相关特征值的提取,获得关于颤振的多特征参数样本库,并用其对BP神经网络模型进行学习和训练,建立BP神经网络在线识别颤振的算法模型,实现对机床加工过程中是否发生颤振的在线监测和识别。试验结果表明:这种基于BP神经网络模型的颤振识别测试结果与磨削加工试验中的磨削颤振现象结果相符合。该方法能够有效地识别磨削加工过程中的颤振,并起到在线监测识别的作用。To improve the ability of the machine tool to identify chatter during the grinding process, a chatter recognition method is proposed based on the BP(back propagation) neural network model. By extracting the relevant feature values of the high-frequency acoustic emission signals and vibration signals in the processing process, multi-feature signal samples library about flutter are obtained. The multi-feature signal sample library is used to learn and train the BP neural network to establish recognition model. The model realizes on-line monitoring and accurate identification of whether chattering occurring during machine tool processing. The experimental results show that the flutter recognition based on the BP neural network model verifies that the measured test results are consistent with the actual flutter and network recognition results. Therefore, this method can effectively identify the flutter phenomenon in the processing process and play the role of online intelligent monitoring.

关 键 词：BP神经网络 外圆磨削 颤振 智能监测 

分 类 号：TG581.1[金属学及工艺—金属切削加工及机床]