Abstract：Aiming at the low recognition rate under changing processing conditions of the existing tool wear state recognition methods, according to real-time acquisition of acoustic emission signal, an adaptive tool wear state features extraction method from acoustic emission signal and a tool wear state recognition method based on grey relational analysis between wear state feature data sequences are proposed. Experiment with four WNMG080408-TM T9125 type turning tools on ZCK20 digital controlled lathe was conducted and tool wear state recognition was implemented, the results show that the proposed methods are able to acquire the turning tools’ wear state feature effectively and adaptively, and the tools wear state recognition results are consistent with the actual condition, and a high recognition rate is achieved.
［1］李鹏阳,郝重阳,祝双武,等. 基于脉冲耦合神经网络的刀具磨损检测［J］. 中国机械工程,2008,19(5):547-550.
［2］Niranjan P K, Ramamoorthy B. Tool wear evaluation by stereo vision and prediction by artificial neural network［J］.Journal of Materials Proeessing Technology, 2001, 112(1): 43-52.
［3］欧阳八生,唐少农. CNC车削中刀具磨损实时监控的试验研究［J］. 仪器仪表学报,2004,25(4):127-129.
［4］申志刚,何宁,李亮. 高速硬铣削加工刀具磨损监测研究［J］. 中国机械工程,2009,20(13):1582-1586.
［5］姚静毅,付元杰,袁景阳. 基于DSP的声发射信号采集及分析系统的研究［J］. 计量技术,2012,(3):16-19.
［6］Srinivasa P P, Ramakrishna R P K. Acoustic emission analysis for tool wear monitoring in face milling［J］.International Journal of Production Researeh, 2002, 40(5): 1081-1093.
［7］王彦青,魏连鑫. 一种改进的小波阈值去噪方法［J］. 上海理工大学学报,2011,33(4):405-408.
［8］陈爱弟,王信义,王忠民,等. 用于监测刀具磨损的声发射(AE)特征优选方法［J］.北京理工大学学报,2000,20(3):270-275.
［9］张定会. 基于小波分析的故障诊断［J］. 上海理工大学学报,2000,22(2):137-140.
［10］孙勇,景博,覃征,等. 基于小波分析的信噪分离方法研究［J］. 计量学报,2006,27(2):153-155.
［11］Shao H, Wang H L, Zhao X M. A Cutting Power Model for Tool Wear Monitoring in Milling［J］. International Journal of Machine Tools & Manufacture, 2004, 44: 1503-1509.
［12］黄凯锋,许黎明,范浩,等. 基于振动信号的砂轮磨损状态的在线特征识别［J］. 仪器仪表学报,2005,26(8):632-633.
［13］高宏力,许明恒,傅攀,等. 基于动态树理论的刀具磨损监测技术［J］. 机械工程学报,2006,42(7):227-230.
2015, Vol. 36 
