Research on Real-time Control of Machining Surface Quality Stability Based on Wear Monitoring

doi:10.3901/JME.2020.11.240

Abstract

Abstract: In the process of cutting, the wear will accumulate with the change of time, resulting in the fluctuation of machining quality. In order to solve this problem, a real-time control method of surface quality based on wear monitoring is proposed under the background of large data. The mapping relationship between cutting force signal and wear is established through historical database. Tool wear reflects the current processing state. By comparing the processing quality of the current processing state with customer demand, the processing parameters are optimized to make the processing quality as close as possible to customer demand. The optimization model is based on the modeling principle of generalized regression neural network, so that the optimization problem can be solved by non-linear programming and the control decision can be made quickly. A large number of milling experiments have been carried out on TC18 material. The experimental results verify the reliability of the method, and also prove that the method can respond quickly to the change of processing state. This research solves the problem that the control accuracy and response time cannot be guaranteed simultaneously in the existing research, and provides a new idea for online intelligent control of cutting surface processing quality.

Key words: roughness, big data, generalized regression neural network, wear, quality stability control

CLC Number:

TP273

LIAO Xiaoping, CHEN Kai, LU Juan. Research on Real-time Control of Machining Surface Quality Stability Based on Wear Monitoring[J]. Journal of Mechanical Engineering, 2020, 56(11): 240-248.

References

[1] 刘献礼,刘强,岳彩旭,等. 切削过程中的智能技术[J]. 机械工程学报,2018,54(16):45-61. LIU Xianli,LIU Qiang,YUE Caixu,et al. Intelligent technology in cutting process[J]. Journal of Mechanical Engineering,2018,54(16):45-61.
[2] CHEN Wanqun,SUN Yazhou,HUO Dehong,et al. Modelling of the influence of tool runout on surface generation in micro milling[J]. Chinese Journal of Mechanical Engineering,2019,32(1):152-160.
[3] YEGANEFAR A,NIKNAM S A,ASADI R. The use of support vector machine,neural network,and regression analysis to predict and optimize surface roughness and cutting forces in milling[J]. The International Journal of Advanced Manufacturing Technology,2019,105(1-4):951-965.
[4] 阴艳超,丁卫刚. 切削加工表面粗糙度的多维多规则云预测方法[J]. 机械工程学报,2016,52(15):204-212. YIN Yanchao,DING Weigang. Multi-dimensional and multi-rule cloud prediction method for cutting surface roughness[J]. Journal of Mechanical Engineering,2016,52(15):204-212.
[5] HUANG P B,SHIANG W J,JOU Y T,et al. An in-process adaptive control of surface roughness in end milling operations[C]//International Conference on Machine Learning & Cybernetics,July 11-14,2010,Qingdao,China. IEEE,2010:2160-1348.
[6] PIMENOV D Y,BUSTILLO A,MIKOLAJCZYK T. Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth[J]. Journal of Intelligent Manufacturing,2018,29:1045-1061.
[7] ZHAO Guoyong,GUO Y B,ZHU Peiyu,et al. Energy consumption characteristics and influence on surface quality in milling[J]. Procedia CIRP,2018,71:111-115.
[8] 张洁,刘成颖,郑烽,等. 基于铣削动力学的刀具强迫振动抑制研究[J]. 机械工程学报,2018,54(17):94-99. ZHANG Jie,LIU Chengying,ZHENG Feng,et al. Research on tool vibration suppression based on milling dynamics[J]. Journal of Mechanical Engineering,2018,54(17):94-99.
[9] LIU Lijia,LIU Xianli,MAN Chuntao,et al. Delayed observer-based H∞ control for networked control systems[J]. Neurocomputing,2016,179:101-109.
[10] 李茂月,韩振宇,富宏亚,等. 基于开放式控制器的铣削颤振在线抑制[J]. 机械工程学报,2012,48(17):172-182. LI Maoyue,HAN Zhenyu,FU Hongya,et al. On-line suppression of milling chatter based on open controller[J]. Journal of Mechanical Engineering,2012,48(17):172-182.
[11] LIU Xianli,DING Yunpeng,YUE Caixu,et al. Off-line feedrate optimization with multiple constraints for corner milling of a cavity[J]. The International Journal of Advanced Manufacturing Technology,2016,82(9-12):1899-1907.
[12] 刘献礼,丁云鹏,岳彩旭,等. 基于载荷控制的拐角铣削进给优化[J]. 机械工程学报,2016,52(19):189-196. LIU Xianli,DING Yunpeng,YUE Caixu,et al. Feed optimization of corner milling based on load control[J]. Journal of Mechanical Engineering,2016,52(19):189-196.
[13] YAO Xifan,ZHANG Yi,LI Bin,et al. Machining force control with intelligent compensation[J]. International Journal of Advanced Manufacturing Technology,2013,69(5-8):1701-1715.
[14] LIAO Xiaoping,ZHOU Gang,ZHANG Zhenkun,et al. Tool wear state recognition based on GWO-SVM with feature selection of genetic algorithm[J]. The International Journal of Advanced Manufacturing Technology,2019,104(1-4):1051-1063.
[15] BABATUNDE O H,ARMSTRONG L,LENG J,et al. A genetic algorithm-based feature selection[J]. International Journal of Electronics Communication and Computer Engineering,2014,5(4):889-905.
[16] BABATUNDE O H,ARMSTRONG L,LENG J,et al. Zernike moments and genetic algorithm:Tutorial and application[J]. British Journal of Mathematics & Computer Science,2014,4(15):2217-2236.
[17] SPECHT D F. A general regression neural network[J]. IEEE Transactions on Neural Networks,1991,2(6):568-576.