Modeling for CNC Machine Tool Thermal Error Based on Genetic Algorithm Optimization Wavelet Neural Networks

doi:10.3901/JME.2019.21.215

Abstract

Abstract: Thermal error has been a significant factor influencing the accuracy of CNC machine tools,in order to maximize the accuracy and efficiency of thermal error compensation for CNC machine tools, a novel thermal error compensation model based on genetic algorithm for optimizing wavelet neural network is presented by combining the advantages of adaptive global optimization searching ability of genetic algorithm and good time-frequency local characteristics of wavelet neural network. Taking a five-axis swing horizontal machining center as the test object, the thermal error prediction model of wavelet neural network model is established with the temperature variables and thermal errors of machine tools as input samples. Then the weights and thresholds of wavelet neural network are adjusted by genetic algorithm, and the thermal error prediction model is finally established. Compared with traditional artificial neural network and ordinary wavelet neural network, the new compensation model has the advantages of high precision, strong anti-disturbance ability and robustness. This model is expected to be used in thermal error prediction and comp-ensation of the complex industrial applications.

Key words: thermal error, error compensation, machine tool, wavelet neural networks, genetic algorithm optimization

CLC Number:

TG502

LI Bin, ZHANG Yun, WANG Liping, LI Xuekun. Modeling for CNC Machine Tool Thermal Error Based on Genetic Algorithm Optimization Wavelet Neural Networks[J]. Journal of Mechanical Engineering, 2019, 55(21): 215-220.

References

[1] RAMESH R. Error compensation in machine tools-a review partⅡ:Thermal errors[J]. In. J. of Mach. Tools Manuf.,2000,40(9):1257-1284.
[2] 郑艳霞. 国内数控机床热误差建模研究现状[J]. 机械工程与自动化,2016(6):222-226. ZHENG Yanxia. Research status of thermal error modeling for CNC machine tools in China[J]. Mechanical Engineering and Automation,2016(6):222-226.
[3] 王海同,李铁明,王立平,等. 机床热误差建模研究综述[J]. 机械工程学报,2015,51(3):119-128. WANG Haitong,LI Tieming,WANG Liping,et al.[J]. Journal of Mechanical Engineering,2015,51(3):119-128.
[4] FALAMARZI Y,PALIZDAN N,HUANG Y F,et al.Estimating evapotranspiration from temperature and wind speed data using artificial and wavelet neural networks(WNNs)[J].Agric. Water Manag.,2014,140:26-36.
[5] GUAN C,LUH P B,MICHEL L D,et al. Very short-term load forecasting:Wavelet neural networks with Data Pre-Filtering[J]. IEEE Transactions on Power Systems,2013,28(1):30-41.
[6] KUMON T,IWASAKI M,SUZUKI T,et al. Nonlinear system identification using genetic algorithm[C]//Conference of the IEEE Industrial Electronics Society. IEEE,2000.
[7] HAYKIN S. Neural networks:A comprehensive foundation[M]. London:Macmillan,1998.
[8] 罗玉春,都洪基,崔芳芳.基于MATLAB的BP神经网络结构与函数逼近能力的关系分析[J].现代电子技术,2007,30(24):88-90. LUO Yuchun,DU Hongji,CUI Fangfang.Analysis of Relation between the structure of BP feed-forward neural network and precision proximate based on MATLAB[J]. Modern Electronics Technique,2007,30(24):88-90.
[9] 赵忠,王鹏.高精度惯性导航系统垂线偏差影响与补偿[J].中国惯性技术学报,2013,2l(6):701-705. ZHAO Zhong,WANG Peng.Analysis and compensation of vertical deflection effect on high accuracy inertial navigation system[J].Journal of Chinese Inertial Technology,2013,21(6):701-705.
[10] ALEXANDRIDIS A K,ZAPRANIS A D. Wavelet neural networks:A practical guide[J].Neural Networks,2013, 42:1-27.
[11] 张良均,曹晶,蒋世忠.神经`网络实用教程[M]. 北京:机械工业出版社,2008. ZHANG Liangjun,CAO Jing,JIANG Shizhong. Practical course of neural network[M]. Beijing:China Machine Press,2008.
[12] 朱灿.实数编码遗传算法机理分析及算法改进研究[D]. 长沙:中南大学,2009. ZHU Can. Theoretical analysis and algorithm improvement of real coded genetic algorithm[D]. Changsha:Central South University,2009.
[13] ZHU Jie,NI Jun,ALBERT J S.Robust machine tool thermal error modeling through thermal mode concept[J].Journal of Manufacturing Science and Engineering,2008,130(6):061006-9.
[14] 沈华,李永祥,鲁志政,等.数控车床几何和热误差综合实时补方法应用[J].四川大学学报,2008,40(1):163-166. SHEN Jinhua,LI Yongxiang,LU Zhizheng,et al. Geometric and thermal error synthesis of CNC lathe. Application of combined real-time compensation method[J]. Journal of Sichuan University,2008,40(1):163-166.
[15] ABDERRAZAK E O,MICHEL G.A comprehensive approach for thermal error model optimization for ANN-based real-time error compensation in CNC machine tools[J]. Mechanical and Aerospace Engineering ICMAE,2012,232(9):640-646.