Research on Analytical Model and DDQN-SVR Prediction Model of Turning Surface Roughness

doi:10.3901/JME.2021.13.262

Abstract

Abstract: In turning process, the quality of parts is a problem that producers need to focus on. The surface roughness is an important index to evaluate the quality of parts. Selecting satisfactory cutting parameters to improve surface roughness can effectively improve part quality. In order to improve the prediction accuracy of surface roughness, a segmented analytical model of surface roughness theory is proposed based on the previous research. At the same time, double deep Q network (DDQN) is used to optimize the Support vector regression (SVR) to improve the predictive performance of the data-driven model. The environment design of DDQN to optimize the internal parameters of SVR is explored, and its optimization effect and stability are compared with other algorithms. Based on the turning experiment of 45 steel, the validity of segmented surface roughness theory model and DDQN-SVR prediction model is verified, which provides better technical support for the selection of cutting parameters based on surface roughness.

Key words: turning, surface roughness, theoretical model, support vector regression, deep reinforcement learning

CLC Number:

TG261

CHEN Chaoyi, LU Juan, CHEN Kai, LI Yujia, MA Junyan, LIAO Xiaoping. Research on Analytical Model and DDQN-SVR Prediction Model of Turning Surface Roughness[J]. Journal of Mechanical Engineering, 2021, 57(13): 262-272.

References

[1] 杜国臣. 硬车削技术及其应用[J]. 机械工程师, 2003(4):61-64. DU Guochen. Hard turning technology and its application[J]. Mechanical Engineer, 2003(4):61-64
[2] 孙林, 杨世元. 基于最小二乘支持矢量机的成形磨削表面粗糙度预测及磨削用量优化设计[J]. 机械工程学报, 2009, 45(10):254-260. SUN Lin, YANG Shiyuan. Prediction for surface roughness of profile grinding and optimization of grinding parameters based on least squares support vector machine[J]. Journal of Mechanical Engineering, 2009, 45(10):254-260.
[3] VAJPAYEE S. Analytical study of surface roughness in turning[J]. Wear, 1981, 70(2):165-175.
[4] 卢碧红, 黄文丽, 葛研军. 车削加工表面粗糙度预测新模型[C]//全国高校机械工程测试技术研究会, 中国振动工程学会动态测试专业委员会代表大会暨学术年会. 2004. LU Bihong, HUANG Wenli, GE Yanjun. New model for surface roughness prediction in turning[C]//National Institute of Mechanical Engineering Testing Technology, China Vibration Engineering Society Dynamic Testing Professional Committee Congress and Academic Annual Meeting. 2004.
[5] BOUGHARRIOU A, BOUZID W, SAI K. Analytical modeling of surface proﬁle in turning and burnishing[J]. Int. J. Adv. Manuf. Technol, 2014, 75(1-4):547-558.
[6] SUNG AN, RATNAM M M, LOH W P. Effect of wedge angle on surface roughness in finish turning:Analytical and experimental study[J]. Int. J. Adv. Manuf. Technol., 2014, 74(1-4):139-150
[7] 喻杉. 基于深度环境理解和行为模仿的强化学习智能体设计[D]. 杭州:浙江大学, 2019. YU Shan. Reinforcement learning agent design based on deep environment understanding and behavior imitation[D]. Hangzhou:Zhejiang University, 2019
[8] 丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011, 040(001):1-10. DING Shifei, QI bingjuan, TAN Hongyan. Overview of support vector machine theory and algorithm[J]. Journal of University of Electronic Science and Technology of China, 2011, 040(001):1-10
[9] 鲁娟, 张振坤, 吴智强, 等.基于支持向量机的蠕墨铸铁表面粗糙度预测[J].表面技术, 2020, 49(2):339-346. LU Juan, ZHANG Zhenkun, WU Zhiqiang, et al. Prediction of surface roughness for compacted graphite cast iron based on support vector machine[J]. Surface Technology, 2020, 49(2):339-346
[10] LU J, LIAO X, LI S, et al. An effective ABC-SVM approach for surface roughness prediction in manufacturing processes[J]. Complexity, 2019:1-13.
[11] AICH U, BANERJEE S. Modeling of EDM responses by support vector machine regression with parameters selected by particle swarm optimization[J]. Applied Mathematical Modelling, 2014, 38:2800-2818.
[12] WANG G H, HE T, KUANG Y, et al. Optimization of soft-sensing model for ash content prediction of flotation tailings by image features tailings based on GA-SVMR[J]. Physicochemical Problems of Mineral Processing, 2020, 56(4):590-598.
[13] 郭鹏, 张新艳, 余建波. 基于深度强化学习与有限元仿真集成的拉深成形控制[J]. 机械工程学报, 2020, 56(20):61-72. GUO Peng, ZHANG Xinyan, YU Jianbo. Control of deep drawing process based on integration of deep reinforcement learning and finite element method[J]. Journal of Mechanical Engineering, 2020, 56(20):61-72.
[14] SILVER D, SCHRITTWIESER J, SIMONYAN K, et al. Mastering the game of Go without human knowledge[J]. Nature, 2017, 550(7676):354-359.
[15] WATKINS C J C H, DAYAN P. Q-learning[J]. Machine Learning, 1992, 8(3-4):279-292.
[16] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Playing atari with deep reinforcement learning[J]. Computer Science, 2013.
[17] MNIH, V, KAVUKCUOGLU, K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540):529-533.
[18] van HASSELT H, GUEZ A, SILVER D. Deep Reinforcement Learning with Double Q-learning[J]. Computer Science, 2015.
[19] HUANG X, LUO W, LIU J. Attitude control of fixed-wing UAV based on DDQN[C]//2019 Chinese Automation Congress (CAC). 2019.
[20] ZHANG Q, DU T, TIAN C. A Sim2real method based on double deep Q-Network for training a self-driving scale CA[J]. Mathematical Foundations of Computing, 2019, 2(4):315-331.
[21] CHIFFRE L D, LONARDO P, TRUMPOLD H, et al. Quantitative characterisation of surface texture[J]. CIRP Annals-Manufacturing Technology, 2000, 49(2):635, 644-642, 652.
[22] ISOE. Geometrical product specifications (GPS):Surface texture:Profile method:Metrological characteristics of phase correct filters[S]. New York:ISOE, 1996.
[23] GADELMAWLA E S, KOURA M M, MAKSOUD T M A, et al. Roughness parameters[J]. Journal of Materials Processing Technology, 2002, 123(1):133-145.
[24] CHANG C C, LIN C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2, 1-39.
[25] HASHMI K H, ZAKRIA G, RAZA M B. et al. Optimization of process parameters for high speed machining of Ti-6Al-4V using response surface methodology[J]. Int. J. Adv. Manuf. Technol., 2016, 85, 1847-1856
[26] 王永鑫, 张昌明. 基于响应面法AerMet100超高强度钢钻削预测与优化试验研究[J]. 科学技术与工程, 2019, 19(36):123-127. WANG Yongxin, ZHANG Changming. Experimental research on drilling prediction and optimization of aermet100 ultra-high strength steel based on response surface methodologies[J]. Science Technology and Engineering, 2019, 19(36):123-127.
[27] CHERKASSKY V, MA Y. Practical selection of SVM parameters and noise estimation for SVM regression.[J]. Neural Networks, 2004, 17(1):113-126.
[28] VAPNIK V N. Statistical learning theory[J]. Encyclopedia of the sciences of Learning, 1998, 41(4):3185-3185.