多工序组合气囊抛光策略智能优化
Intelligent Optimization of Multi Process Combination Bonnet Polishing Strategy
摘要: 针对进一步提高多工序气囊抛光效率和质量的技术需要，开展基于智能算法的多工序组合气囊抛光策略优化研究。以黄铜H62轴套为实验样件进行气囊粗抛与精抛实验，分析总结样件表面粗糙度变化规律；构建BP神经网络(Back propagation neural network, BP)模型，利用实验数据训练获得不同抛光工艺参数下表面粗糙度及抛光时间的映射关系；以获得最优表面粗糙度和抛光时间为目标，采用NSGA-II (Non-dominated sorting genetic algorithm-II, NSGA-II)多目标优化的方法优化多工序组合抛光中各工序的工艺参数，预测获得最佳转换工序的时间节点及最优多工序组合抛光参数。实验结果表明，当采用优化的多工序组合抛光策略进行抛光时，相比于优化后的单工序精抛所需总时长缩短了25%的时间，由16分钟下降至12分钟，而表面粗糙度Ra相比于优化后的单工序粗抛下降了0.317 μm。该研究针对多工序组合气囊抛光工艺优化需要，设计了基于NSGA-II多目标优化算法的多工序工艺参数优化策略，可以实现轴套零件多工序气囊抛光加工效率和质量的同步提升。
Abstract: In order to further improve the efficiency and quality of multi-process bonnet polishing, the opti-mization research of multi-process combination airbag polishing strategy based on intelligent algo-rithm is carried out. The brass H62 shaft sleeve was used as the experimental sample to carry out the air bag rough polishing and fine polishing experiments, and the change rules of the surface roughness of the sample were analyzed and summarized; The Back propagation neural network (BP) model is constructed, and the mapping relationship between surface roughness and polishing time under different polishing process parameters is obtained by training the experimental data; In order to obtain the optimal surface roughness and polishing time, the Non-dominated sorting genetic algorithm-II (NSGA-II) multi-objective optimization method is used to optimize the process parameters of each process in multi-process combination polishing, and predict the time node of the optimal conversion process and the optimal multi-process combination polishing parameters. Results: The experimental results show that when the optimized multi-process combination pol-ishing strategy is used for polishing, the total time required for the optimized single-process pol-ishing is reduced by 25%, from 16 minutes to 12 minutes, and the surface roughness Ra is reduced by 0.317 μm compared with the optimized single-process polishing. Aiming at the needs of mul-ti-process combination airbag polishing process optimization, this study designed a multi-process process parameter optimization strategy based on NSGA-II multi-objective optimization algorithm, which can achieve the synchronous improvement of multi-process airbag polishing efficiency and quality of shaft sleeve parts.
文章引用：邱家军. 多工序组合气囊抛光策略智能优化[J]. 建模与仿真, 2023, 12(2): 1388-1399. https://doi.org/10.12677/MOS.2023.122130

参考文献

[1] 贾平. 中国部分精密仪器与装备发展现状及展望[J]. 科技导报, 2017, 35(11): 39-46.
[2] 姜晨, 刘剑, 魏久祥, 等. h形磁性复合流体抛光工具设计及工艺试验[J]. 光学精密工程, 2022, 30(12): 1452-1461.
[3] 袁巨龙, 张飞虎, 戴一帆, 等. 超精密加工领域科学技术发展研究[J]. 机械工程学报, 2010, 46(15): 161-177.
[4] 高宏刚, 曹健林, 朱镛, 等. 超光滑表面及其制造技术的发展[J]. 物理, 2000(10): 610-614.
[5] 高宏刚, 陈斌, 曹健林. 超光滑光学表面加工技术[J]. 光学精密工程, 1995(4): 7-14.
[6] Liu, D., Shi, Y.Y., Lin, X.J., et al. (2020) Polishing Surface Integrity of TC17 Aeroengine Blades. Journal of Mechanical Science and Technology, 34, 689-699. [Google Scholar] [CrossRef] 
[7] 王瑞芳, 徐方. 机器人研磨抛光工艺研究与实现[J]. 新技术新工艺, 2008(9): 19-22+2.
[8] 袁巨龙, 王志伟, 文东辉, 吕冰海, 等. 超精密加工现状综述[J]. 机械工程学报, 2007(1): 35-48.
[9] 周旭升. 大中型非球面计算机控制研抛工艺方法研究[D]: [博士学位论文]. 长沙: 国防科学技术大学, 2007.
[10] 宋剑锋. 曲面光学零件气囊抛光工艺参数优化及其相关技术研究[D]: [博士学位论文]. 哈尔滨: 哈尔滨工业大学, 2009.
[11] Hou, Y., Zhao, N. and Dang, L.X. (2022) Solving Multi-Objective School Bus Routing Problem Using an Improved NSGA-II Algorithm. Engineering Letters, 30, 788-796.
[12] Kruchinin, D., Paramonova, O. and Farafontova, E. (2019) Change of a State of the Optical Parts Surfaces Made of k8 Glass after Polishing Completion. In: Materials Science Forum, Trans Tech Publications Ltd., Bäch, 315-319. [Google Scholar] [CrossRef] 
[13] Sato, U. and Kawakubo, H. (2021) Influence of Na2SO4-Electrlytic Oxidizing Water on Polishing Surface of Oxygen Free Copper. Journal of the Japan Society for Precision Engineering, 87, 772-778. [Google Scholar] [CrossRef] 
[14] Peng, Y.F., Shen, B.Y., Wang, Z.Z., et al. (2021) Re-view on Polishing Technology of Small-Scale Aspheric Optics. International Journal of Advanced Manufacturing Technology, 115, 965-987. [Google Scholar] [CrossRef] 
[15] Wang, P., Gao, R. and Yan, R.Q. (2017) A Deep Learning-Based Ap-proach to Material Removal Rate Prediction in Polishing. CIRP Annals, 66, 429-432. [Google Scholar] [CrossRef] 
[16] 潘杰, 陈凡, 杨炜, 等. 基于SPSO–BP神经网络的自适应抛光工艺参数匹配[J]. 表面技术, 2022, 51(8): 387-399.
[17] 郭继通, 郑方志, 徐成宇, 等. 基于遗传算法和神经网络的软脆工件研磨加工工艺智能决策系统[J]. 表面技术, 2020, 49(4): 23-29+46.
[18] 赵传营, 赵玉刚, 刘宁, 等. 基于神经网络遗传算法的磁粒研磨TC4材料工艺参数优化[J]. 表面技术, 2020, 49(2): 316-321.
[19] 颜晓强, 王晗, 张嘉荣, 等. 小口径非球面小球头接触式抛光及磁流变抛光组合加工[J]. 表面技术, 2022, 51(7): 274-287+323.
[20] 戚德虎, 康继昌. BP神经网络的设计[J]. 计算机工程与设计, 1998(2): 47-49.
[21] 孙志军, 薛磊, 许阳明, 王正. 深度学习研究综述[J]. 计算机应用研究, 2012, 29(8): 2806-2810.
[22] Schneckenburger, M., Hofler, S., Garcia, L., et al. (2022) Material Removal Pre-dictions in the Robot Glass Polishing Process Using Machine Learning. SN Applied Sciences, 4, Article No. 33. [Google Scholar] [CrossRef] 
[23] 刘彩红. BP神经网络学习算法的研究[D]: [硕士学位论文]. 重庆: 重庆师范大学, 2008.
[24] Xiao, G.J., Zhu, B., Zhang, Y.D., et al. (2023) FCSNet: A Quantitative Explanation Method for Surface Scratch Defects during Belt Grinding Based on Deep Learning. Computers in Industry, 144, Article ID: 103793. [Google Scholar] [CrossRef] 
[25] Uday, A.B., Naik, N., Madhu, G.M., et al. (2022) Implementation and Validation of NSGA-II Algorithm for Constrained and Unconstrained Multi-Objective Optimization Problem. 2022 IEEE IAS Global Conference on Emerging Technologies (GlobConET), Arad, 20-22 May 2022, 539-544. [Google Scholar] [CrossRef] 
[26] Deb, K., Agrawal, S., Pratap, A., et al. (2000) A Fast Elitist Non-Dominated Sorting Genetic Algorithm for Multi- Objective Optimization: NSGA-II. In: Schoenauer, M., et al., Eds., Par-allel Problem Solving from Nature PPSN VI, Springer, Berlin, 849-858. [Google Scholar] [CrossRef] 
[27] Deb, K., Pratap, A. and Moitra, S. (2000) Mechanical Component Design for Multiple Objectives Using Elitist Non- Dominated Sorting GA. In: Schoenauer, M., et al., Eds., Parallel Problem Solving from Nature PPSN VI, Springer, Berlin, 859-868. [Google Scholar] [CrossRef] 
[28] 陈小庆, 侯中喜, 郭良民, 等. 基于NSGA-II的改进多目标遗传算法[J]. 计算机应用, 2006(10): 2453-2456.

为你推荐