塑料注射成型工艺参数优化的模糊规则网络模型

doi:10.3901/JME.2022.20.206

机械工程学报 ›› 2022, Vol. 58 ›› Issue (20): 206-220.doi: 10.3901/JME.2022.20.206

• 特邀专栏：高性能塑性成形制造(下) • 上一篇下一篇

扫码分享

塑料注射成型工艺参数优化的模糊规则网络模型

郭飞^1,2, 汪汝健², 张云^1,2, 周华民², 李德群²

1. 哈尔滨工业大学金属精密热加工国家级重点实验室哈尔滨 150001;
2. 华中科技大学材料成形与模具技术国家重点实验室武汉 430074

收稿日期:2021-11-30 修回日期:2022-04-03 出版日期:2022-10-20 发布日期:2022-12-27
通讯作者: 张云(通信作者)，男，1981年出生，博士，教授，博士研究生导师。主要研究方向为材料成形过程建模、仿真与智能化技术。E-mail：marblezy@hust.edu.cn
作者简介:郭飞，男，1995年出生，博士研究生。主要研究方向为塑料注射成型智能化技术。E-mail：guofei_reborn@hust.edu.cn
基金资助:
国家重点研发计划(2019YFB1704900)和浙江省重点研发计划(2022C01069)资助项目。

A Fuzzy Rule-based Network Model for Optimization of Process Parameters in Plastic Injection Molding

GUO Fei^1,2, WANG Ruijian², ZHANG Yun^1,2, ZHOU Huamin², LI Dequn²

1. National Key Laboratory for Precision Hot Processing of Metals, Harbin Institute of Technology Harbin 150001;
2. State Key Laboratory of Materails Processing and Die & Mould Technology, Huazhong University of Science & Technology, Wuhan 430074

Received:2021-11-30 Revised:2022-04-03 Online:2022-10-20 Published:2022-12-27

摘要/Abstract

摘要： 注射成型是塑料产品成型的最主要工艺，工艺参数是影响成型产品外观、尺寸与性能的关键因素之一。工艺参数的设置与优化属于弱理论、强经验的问题，迫切需要发展科学化、系统化的方法。针对产品缺陷修正中人工经验依赖性强的问题，构建知识的统一模糊化规则形式，建立工艺优化知识表示和推理于一体的Takagi-Sugeno-Kang(TSK)模糊规则网络模型。进一步，提出从工艺数据集自动发现工艺参数优化规则的学习方法，采用Dropout策略与Bagging集成学习策略缓解高维工艺数据下工艺知识库增长出现的规则数量爆炸等问题。分析了模糊规则网络参数、结构对知识表示和推理的影响，建立模型的参数学习与结构优化的双重进化方法。提出基于经验回放的工艺数据增量学习方法，建立数据的增量学习策略。在注射成型工艺数据集上的结果表明，模型的规则数量和长度降低了50%，具有高可解释性以及增量学习稳定性。

关键词: 注射成型, 工艺参数, 优化, 模糊规则网络

Abstract: Injection molding is the most crucial process for forming plastic products, and process parameters are one of the critical factors affecting the appearance, size, and performance of products. However, the optimization of the process parameters is weakly theoretical and strongly empirical problems, and there is an urgent need to develop a scientific and systematic method. In response to the problem of the strong dependence of manual experience in product defect correction, a unified knowledge form using fuzzy rules was constructed and a Takagi-Sugeno-Kang (TSK) fuzzy rule network model integrating knowledge representation and inference of process parameters optimization was established. Furthermore, a learning method was proposed to automatically discover optimization rules of process parameters from process datasets. The Dropout strategy and Bagging ensemble learning strategy were adopted to alleviate the problem of rule explosion caused by the growth of process knowledge bases in high-dimensional process data. Then, the influences of the fuzzy rule network parameters and structure on knowledge representation and inference were analyzed. Based on these analyses, two methods, parameters learning and structure learning of the model were developed respectively. The learning method of process data based on experience pool replay was proposed, establishing the incremental learning strategy of process data. The test results on the injection molding dataset showed that the number and length of rules were reduced by 50% in the proposed fuzzy rule-base network model, realizing high interpretability as well as incremental learning stability.

Key words: injection molding, process parameters, optimization, fuzzy neural network<

中图分类号:

TH164

郭飞, 汪汝健, 张云, 周华民, 李德群. 塑料注射成型工艺参数优化的模糊规则网络模型[J]. 机械工程学报, 2022, 58(20): 206-220.

GUO Fei, WANG Ruijian, ZHANG Yun, ZHOU Huamin, LI Dequn. A Fuzzy Rule-based Network Model for Optimization of Process Parameters in Plastic Injection Molding[J]. Journal of Mechanical Engineering, 2022, 58(20): 206-220.

参考文献

[1] ZHOU Huamin. Computer modeling for injection molding:simulation，optimization，and control[M]. New Jersey:John Wiley & Sons，2012.
[2] GAO Huang，ZHANG Yun，ZHOU Xundao，et al. Intelligent methods for the process parameter determination of plastic injection molding[J]. Frontiers of Mechanical Engineering，2018，13(1):85-95.
[3] EVERETT S E，DUBAY R. A sub-space artificial neural network for mold cooling in injection molding[J]. Expert Systems with Applications，2017，79:358-371.
[4] GUO Wei，HUA Lin，MAO Huajie. Minimization of sink mark depth in injection-molded thermoplastic through design of experiments and genetic algorithm[J]. The International Journal of Advanced Manufacturing Technology，2014，72(1):365-375.
[5] TSAI K M，LUO H J. An inverse model for injection molding of optical lens using artificial neural network coupled with genetic algorithm[J]. Journal of Intelligent Manufacturing，2017，28(2):473-487.
[6] YANG Dongzhe，DANAI K，KAZMER D. A knowledge-based tuning method for injection molding machines[J]. Journal of Manufacturing Science and Engineering，2001，123(4):682-691.
[7] KARASU M K，SALUM L. FIS-SMED:a fuzzy inference system application for plastic injection mold changeover[J]. The International Journal of Advanced Manufacturing Technology，2018，94(1):545-559.
[8] KHOSRAVANI M R，NASIRI S，WEINBERG K. Application of case-based reasoning in a fault detection system on production of drippers[J]. Applied Soft Computing，2019，75:227-232.
[9] CORDÓN O，HERRERA F，GOMIDE F，et al. Ten years of genetic fuzzy systems:current framework and new trends[C]//Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference. July 25-28，2001，IEEE，Vancouver，BC，Canada，3:1241-1246.
[10] HE Congjie，MA Meng，WANG Ping. Extract interpretability-accuracy balanced rules from artificial neural networks:a review[J]. Neurocomputing，2020，387:346-358.
[11] TAN K H，YUEN M M F. A fuzzy multiobjective approach for minimization of injection molding defects[J]. Polymer Engineering & Science，2000，40(4):956-971.
[12] MOK S L，KWONG C K. Application of artificial neural network and fuzzy logic in a case-based system for initial process parameter setting of injection molding[J]. Journal of Intelligent Manufacturing，2002，13(3):165-176.
[13] ZHOU Huamin，ZHAO Peng，FENG Wei. An integrated intelligent system for injection molding process determination[J]. Advances in Polymer Technology:Journal of the Polymer Processing Institute，2007，26(3):191-205.
[14] JANG J S R. ANFIS:Adaptive-network-based fuzzy inference system[J]. IEEE Transactions on Systems，Man，and Cybernetics，1993，23(3):665-685.
[15] CUI Yuqi，WU Dongrui，HUANG Jian. Optimize TSK fuzzy systems for classification problems:Minibatch gradient descent with uniform regularization and batch normalization[J]. IEEE Transactions on Fuzzy Systems，2020，28(12):3065-3075.
[16] GU Suhang，CHUNG F L，WANG Shitong. A novel deep fuzzy classifier by stacking adversarial interpretable TSK fuzzy sub-classifiers with smooth gradient information[J]. IEEE Transactions on Fuzzy Systems，2019，28(7):1369-1382.
[17] YEGANEJOU M，DICK S，MILLER J. Interpretable deep convolutional fuzzy cassifier[J]. IEEE Transactions on Fuzzy Systems，2019，28(7):1407-1419.
[18] HE W，ZHANG Y F，LEE K S，et al. Development of a fuzzy-neuro system for parameter resetting of injection molding[J]. Journal of Manufacturing Science and Engineering，2001，123(1):110-118.
[19] SRIVASTAVA N，HINTON G，KRIZHEVSKY A，et al. Dropout:A simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research，2014，15(1):1929-1958.
[20] DENG Zhaohong，CHOI K S，CHUNG F L，et al. Scalable TSK fuzzy modeling for very large datasets using minimal-enclosing-ball approximation[J]. IEEE Transactions on Fuzzy Systems，2010，19(2):210-226.
[21] HU Xingchen，PEDRYCZ W，WANG Xianmin. Random ensemble of fuzzy rule-based models[J]. Knowledge-Based Systems，2019，181:104768.
[22] NOVATI G，KOUMOUTSAKOS P. Remember and forget for experience replay[C]//International Conference on Machine Learning. June 10-15，2019，PMLR，Long Beach，CA，USA，97:4851-486.
[23] HOU Saihui，PAN Xinyu，LOY C C，et al. Learning a unified classifier incrementally via rebalancing[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 16-20，2019，Long Beach，CA，USA:831-839.
[24] HOU Yuenan，LIU Lifeng，WEI Qing，et al. A novel DDPG method with prioritized experience replay[C]// 2017 IEEE international conference on systems，man，and cybernetics (SMC).October 5-8，2017，IEEE，Banff，AB，Canada:316-321.
[25] DESTERCKE S，GUILLAUME S，CHARNOMORDIC B. Building an interpretable fuzzy rule base from data using orthogonal least squares-application to a depollution problem[J]. Fuzzy Sets and Systems，2007，158(18):2078-2094.
[26] JAKUBEK S，HAMETNER C，KEUTH N. Total least squares in fuzzy system identification:An application to an industrial engine[J]. Engineering Applications of Artificial Intelligence，2008，21(8):1277-1288.
[27] RONG H J，SUNDARARAJAN N，HUANG G B，et al. Sequential adaptive fuzzy inference system (SAFIS) for nonlinear system identification and prediction[J]. Fuzzy Sets and Systems，2006，157(9):1260-1275.
[28] GOODFELLOW I，BENGIO Y，COURVILLE A. Deep learning[M]. London:MIT Press，2016.
[29] CHEONG F，LAI R. Constraining the optimization of a fuzzy logic controller using an enhanced genetic algorithm[J]. IEEE Transactions on Systems，Man，and Cybernetics，Part B (Cybernetics)，2000，30(1):31-46.
[30] PANCHO D P，ALONSO J M，CORDÓN O，et al. FINGRAMS:Visual representations of fuzzy rule-based inference for expert analysis of comprehensibility[J]. IEEE Transactions on Fuzzy Systems，2013，21(6):1133-1149.

塑料注射成型工艺参数优化的模糊规则网络模型

A Fuzzy Rule-based Network Model for Optimization of Process Parameters in Plastic Injection Molding

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘鑫, 张俊, 徐斌斌, 刘弘光, 赵万华. 激光辅助铣削过程的预热温度场调控方法研究[J]. 机械工程学报, 2024, 60(9): 218-228.
[2]	魏荣, 徐默然, 李常平, 李树健, 李鹏南. 电火花辅助铣削钛合金多能场建模及调控优化研究[J]. 机械工程学报, 2024, 60(9): 393-409.
[3]	杨柳, 高天雄, 宋颜和, 孔祥东, 张世林. 基于田口法的比例电磁铁极靴结构优化研究[J]. 机械工程学报, 2024, 60(8): 329-336.
[4]	张行, 富宽, 陈铭浩, 李睿, 石新娜. 压差式多节串联管道机器人越障时动力学演化规律及减振分析[J]. 机械工程学报, 2024, 60(8): 348-359.
[5]	赵希坤, 李聪波, 杨勇, 吕岩, 姜书艳. 数据-机理混合驱动下考虑刀具柔性的柔性加工工艺参数能效优化方法[J]. 机械工程学报, 2024, 60(7): 236-248.
[6]	郭江, 潘博, 连佳乐, 杨哲, 刘欢, 高菲, 康仁科. 双面研磨技术研究现状与发展趋势[J]. 机械工程学报, 2024, 60(7): 266-288.
[7]	姜文涛, 刘晓明, 李培源, 陈海, 张煦松. 机械式真空快速切换开关机构多目标优化设计[J]. 机械工程学报, 2024, 60(6): 153-162.
[8]	周晨, 徐飞翔. 四轮独立转向车辆转向模式切换轨迹多目标优化方法研究[J]. 机械工程学报, 2024, 60(6): 306-320.
[9]	柴依扬, 张乐乐, 窦伟元, 张海峰. 基于并行NSGA-III算法的高速列车车体侧墙结构高维多目标优化[J]. 机械工程学报, 2024, 60(6): 321-333.
[10]	周祖意, 杨玉维, 齐文耀, 龚健超, 李照童. 腰部外骨骼机器人多刚-柔体动力学等效逆解方法研究及其性能优化综合[J]. 机械工程学报, 2024, 60(5): 107-118.
[11]	赵承伟, 张文豪, 龚天诚, 张逸云, 王长涛, 罗先刚. 平面光学元件超平整吸附装载的优化设计与分析[J]. 机械工程学报, 2024, 60(5): 241-248.
[12]	张鹏, 尹来容, 仝永刚, 黄龙. 基于间隙预测模型的自动铺带轨迹优化方法[J]. 机械工程学报, 2024, 60(5): 296-316.
[13]	高强, 王健, 张严, 郑旭阳, 吕昊, 殷国栋. 拓扑优化方法及其在运载工程中的应用与展望[J]. 机械工程学报, 2024, 60(4): 369-390.
[14]	纵怀志, 艾吉昆, 张军辉, 江磊, 谭树杰, 刘余贤, 苏琦, 徐兵. 基于拓扑优化和晶格填充的四足机器人肢腿单元轻量化设计[J]. 机械工程学报, 2024, 60(4): 420-429.
[15]	苏建涛, 董绍华, 朱诗敏. 多目标混合流水车间机器故障重调度问题研究[J]. 机械工程学报, 2024, 60(4): 438-448.