基于强化学习的注塑工艺参数自动调优方法及应用

冯子豪; 万会龙; 林江豪; 任志刚

doi:10.12052/gdutxb.240142

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于强化学习的注塑工艺参数自动调优方法及应用

控制科学与工程 | 更新时间：2026-05-27

- 基于强化学习的注塑工艺参数自动调优方法及应用
- Reinforcement Learning-based Automatic Tuning Method and Application of Injection Molding Process Parameters
- 广东工业大学学报 2025年42卷第2期页码：59-69
- 作者机构：
  
  广东工业大学自动化学院,广东,广州,510006
- 作者简介：
  
  冯子豪(1999–)，男，硕士研究生，主要研究方向为强化学习和工艺参数寻优，E-mail：849612040@qq.com
  任志刚(1987–)，男，副教授，硕士生导师，主要研究方向为复杂工业过程优化与控制、工业智能，E-mail：renzhigang@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(62073088);广东省基础与应用基础研究基金资助项目(2024A1515011768)
- DOI：10.12052/gdutxb.240142
  中图分类号： TP271
- 纸质出版：2025
- 稿件说明：
移动端阅览
冯子豪, 万会龙, 林江豪, 等. 基于强化学习的注塑工艺参数自动调优方法及应用[J]. 广东工业大学学报, 2025, 42(2): 59–69.

Feng Zihao, Wan Huilong, Lin Jianghao, et al. Reinforcement Learning-based Automatic Tuning Method and Application of Injection Molding Process Parameters[J]. 2025, 42(2): 59-69.
冯子豪, 万会龙, 林江豪, 等. 基于强化学习的注塑工艺参数自动调优方法及应用[J]. 广东工业大学学报, 2025, 42(2): 59–69. DOI： 10.12052/gdutxb.240142

Feng Zihao, Wan Huilong, Lin Jianghao, et al. Reinforcement Learning-based Automatic Tuning Method and Application of Injection Molding Process Parameters[J]. 2025, 42(2): 59-69. DOI： 10.12052/gdutxb.240142.

摘要

注塑工艺参数的优化在当代制造业中至关重要，它不仅影响产品质量，还决定了生产成本和效率。传统的人工调优方法依赖试错，导致生产周期延长和成本上升。为此，本文首次将强化学习(Reinforcement Learning

RL)技术应用于注塑工艺参数调优，提出了一种基于RL的新型注塑工艺参数自动调优算法，旨在通过智能化手段优化注塑过程。首先，本文将注塑工艺参数调优问题建模为顺序决策问题，并设计了一个定制化的马尔可夫决策过程模型。然后，提出了一种无模型的RL方法，基于Q-learning算法实现了注塑工艺参数的自动选择。与传统方法相比，该算法能在动态变化的生产环境中自动探索并优化工艺参数配置。最后，通过实验验证了所提方法的可行性和有效性，展示了较好的应用潜力。

Abstract

The optimization of injection molding process parameters is crucial in contemporary manufacturing

as it affects not only product quality but also production costs and efficiency. Traditional manual tuning methods rely on trial and error

leading to extended production cycles and increased costs. To address this

reinforcement learning (RL) technology is applied

for the first time

to the tuning of injection molding process parameters

proposing a novel automatic tuning algorithm based on RL for injection molding process parameters. The paper first models the injection molding process parameter tuning problem as a sequential decision-making problem and designs a customized Markov Decision Process model. Subsequently

a model-free RL method is proposed

implementing the automatic selection of injection molding process parameters based on the Q-learning algorithm. Compared with traditional methods

this algorithm can automatically explore and optimize process parameter configurations in dynamically changing production environments. Finally

the feasibility and effectiveness of the proposed method are experimentally validated

demonstrating significant application potential.

关键词

Keywords

references

ZHENG R, TANNER R I, FAN X J. Injection molding: integration of theory and modeling methods[M]. Berlin: Springer Science Business Media, 2011.

YU S H, HE X M, Z G Y. Optimization of injection molding process based on response surface model and NSGA-II algorithm[J]. Journal of Plasticity Engineering, 2014, 21(3): 15-19.

KHOSRAVANI M R, NASIRI S. Injection molding manufacturing process: review of case-based reasoning applications[J]. Journal of Intelligent Manufacturing, 2020, 31: 847-864.

OZCELIK B, ERZURUMLU T. Determination of effecting dimensional parameters on warpage of thin shell plastic parts using integrated response surface method and genetic algorithm[J]. International Communications in Heat and Mass Transfer, 2005, 32(8): 1085-1094.

OKTEM H, ERZURUMLU T, UZMAN I. Application of Taguchi optimization technique in determining plastic injection molding process parameters for a thin-shell part[J]. Materials Design, 2007, 28(4): 1271-1278.

SHEN C, WANG L, LI Q. Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method[J]. Journal of Materials Processing Technology, 2007, 183(2-3): 412-418.

ALTAN M. Reducing shrinkage in injection moldings via the Taguchi, ANOVA and neural network methods[J]. Materials Design, 2010, 31(1): 599-604.

WANG G, ZHAO G, LI H, et al . Research on optimization design of the heating/cooling channels for rapid heat cycle molding based on response surface methodology and constrained particle swarm optimization[J ] . Expert Systems with Applications, 2011, 38(6): 6705-6719.

XU Y, ZHANG Q W, ZHANG W, et al . Optimization of injection molding process parameters to improve the mechanical performance of polymer product against impact[J ] . The International Journal of Advanced Manufacturing Technology, 2015, 76: 2199-2208.

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: 473-487.

MOAYYEDIAN M, ABHARY K, MARIAN R. Optimization of injection molding process based on fuzzy quality evaluation and Taguchi experimental design[J]. CIRP Journal of Manufacturing Science and Technology, 2018, 21: 150-160.

ALAM S T, AMIN M A. Determining optimum design parameters of foldable product using response surface methodology and genetic algorithm[J]. Engineering, 2020, 12(11): 839-850.

HU L, GAO H, LI Y, et al . An optimization method of injection molding process parameters based on classification model[J ] . Plastics Industry, 2017, 45(3): 74-78.

RIBEIRO B. Support vector machines for quality monitoring in a plastic injection molding process[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) , 2005, 35(3): 401-410.

YE D, CHEN G, ZHANG W, et al . Towards playing full moba games with deep reinforcement learning[J ] . Advances in Neural Information Processing Systems, 2020, 33: 621-632.

KOBER J, BAGNELL J A, PETERS J. Reinforcement learning in robotics: a survey[J]. The International Journal of Robotics Research, 2013, 32(11): 1238-1274.

WANG N, GAO Y, ZHAO H, et al . R einforcement learning-based optimal tracking control of an unknown unmanned surface vehicle[J ] . IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(7): 3034-3045.

ZHAO Z, HE W, MU C, et al . Reinforcement learning control for a 2-DOF helicopter with state constraints: theory and experiments[J ] . IEEE Transactions on Automation Science and Engineering, 2022, 21(1): 157-167.

DONG H, YANG J, LI S B, et al . Research progress of robot motion control based on deep reinforcement learning[J ] . Control and Decision, 2022, 37(2): 278-292.

AFSAR M M, CRUMP T, FAR B. Reinforcement learning based recommender systems: a survey[J]. ACM Computing Surveys, 2022, 55(7): 1-38.

CHEN X, YAO L, MCAULEY J, et al . Deep reinforcement learning in recommender systems: a survey and new perspectives[J ] . Knowledge-based Systems, 2023, 264: 110335.

LIU C, DING J, SUN J. Reinforcement learning based decision making of operational indices in process industry under changing environment[J]. IEEE Transactions on Industrial Informatics, 2020, 17(4): 2727-2736.

OLIFF H, LIU Y, KUMAR M, et al . Reinforcement learning for facilitating human-robot-interaction in manufacturing[J ] . Journal of Manufacturing Systems, 2020, 56: 326-340.

LENG J, RUAN G, SONG Y, et al . A loosely-coupled deep reinforcement learning approach for order acceptance decision of mass-individualized printed circuit board manufacturing in industry 4.0[J ] . Journal of Cleaner Production, 2021, 280: 124405.

TANG Z T, SHAO K, ZHAO D B, et al . Recent progress of deep reinforcement learning: from AlphaGo to AlphaGo Zero[J ] . Control Theory and Technology, 2017, 34(12): 1529-1546.

LI M L, ZHANG Y, KANG J W, et al . Secure data sharing in blockchain-enabled vehicular networks based on multi-agent reinforcement learning[J ] . Journal of Guangdong University of Technology, 2021, 38(6): 62-69.

GUO X D, DING H Q. An AGV path planning method for discrete manufacturing smart factory[J]. Journal of Guangdong University of Technology, 2021, 38(6): 70-76.

DAYAN P, WATKINS C. Q-learning[J]. Machine Learning, 1992, 8(3): 279-292.

SUTTON R S, BARTO A G. Reinforcement learning: an introduction[M]. Cambridge: MIT Press, 2018.

MNIH V, KAVUKCUOGLU K, SILVER D, et al . Human-level control through deep reinforcement learning[J ] . Nature, 2015, 518(7540): 529-533.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深度强化学习的对话策略网络

基于深度强化学习的车联网频谱分配研究

基于技能发现的元强化学习

基于多智能体注意力机制的自动巡检路线强化学习模型

改进判别式深度Dyna-Q的任务对话策略学习方法