基于时序演变粒子群算法的双色注射产品翘曲工艺优化

doi:10.11949/0438-1157.20241431

摘要/Abstract

摘要：

以某轿车精密仪表板双色注射成型为研究对象，通过优化双色注射成型工艺参数，降低产品翘曲变形，从而提高产品质量。鉴于双色注射工艺参数与产品翘曲变形之间呈现高维度、非线性、波动性等特征且多工序耦合严重，极易导致传统优化方法陷入局部最优，造成优化困难等问题，提出了一种基于时序演变的粒子群优化算法(TEPSO)，利用正交膨胀空间均衡散布的优点提高粒子群的搜索能力和效率，并采用Q-Learning思想，通过粒子与环境的不断交互探索，开发基于时序演变的学习策略以确定粒子正交空间的膨胀因子。在某轿车仪表板优化设计中，与初始试验方案相比，采用TEPSO算法优化后仪表板Z向翘曲从4.698 mm降低到2.194 mm，优化效果达到53.3%，证实了TEPSO算法的有效性和实用性。

关键词: 双色注射成型, 粒子群算法, 强化学习, 优化设计, 翘曲变形, 模拟, 预测

Abstract:

This article takes the dual color injection molding of a precision instrument panel for a certain sedan as the research object. By optimizing the dual color injection molding process parameters, the product warpage and deformation are reduced, thereby improving product quality. In view of the high dimensionality, nonlinearity, volatility and other characteristics between the two-color injection process parameters and the product warpage deformation, and the serious coupling of multiple processes, it is very easy to cause the traditional optimization method to fall into the local optimum, resulting in optimization difficulties and other problems. Based on temporal evolution particle swarm optimization algorithm(TEPSO) is proposed to address the above issues. The algorithm utilizes the advantage of balanced dispersion in orthogonal expansion space to improve the search ability and efficiency of particle swarm optimization, and adopts the Q-learning concept to develop a learning strategy based on temporal evolution through continuous interaction and exploration between particles and the environment to determine the expansion factor of particle orthogonal space. Firstly, each particle generates a Q-table, and the corresponding expansion factor is determined based on the Q-table and state. The fitness value change of each particle is obtained as an immediate reward, and the Q-table is updated using social learning behavior strategies. Secondly, the expansion factor is obtained through Q-learning, and orthogonal design is used for expansion to obtain more environmental information. Finally, shrink each orthogonal expansion space, select the particle position with the smallest fitness value to update the current particle position, and complete the iteration. Optimization design of injection molding process parameters for precision instrument panel of a certain sedan, compared with the initial experimental plan, the use of TEPSO algorithm for optimization reduced the Z-direction warping of the outer cover plate from 4.698 mm to 2.194 mm, and the optimization efficiency reached 53.3%, confirming the effectiveness and practicality of TEPSO algorithm.

Key words: dual-color injection molding, particle swarm optimization, reinforcement learning, optimal design, warping and deformation, simulation, prediction

中图分类号:

TQ 320.6

王涛, 李光明, 胡秋霞, 徐静. 基于时序演变粒子群算法的双色注射产品翘曲工艺优化[J]. 化工学报, 2025, 76(7): 3403-3415.

Tao WANG, Guangming LI, Qiuxia HU, Jing XU. Optimization of warpage process for two-color injection products based on temporal evolution particle swarm optimization algorithm[J]. CIESC Journal, 2025, 76(7): 3403-3415.

图/表 19

参考文献 38

[1]	魏翔宇. 汽车三色固定侧尾灯灯罩注塑工艺参数多目标优化与模具设计[D]. 镇江: 江苏大学, 2021.
	Wei X Y. Multi-objective optimization and mold design of injection process parameters for automobile three-color fixed side taillight lampshade[D]. Zhenjiang: Jiangsu University, 2021.
[2]	张海涛. 双色注塑制品翘曲变形的研究[D]. 哈尔滨: 哈尔滨工业大学, 2015.
	Zhang H T. Study on warping deformation of two-color injection molded products[D]. Harbin: Harbin Institute of Technology, 2015.
[3]	Chang R Y, Peng A Y, Yang W H, et al. Three-dimensional simulation of multi-shot sequential molding[C]//Society of Plastics Engineers Annual Technical Conference. Boston, USA, 2005: 47-50.
[4]	Zheng R, Kennedy P, Phan-Thien N, et al. Thermoviscoelastic simulation of thermally and pressure-induced stresses in injection moulding for the prediction of shrinkage and warpage for fibre-reinforced thermoplastics[J]. Journal of Non-Newtonian Fluid Mechanics, 1999, 84(2/3): 159-190.
[5]	Huang C T, Chen M C, Yang W L, et al. Investigation on warpage and its behavior in sequential overmolding[C]//Society of Plastics Engineers Annual Technical Conference. Cincinnati, USA, 2007: 760-764.
[6]	王梦寒, 刘晓, 危康, 等. 基于Kriging与GA的双层变模温注射成型收缩控制策略[J]. 化工学报, 2017, 68(1): 391-397.
	Wang M H, Liu X, Wei K, et al. Strategy of molding shrinkage control for bi-layered RHCM based on Kriging and GA[J]. CIESC Journal, 2017, 68(1): 391-397.
[7]	巫兴悦. 汽车前大灯双色灯罩注塑成型工艺参数优化[D]. 昆明: 昆明理工大学, 2023.
	Wu X Y. Optimization of injection molding process parameters for two-color lampshade of automobile headlights[D]. Kunming: Kunming University of Science and Technology, 2023.
[8]	孟小林, 张继祥, 李又兵, 等. 汽车B柱外饰板双色注塑翘曲变形分析及工艺优化[J]. 工程塑料应用, 2023, 51(2): 54-59.
	Meng X L, Zhang J X, Li Y B, et al. Warpage deformation analysis and process optimization of automotive B-pillar exterior panel with two-color injection[J]. Engineering Plastics Application, 2023, 51(2): 54-59.
[9]	Pisanu L, Santiago L C, Barbosa J D V, et al. Effect of the process parameters on the adhesive strength of dissimilar polymers obtained by multicomponent injection molding[J]. Polymers, 2021, 13(7): 1039.
[10]	Li J, Wang Z C, Xie J, et al. Study on the processes and warpage of double‐injection‐molded parts containing PP recycled materials[J]. Polymer Engineering & Science, 2024, 64(4): 1686-1698.
[11]	楚焱芳. 基于粒子群神经网络的双色注塑工艺参数优化[D]. 南京: 南京理工大学, 2011.
	Chu Y F. Optimization of process parameters of two-color injection molding based on particle swarm neural network[D]. Nanjing: Nanjing University of Science and Technology, 2011.
[12]	Huang M S, Ke K C, Liu C Y. Cavity pressure-based holding pressure adjustment for enhancing the consistency of injection molding quality[J]. Journal of Applied Polymer Science, 2021, 138(18): 50357.
[13]	Bensingh R J, Machavaram R, Boopathy S R, et al. Injection molding process optimization of a bi-aspheric lens using hybrid artificial neural networks (ANNs) and particle swarm optimization (PSO)[J]. Measurement, 2019, 134: 359-374.
[14]	Cheng J, Liu Z Y, Tan J R. Multiobjective optimization of injection molding parameters based on soft computing and variable complexity method[J]. The International Journal of Advanced Manufacturing Technology, 2013, 66(5): 907-916.
[15]	Moayyedian M, Qazani M R C, Amirkhizi P J, et al. Multiple objectives optimization of injection-moulding process for dashboard using soft computing and particle swarm optimization[J]. Scientific Reports, 2024, 14(1): 23767.
[16]	Zeng W, Yi G D, Zhang S Y, et al. Multi-objective optimization method of injection molding process parameters based on hierarchical sampling and comprehensive entropy weights[J]. The International Journal of Advanced Manufacturing Technology, 2024, 133(3): 1481-1499.
[17]	薛茂远, 梅益, 唐方艳, 等. 基于GA-ELM及遗传算法的注塑件成型工艺优化[J]. 塑料, 2022, 51(1): 56-61, 66.
	Xue M Y, Mei Y, Tang F Y, et al. Optimization of injection molding process based on GA-ELM and genetic algorithm[J]. Plastics, 2022, 51(1): 56-61, 66.
[18]	印磊, 苏小平, 潘杰. 基于NCGA的汽车外饰件注塑成型工艺参数多目标优化[J]. 塑料工业, 2024, 52(8): 95-100.
	Yin L, Su X P, Pan J. Multi objective optimization of injection molding process parameters for automotive exterior parts based on NCGA[J]. China Plastics Industry, 2024, 52(8): 95-100.
[19]	余佳欣. 基于迁移学习的薄壁类零件注塑工艺优化研究[D]. 绵阳: 西南科技大学, 2023.
	Yu J X. Study on injection process optimization of thin-walled parts based on transfer learning[D]. Mianyang: Southwest University of Science and Technology, 2023.
[20]	孙显俊. 聚丙烯及其复合材料注塑件翘曲变形数值模拟与实验研究[D]. 南京: 南京航空航天大学, 2015.
	Sun X J. Numerical simulation and experimental study on warping deformation of polypropylene and its composite injection parts[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2015.
[21]	傅建钢, 赵朋, 傅建中, 等. 电器仪表外壳注塑模具设计[J]. 塑料科技, 2024, 52(2): 112-115.
	Fu J G, Zhao P, Fu J Z, et al. Design of injection mold for electrical instrument shell[J]. Plastics Science and Technology, 2024, 52(2): 112-115.
[22]	Chang R Y, Tsaur B D. Experimental and theoretical studies of shrinkage, warpage, and sink marks of crystalline polymer injection molded parts[J]. Polymer Engineering & Science, 1995, 35(15): 1222-1230.
[23]	张君. 汽车位置灯厚壁Logo饰件注塑模具设计及多目标工艺参数优化[D]. 镇江: 江苏大学, 2023.
	Zhang J. Design of injection mold and optimization of multi-objective process parameters for thick wall Logo decoration of automobile position[D]. Zhenjiang: Jiangsu University, 2023.
[24]	朱宏峰. 随形冷却对注塑成型制品翘曲变形影响研究[D]. 南昌: 南昌大学, 2014.
	Zhu H F. Study on the influence of conformal cooling on warping deformation of injection molded products[D]. Nanchang: Nanchang University, 2014.
[25]	傅超. 基于BP-NSGA Ⅱ的双色贯穿灯注塑工艺参数多目标优化与模具设计[D]. 镇江: 江苏大学, 2023.
	Fu C. Multi-objective optimization of injection process parameters and mold design of two-color through lamp based on BP-NSGA Ⅱ[D]. Zhenjiang: Jiangsu University, 2023.
[26]	Zhao N Y, Lian J Y, Wang P F, et al. Recent progress in minimizing the warpage and shrinkage deformations by the optimization of process parameters in plastic injection molding: a review[J]. The International Journal of Advanced Manufacturing Technology, 2022, 120(1/2): 85-101.
[27]	Kitayama S. Process parameters optimization in plastic injection molding using metamodel-based optimization: a comprehensive review[J]. The International Journal of Advanced Manufacturing Technology, 2022, 121(11): 7117-7145.
[28]	欧阳宇. 进气歧管注塑成型工艺参数及进气性能优化研究[D]. 昆明: 昆明理工大学, 2023.
	Ouyang Y. Study on optimization of injection molding process parameters and intake performance of intake manifold[D]. Kunming: Kunming University of Science and Technology, 2023.
[29]	Eberhart R, Kennedy J. A new optimizer using particle swarm theory[C]//Proceedings of the Sixth International Symposium on Micro Machine and Human Science. Nagoya, Japan: IEEE, 1995: 39-43.
[30]	Watkins C J C H, Dayan P. Q-learning[J]. Machine Learning, 1992, 8: 279-292.
[31]	Sutton R S, Barto A G. Reinforcement learning: an introduction[J]. IEEE Transactions on Neural Networks, 1998, 9(5): 1054.
[32]	罗逸轩, 刘建华, 胡任远, 等. 融合经验共享Q学习的粒子群优化算法[J]. 计算机科学与探索, 2022, 16(9): 2151-2162.
	Luo Y X, Liu J H, Hu R Y, et al. Particle swarm optimization combined with Q-learning of experience sharing strategy[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(9): 2151-2162.
[33]	张程, 邱炳林, 刘佳静, 等. 基于社会学习的粒子群优化算法的电力系统稳定器参数协调优化设计[J]. 电工电能新技术, 2022, 41(4): 24-33.
	Zhang C, Qiu B L, Liu J J, et al. Parameters coordinated optimization design of power system stabilizer by social learning based particle swarm optimization algorithm[J]. Advanced Technology of Electrical Engineering and Energy, 2022, 41(4): 24-33.
[34]	Jiyue E, Liu J L, Wan Z. A novel adaptive algorithm of particle swarm optimization based on the human social learning intelligence[J]. Swarm and Evolutionary Computation, 2023, 80: 101336.
[35]	Kennedy J, Eberhart R. Particle swarm optimization[C]//Proceedings of ICNN’95-International Conference on Neural Networks. Perth, WA, Australia: IEEE, 1995: 1942-1948.
[36]	Holland J H. Genetic algorithms[J]. Scientific American, 1992, 267(1): 66-73.
[37]	Mirjalili S. SCA: a sine cosine algorithm for solving optimization problems[J]. Knowledge-Based Systems, 2016, 96: 120-133.
[38]	Storn R, Price K. Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359.

参数	PP材料	PC+ABS材料
固体密度/(g·cm^-3)	1.3717	1.1251
熔体密度/(g·cm^-3)	1.2309	1.0095
最大剪切应力/MPa	0.25	0.4
最大剪切速率/s^-1	100000	40000
第一方向弹性模量/MPa	2822	2175.78
第二方向弹性模量/MPa	2387	2188.67
泊松比1	0.375	0.374
泊松比2	0.389	0.396

参数	PP材料	PC+ABS材料
固体密度/(g·cm^-3)	1.3717	1.1251
熔体密度/(g·cm^-3)	1.2309	1.0095
最大剪切应力/MPa	0.25	0.4
最大剪切速率/s^-1	100000	40000
第一方向弹性模量/MPa	2822	2175.78
第二方向弹性模量/MPa	2387	2188.67
泊松比1	0.375	0.374
泊松比2	0.389	0.396

参数	固定值
第一色熔体温度/℃	210
第一色注射时间/s	1.6
第一色充填体积/%	99
第一色保压压力/MPa	70
第一色保压时间/s	10
第一色冷却时间/s	25
第二色熔体温度/℃	250
第二色注射时间/s	1.5
第二色充填体积/%	99
第二色保压压力/MPa	95
第二色保压时间/s	7
第二色冷却时间/s	25

参数	固定值
第一色熔体温度/℃	210
第一色注射时间/s	1.6
第一色充填体积/%	99
第一色保压压力/MPa	70
第一色保压时间/s	10
第一色冷却时间/s	25
第二色熔体温度/℃	250
第二色注射时间/s	1.5
第二色充填体积/%	99
第二色保压压力/MPa	95
第二色保压时间/s	7
第二色冷却时间/s	25

成型工艺	水平1	水平2	水平3
第一色熔体温度/℃	210	220	230
第一色注射时间/s	1.2	1.6	2
第一色充填体积/%	95	97	99
第一色保压压力/MPa	70	78	85
第一色保压时间/s	7	10	13
第一色冷却时间/s	25	30	35
第二色熔体温度/℃	245	255	265
第二色注射时间/s	1.2	1.5	1.8
第二色充填体积/%	95	97	99
第二色保压压力/MPa	70	78	85
第二色保压时间/s	7	10	13
第二色冷却时间/s	25	30	35