基于多基因遗传规划的注塑过程参数关联预测方法  

Parameter-correlation prediction method for injection molding process based on multi-gene genetic programming

作　　者：蒋小俊 战洪飞[1] 林颖俊 余军合[1] 王瑞 JIANG Xiaojun;ZHAN Hongfei;LIN Yingjun;YU Junhe;WANG Rui(School of Mechanical Engineering&Mechanics,Ningbo University,Ningbo 315211;Zhong Yin(Ningbo)Battery Limited Company,Ningbo 315040)

机构地区：[1]宁波大学机械工程与力学学院,浙江宁波315211 [2]中银(宁波)电池有限公司,浙江宁波315040

出　　处：《机械设计》2024年第4期74-82,共9页Journal of Machine Design

基　　金：国家重点研发计划项目(2019YFB1707101,2019YFB1707103);浙江省省属高校基本科研业务费项目(SJLZ2023001)。

摘　　要：鉴于传统注塑过程参数选择与设置依赖于人工经验,且过程参数与输出参数之间存在着非线性、强耦合的关系,文中提出了一种基于多基因遗传规划的注塑过程参数关联预测方法。该方法基于数据生成初始多基因树种群,随后迭代进行选择,高、低级树交叉及两类树突变操作,以获得最适应数据的模型,并演化出一个能清晰描述过程参数与输出参数关联的代数方程,确定控制输出的关键参数。在设置选择指标时,针对模型方程的复杂性会影响到实际使用效率的问题,引入复杂性维度作为评估指标进行多目标选择。以注塑过程为例,试验结果表明了所提方法的有效性。此外,参数和灵敏度分析验证了模型的鲁棒性,揭示了参数间隐藏的非线性关系,对后续注塑过程参数设置及优化提供了依据。In this article,since the selection and setting of parameters in the traditional injection molding process depend on manual experience,and there is a nonlinear and strong coupling relationship between the process parameters and the output parameters,a parameter-correlation prediction method for the injection molding process is proposed based on multi-gene genetic programming.This method generates an initial multi-gene tree population according to the specific data,and then performs iterative selection,high-level and low-level tree crossover,as well as two types of tree mutation operations,in order to identify the most suitable model for the data;besides,efforts are made to evolve an algebraic equation that can clearly describe the relationship between the process parameters and the output parameters,so as to determine the key parameters for output control.When setting the selection index,since the model equation’s complexity will affect the efficiency in utilization,the complexity dimension is introduced as an evaluation index for multi-objective selection.With the injection molding process as an example,the experiments show that this method is effective.In addition,the parameter and sensitivity analysis has verified the model’s robustness and revealed the hidden nonlinear relationship between various parameters.This study provides basis for parameter setting and optimization of the subsequent injection molding process.

关 键 词：参数关联预测 多基因遗传规划 多目标选择 注塑过程 

分 类 号：TQ320.66[化学工程—合成树脂塑料工业] TP18[自动化与计算机技术—控制理论与控制工程]