Scholarlink

<p>The main factors affecting the molding quality of&#xa0;the glass fiber injection-molded product are warpage deformation and volume shrinkage. To ensure high molding quality, this paper proposes a multi-objective optimization method for process parameters, using improved light spectrum optimizer optimization random forest (ILSO-RF) model and multi-strategy improved non-dominated sorting whale optimization algorithm (MSINSWOA), specifically addressing warpage deformation and volumetric shrinkage defects. Based on experimental simulation results from face-centered central composite design (FCCD), the ILSO-RF models with minimal prediction error was selected for establishing the relationship between injection molding process parameters and quality objectives. The MSINSWOA algorithm, capable of generating a superior solution set, was then employed for multi-objective optimization on the ILSO-RF models. The Critic method was integrated to determine the optimal combination of process parameters. The optimal combination of process parameters was inputted into Moldflow for injection molding simulation validation. Validation results indicated that the ILSO-RF models maintains prediction errors within 5% for warpage deformation and volumetric shrinkage, demonstrating good prediction accuracy. Warpage deformation and volumetric shrinkage after optimization are reduced by 33.55% and 17.28% respectively, validating the effectiveness of this optimization method</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimization of Glass Fiber Reinforced Injection Molded Product Quality Based on the ILSO-RF Model and MSINSWOA

  • 期刊论文

  • 发表日期：

    2025年3月5日

查看全文
  • Zhijiang Wang,
  • Xiying Fan,
  • Yonghuan Guo,
  • Junyi Hua,
  • Liuyu Zhu,
  • Lie Li

摘要

The main factors affecting the molding quality of the glass fiber injection-molded product are warpage deformation and volume shrinkage. To ensure high molding quality, this paper proposes a multi-objective optimization method for process parameters, using improved light spectrum optimizer optimization random forest (ILSO-RF) model and multi-strategy improved non-dominated sorting whale optimization algorithm (MSINSWOA), specifically addressing warpage deformation and volumetric shrinkage defects. Based on experimental simulation results from face-centered central composite design (FCCD), the ILSO-RF models with minimal prediction error was selected for establishing the relationship between injection molding process parameters and quality objectives. The MSINSWOA algorithm, capable of generating a superior solution set, was then employed for multi-objective optimization on the ILSO-RF models. The Critic method was integrated to determine the optimal combination of process parameters. The optimal combination of process parameters was inputted into Moldflow for injection molding simulation validation. Validation results indicated that the ILSO-RF models maintains prediction errors within 5% for warpage deformation and volumetric shrinkage, demonstrating good prediction accuracy. Warpage deformation and volumetric shrinkage after optimization are reduced by 33.55% and 17.28% respectively, validating the effectiveness of this optimization method