Based on WCA-KELM and MOSOA: optimization of injection molding quality for plastic alloy products
- 8 July 2025
- journal article
- research article
- Published by Walter de Gruyter GmbH in Journal of Polymer Engineering
- Vol. 45 (8) , 710-721
Abstract
For PC/ABS plastic alloy injection-molded products, warping and volumetric shrinkage are two prevalent quality defects attributed to the injection molding process. To mitigate these defects to the greatest extent, this study introduces an optimized injection molding process parameter scheme based on the water cycle algorithm enhanced kernel extreme learning machine (WCA-KELM), the multi-objective seagull optimization algorithm (MOSOA), and grey relational evaluation. Firstly, all experimental data were derived from orthogonal experimental designs conducted via Moldflow software, focusing on seven factors, such as melt temperature, mold temperature, packing pressure, and packing time. Warpage and volume shrinkage results were obtained in each set of experiments. Secondly, the predictive accuracy of the unoptimized kernel extreme learning machine (KELM) model was compared against that of the WCA-KELM model within this optimization framework, demonstrating that the WCA-KELM model predicts defect values with enhanced precision. Finally, the MOSOA was utilized to identify the pareto optimal frontier, from which the optimal solution was pinpointed through grey relational evaluation. According to the results, the warpage and volume shrinkage are 0.9388 mm and 8.538 %, respectively, which are effectively reduced by 41.73 % and 18.37 % compared with before optimization, indicating the efficacy and reliability of the proposed optimization methodology.Keywords
Funding Information
- Innovation Program of Jiangsu Normal University (2024XKT0632)
- National Natural Science Foundation of China (52075231)
- Innovation Program of Jiangsu Normal University (2024XKT0632)
- National Natural Science Foundation of China (52075231)
This publication has 18 references indexed in Scilit:
- Multi-objective optimization of residential building energy consumption, daylighting, and thermal comfort based on BO-XGBoost-NSGA-IIBuilding and Environment, 2024
- The adaptive kernel-based extreme learning machine for state of charge estimationIonics, 2023
- Objectives, challenges, and prospects of batch processes: Arising from injection molding applicationsKorean Journal of Chemical Engineering, 2022
- Recent progress in minimizing the warpage and shrinkage deformations by the optimization of process parameters in plastic injection molding: a reviewThe International Journal of Advanced Manufacturing Technology, 2022
- Correction to: Decision-making for structural parameters of injection mold gating system based on agent model and intelligent algorithmThe International Journal of Advanced Manufacturing Technology, 2022
- Machine learning aided design of conformal cooling channels for injection moldingJournal of Intelligent Manufacturing, 2021
- Multi‐objective optimization of injection molding parameters, based on the Gkriging‐NSGA‐vague methodJournal of Applied Polymer Science, 2019
- Experimental-Based Multi-objective Optimization of Injection Molding Process ParametersArabian Journal for Science and Engineering, 2019
- An inverse model for injection molding of optical lens using artificial neural network coupled with genetic algorithmJournal of Intelligent Manufacturing, 2014
- Water cycle algorithm – A novel metaheuristic optimization method for solving constrained engineering optimization problemsComputers & Structures, 2012