Moayyedian Mehdi, Qazani Mohammad Reza Chalak, Amirkhizi Parisa Jourabchi, Asadi Houshyar, Hedayati-Dezfooli Mohsen
College of Engineering and Technology, American University of the Middle East, Egaila, 54200, Kuwait.
Faculty of Computing and Information Technology (FoCIT), Sohar University, Sohar, 311, Oman.
Sci Rep. 2024 Oct 10;14(1):23767. doi: 10.1038/s41598-024-62618-7.
This research focuses on utilizing injection moulding to assess defects in plastic products, including sink marks, shrinkage, and warpages. Process parameters, such as pure cooling time, mould temperature, melt temperature, and pressure holding time, are carefully selected for investigation. A full factorial design of experiments is employed to identify optimal settings. These parameters significantly affect the physical and mechanical properties of the final product. Soft computing methods, such as finite element (FE), help mitigate behaviour by considering different input parameters. A CAD model of a dashboard component integrates into an FE simulation to quantify shrinkage, warpage, and sink marks. Four chosen parameters of the injection moulding machine undergo comprehensive experimental design. Decision tree, multilayer perceptron, long short-term memory, and gated recurrent units models are explored for injection moulding process modelling. The best model estimates defects. Multiple objectives particle swarm optimisation extracts optimal process parameters. The proposed method is implemented in MATLAB, providing 18 optimal solutions based on the extracted Pareto-Front.
本研究着重于利用注塑成型来评估塑料制品中的缺陷，包括缩痕、收缩和翘曲。仔细选择诸如纯冷却时间、模具温度、熔体温度和保压时间等工艺参数进行研究。采用全因子实验设计来确定最佳设置。这些参数会显著影响最终产品的物理和机械性能。诸如有限元（FE）等软计算方法通过考虑不同输入参数来帮助减轻相关行为。仪表盘部件的CAD模型被集成到FE模拟中，以量化收缩、翘曲和缩痕。对注塑机的四个选定参数进行全面的实验设计。探索决策树、多层感知器、长短期记忆和门控循环单元模型用于注塑成型过程建模。最佳模型估计缺陷。多目标粒子群优化算法提取最优工艺参数。所提出的方法在MATLAB中实现，基于提取的帕累托前沿提供18个最优解。
