Scholarlink

This study explores the optimization of injection molding process parameters using K-means clustering, an artificial intelligence technique, to mitigate defects such as sink marks, cooling inefficiencies, and volumetric shrinkage. By analyzing six critical parameters—Mold Temperature, Melt Temperature, Coolant Temperature, Injection Pressure Limit, Pure Cooling Time, and Pressure Holding Time—through simulations conducted in SolidWorks Plastics, the research identifies optimal parameter combinations that enhance product quality and process efficiency. SPSS software facilitated the K-means clustering, which resulted in ten distinct clusters representing unique parameter configurations. Clusters with moderate mold and melt temperatures and optimal cooling times demonstrated reduced defects, with Cluster 3 and Cluster 8 emerging as optimal baselines. The study's findings are validated using ANOVA, confirming significant differences across clusters and the efficacy of K-means clustering in process optimization. This research contributes to sustainable manufacturing practices, aligning with Sustainable Development Goals (SDGs) related to industry innovation, responsible production, and climate action, while also providing a framework for future advancements in real-time monitoring and AI integration in manufacturing.

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

Optimizing Injection Molding Process Parameters Using Artificial Intelligence-Based K-Means Clustering: A Simulation Data and Computer-Aided Engineering Approach

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Sonia M. Pol,
  • Bhushan T. Patil,
  • Amit J. Lopes

摘要

This study explores the optimization of injection molding process parameters using K-means clustering, an artificial intelligence technique, to mitigate defects such as sink marks, cooling inefficiencies, and volumetric shrinkage. By analyzing six critical parameters—Mold Temperature, Melt Temperature, Coolant Temperature, Injection Pressure Limit, Pure Cooling Time, and Pressure Holding Time—through simulations conducted in SolidWorks Plastics, the research identifies optimal parameter combinations that enhance product quality and process efficiency. SPSS software facilitated the K-means clustering, which resulted in ten distinct clusters representing unique parameter configurations. Clusters with moderate mold and melt temperatures and optimal cooling times demonstrated reduced defects, with Cluster 3 and Cluster 8 emerging as optimal baselines. The study's findings are validated using ANOVA, confirming significant differences across clusters and the efficacy of K-means clustering in process optimization. This research contributes to sustainable manufacturing practices, aligning with Sustainable Development Goals (SDGs) related to industry innovation, responsible production, and climate action, while also providing a framework for future advancements in real-time monitoring and AI integration in manufacturing.