Scholarlink

<p>This study experimentally investigates the parametric influence and optimization of the material extrusion (MEX) process using a statistical analysis and artificial intelligence (AI)–driven multi-objective decision-making approach for thermoplastic parts. Experiments were conducted to examine the effects of print head temperature, layer size, and feed rate on mechanical strength and manufacturing time. The experimental results were analyzed using response surface methodology and multi-objective genetic algorithm for optimization, while the technique for order of preference by similarity to ideal solution (TOPSIS) was employed for ranking optimal parameter combinations. Additionally, microstructural analysis of fractured samples was performed to correlate actual process conditions with material bonding and fracture behavior. The integrated optimization approach effectively identified optimal process parameters: print head temperature of 230 ℃, layer size of 0.25&#xa0;mm, and feed rate of 55&#xa0;mm/min, which consistently resulted in high tensile mechanical strength and reduced manufacturing time. Study achieved a maximum tensile mechanical strength of 36.554&#xa0;MPa and minimized manufacturing time to 27.965&#xa0;min, while TOPSIS provided a balanced optimization with high closeness coefficients, confirming the reliability of these settings. Confirmation experiments validated the model predictions, showing a 3.25% and 1.32% of improvement in tensile strength and reduction in manufacturing time respectively. This study provides valuable insights into process optimization for MEX-AM.</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 Material Extrusion Process with Artificial Intelligence–Based Multi-Objective Decision-Making

  • 期刊论文

  • 发表日期：

    2025年10月27日

查看全文
  • Saty Dev,
  • Rajeev Srivastava,
  • Manjoo Rani,
  • Ravindra Kumar

摘要

This study experimentally investigates the parametric influence and optimization of the material extrusion (MEX) process using a statistical analysis and artificial intelligence (AI)–driven multi-objective decision-making approach for thermoplastic parts. Experiments were conducted to examine the effects of print head temperature, layer size, and feed rate on mechanical strength and manufacturing time. The experimental results were analyzed using response surface methodology and multi-objective genetic algorithm for optimization, while the technique for order of preference by similarity to ideal solution (TOPSIS) was employed for ranking optimal parameter combinations. Additionally, microstructural analysis of fractured samples was performed to correlate actual process conditions with material bonding and fracture behavior. The integrated optimization approach effectively identified optimal process parameters: print head temperature of 230 ℃, layer size of 0.25 mm, and feed rate of 55 mm/min, which consistently resulted in high tensile mechanical strength and reduced manufacturing time. Study achieved a maximum tensile mechanical strength of 36.554 MPa and minimized manufacturing time to 27.965 min, while TOPSIS provided a balanced optimization with high closeness coefficients, confirming the reliability of these settings. Confirmation experiments validated the model predictions, showing a 3.25% and 1.32% of improvement in tensile strength and reduction in manufacturing time respectively. This study provides valuable insights into process optimization for MEX-AM.