Scholarlink

<p>The accuracy of finite element analysis (FEA) simulations for fused filament fabrication (FFF) 3D-printed parts is often limited by assumptions regarding the material's mechanical properties, particularly when these properties are derived from conventional injection-molded specimens rather than directly measured from 3D-printed components. The acquisition of precise mechanical properties for FEA requires testing 3D-printed samples that exactly replicate printing parameters such as raster angle and infill density and layer thickness, which is a time-consuming and expensive procedure. This study presents a physics-informed neural network (PINN) approach to enhance FEA simulation accuracy for the elasto-plastic tensile behavior, including Young's modulus and yield strength, of 3D-printed polylactic acid (PLA) parts produced via FFF. Experimental tensile test data from various raster angles, infill densities, and layer thicknesses enable us to train a PINN for material property prediction which could differ substantially from traditional injection-molded PLA properties. The approach enables the prediction of this behavior across various printing options while reduces the amount of additional testing within the studied parameter ranges. Benchmark comparisons with conventional machine learning (ML) methods demonstrate PINN's advantages in reducing overfitting and requiring fewer data. The research indicates that combining PINNs with standard FEA techniques leads to better simulation accuracy and represents a budget-friendly alternative to direct testing. The proposed method demonstrates how machine learning technology speeds up computational methods while addressing the precise modeling challenges of 3D-printed materials.</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

Enhancing Finite Element Simulations of 3D-Printed PLA Using Physics-Informed Neural Networks: Validation Through Experimental Tensile Testing and Benchmark Comparisons

  • 期刊论文

  • 发表日期：

    2026年2月5日

查看全文
  • Mohammad Hadi Zahmatkeshan,
  • Farid Reza Biglari,
  • Bijan Mollaei Dariani

摘要

The accuracy of finite element analysis (FEA) simulations for fused filament fabrication (FFF) 3D-printed parts is often limited by assumptions regarding the material's mechanical properties, particularly when these properties are derived from conventional injection-molded specimens rather than directly measured from 3D-printed components. The acquisition of precise mechanical properties for FEA requires testing 3D-printed samples that exactly replicate printing parameters such as raster angle and infill density and layer thickness, which is a time-consuming and expensive procedure. This study presents a physics-informed neural network (PINN) approach to enhance FEA simulation accuracy for the elasto-plastic tensile behavior, including Young's modulus and yield strength, of 3D-printed polylactic acid (PLA) parts produced via FFF. Experimental tensile test data from various raster angles, infill densities, and layer thicknesses enable us to train a PINN for material property prediction which could differ substantially from traditional injection-molded PLA properties. The approach enables the prediction of this behavior across various printing options while reduces the amount of additional testing within the studied parameter ranges. Benchmark comparisons with conventional machine learning (ML) methods demonstrate PINN's advantages in reducing overfitting and requiring fewer data. The research indicates that combining PINNs with standard FEA techniques leads to better simulation accuracy and represents a budget-friendly alternative to direct testing. The proposed method demonstrates how machine learning technology speeds up computational methods while addressing the precise modeling challenges of 3D-printed materials.