<p>This study investigates the development of composites based on poly(lactic acid) as a polymer matrix and cellulose nanocrystals (CNC) as reinforcement. The objective of the study was to explore the use of artificial neural networks (ANNs) to predict the mechanical properties of PLA/CNC nanocomposites, prepared by melt extrusion and injection processes. The study details the preparation of PLA/CNC nanocomposites, followed by tensile tests to evaluate their mechanical properties. The employment of a neural network was employed to model the stress–strain curves enabling the precise prediction of mechanical parameters such as maximum stress, Young’s modulus, and maximum elongation. The results show that the artificial neural network model achieved notable prediction accuracy, and based on the model obtained, a software was developed to calculate the values of the mechanical properties of the materials. The employment of the artificial neural network model and developed software has been demonstrated to offer a highly start point to reduce the need for extensive physical experiments and consequently save time, costs, and resources in the characterization of novel materials.</p> Graphical abstract <p></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

Artificial neural network for predicting the mechanical behavior of extruded poly(lactic acid)/cellulose nanocrystal nanocomposites

  • Jorge Hernando Tobón López,
  • Liliane Cristina Battirola,
  • Joylan Nunes Maciel

摘要

This study investigates the development of composites based on poly(lactic acid) as a polymer matrix and cellulose nanocrystals (CNC) as reinforcement. The objective of the study was to explore the use of artificial neural networks (ANNs) to predict the mechanical properties of PLA/CNC nanocomposites, prepared by melt extrusion and injection processes. The study details the preparation of PLA/CNC nanocomposites, followed by tensile tests to evaluate their mechanical properties. The employment of a neural network was employed to model the stress–strain curves enabling the precise prediction of mechanical parameters such as maximum stress, Young’s modulus, and maximum elongation. The results show that the artificial neural network model achieved notable prediction accuracy, and based on the model obtained, a software was developed to calculate the values of the mechanical properties of the materials. The employment of the artificial neural network model and developed software has been demonstrated to offer a highly start point to reduce the need for extensive physical experiments and consequently save time, costs, and resources in the characterization of novel materials.

Graphical abstract