Scholarlink

<p>This study evaluates the efficacy of statistical, artificial neural network (ANN), and deep learning (DL) methods in developing mathematical models for estimating dimensionless fracture parameters in single-edge notched bend (SENB) specimens under Mode I/II brittle fracture conditions. The research focuses on this specimen, a commonly used configuration in fracture mechanics studies. The primary objective is to benchmark the accuracy, computational efficiency, and generalization capabilities of various modelling approaches, including linear regression, polynomial regression, Random Forest Regression (RFR), and Bidirectional Long Short-Term Memory (BiLSTM) networks. The study leverages a comprehensive dataset encompassing various geometric configurations and loading conditions to develop predictive models for key fracture parameters such as <i>Y</i><sub><i>I</i></sub>, <i>Y</i><sub><i>II</i></sub>, and <i>T</i><sup><i>*</i></sup>. The results shows that regression methods are insufficient for capturing the complex, non-linear relationships inherent in fracture mechanics. RFR demonstrated superior accuracy with training <i>R²</i> values of 0.99 (<i>Y</i><sub><i>I</i></sub>) and 0.99 (<i>Y</i><sub><i>II</i></sub>), and validation <i>R²</i> values of 0.93(<i>Y</i><sub><i>I</i></sub>), 0.96 (<i>Y</i><sub><i>II</i></sub>), and 0.99 (<i>T</i><sup><i>*</i></sup>). BiLSTM also performed robustly, achieving validation <i>R²</i> values of 0.99 (<i>Y</i><sub><i>I</i></sub>), 0.96 (<i>Y</i><sub><i>II</i></sub>), and 0.99 (<i>T</i><sup><i>*</i></sup>). In contrast, simple regression methods like multiple linear regression (MLR) and polynomial regression (PR) showed limited effectiveness, with <i>R²</i> values as low as 0.44 (MLR) and 0.57 (PR) for <i>Y</i><sub><i>I</i></sub>.</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

A comparative study of machine learning methods for predicting mode I and II brittle fracture in notched bend specimens

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月17日

查看全文
  • Linfeng Li,
  • Haytham F. Isleem,
  • Mohammad Khishe,
  • Ghanshyam G. Tejani

摘要

This study evaluates the efficacy of statistical, artificial neural network (ANN), and deep learning (DL) methods in developing mathematical models for estimating dimensionless fracture parameters in single-edge notched bend (SENB) specimens under Mode I/II brittle fracture conditions. The research focuses on this specimen, a commonly used configuration in fracture mechanics studies. The primary objective is to benchmark the accuracy, computational efficiency, and generalization capabilities of various modelling approaches, including linear regression, polynomial regression, Random Forest Regression (RFR), and Bidirectional Long Short-Term Memory (BiLSTM) networks. The study leverages a comprehensive dataset encompassing various geometric configurations and loading conditions to develop predictive models for key fracture parameters such as YI, YII, and T*. The results shows that regression methods are insufficient for capturing the complex, non-linear relationships inherent in fracture mechanics. RFR demonstrated superior accuracy with training R² values of 0.99 (YI) and 0.99 (YII), and validation R² values of 0.93(YI), 0.96 (YII), and 0.99 (T*). BiLSTM also performed robustly, achieving validation R² values of 0.99 (YI), 0.96 (YII), and 0.99 (T*). In contrast, simple regression methods like multiple linear regression (MLR) and polynomial regression (PR) showed limited effectiveness, with R² values as low as 0.44 (MLR) and 0.57 (PR) for YI.