Interpretable Machine Learning Method for Modelling Fatigue Short Crack Growth Behaviour

IF 3.3 3区材料科学 Q2 MATERIALS SCIENCE, MULTIDISCIPLINARY Metals and Materials International Pub Date : 2024-02-10 DOI:10.1007/s12540-024-01628-6

Shuwei Zhou, Bing Yang, Shoune Xiao, Guangwu Yang, Tao Zhu

{"title":"Interpretable Machine Learning Method for Modelling Fatigue Short Crack Growth Behaviour","authors":"Shuwei Zhou, Bing Yang, Shoune Xiao, Guangwu Yang, Tao Zhu","doi":"10.1007/s12540-024-01628-6","DOIUrl":null,"url":null,"abstract":"<div><p>Interpretable machine learning (ML) has become a popular tool in the field of science and engineering. This research proposed a domain knowledge combined with ML method to increase interpretability while ensuring the accuracy of ML models and verifies the generality of the ML approach in fatigue crack growth (FCG) modelling. LZ50 steel single edge notch tension (SENT) specimens were tested for short crack (SC) growth rate and microstructure characterization under various <i>R</i>-controls. Based on the test results, the SC growth process was divided into 3 stages: microstructural short crack (0–145 μm), physical short crack (145–1000 μm), and long crack (1000 μm–fracture). Following the analysis of 8 semi-empirical FSCG rate equations with different driving forces, 6 impact variables that may affect the FCG rate characteristics were identified. Random forest and Pearson correlation analysis were used to investigate the influence of each feature on the FCG rate and the relationships among the features. The main influential features for the short crack symbolic regression (SCSR) model were found to be |Δ<i>K</i>–Δ<i>K</i><sub><i>a</i>t</sub>|, Δ<i>γ</i><sub><i>xy</i></sub>, |<i>a</i>–<i>a</i><sub>t</sub>|, and <i>e</i><sup><i>α</i>(1−<i>R</i>)</sup>. After considering these 4 input features, the predicted FSCG rate equation generated by the SR model has a concise mathematical structure. Finally, an elastic net multiple linear regression method was proposed to determine the parameters of the predicted equation, while retaining the physical characteristics of each parameter. The SCSR model for SC demonstrated good prediction performance on various metallic materials.</p><h3>Graphical Abstract</h3><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":703,"journal":{"name":"Metals and Materials International","volume":"30 7","pages":"1944 - 1964"},"PeriodicalIF":3.3000,"publicationDate":"2024-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Metals and Materials International","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1007/s12540-024-01628-6","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

Interpretable machine learning (ML) has become a popular tool in the field of science and engineering. This research proposed a domain knowledge combined with ML method to increase interpretability while ensuring the accuracy of ML models and verifies the generality of the ML approach in fatigue crack growth (FCG) modelling. LZ50 steel single edge notch tension (SENT) specimens were tested for short crack (SC) growth rate and microstructure characterization under various R-controls. Based on the test results, the SC growth process was divided into 3 stages: microstructural short crack (0–145 μm), physical short crack (145–1000 μm), and long crack (1000 μm–fracture). Following the analysis of 8 semi-empirical FSCG rate equations with different driving forces, 6 impact variables that may affect the FCG rate characteristics were identified. Random forest and Pearson correlation analysis were used to investigate the influence of each feature on the FCG rate and the relationships among the features. The main influential features for the short crack symbolic regression (SCSR) model were found to be |ΔK–ΔK_at|, Δγ_xy, |a–a_t|, and e^α(1−R). After considering these 4 input features, the predicted FSCG rate equation generated by the SR model has a concise mathematical structure. Finally, an elastic net multiple linear regression method was proposed to determine the parameters of the predicted equation, while retaining the physical characteristics of each parameter. The SCSR model for SC demonstrated good prediction performance on various metallic materials.

Graphical Abstract

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

用于模拟疲劳短裂纹生长行为的可解释机器学习方法

可解释的机器学习（ML）已成为科学和工程领域的流行工具。本研究提出了一种领域知识与 ML 相结合的方法，以提高可解释性，同时确保 ML 模型的准确性，并验证了 ML 方法在疲劳裂纹生长（FCG）建模中的通用性。在不同的 R 控制下，对 LZ50 钢单边缺口拉伸（SENT）试样进行了短裂纹（SC）生长率和微观结构特征测试。根据测试结果，将短裂纹的生长过程分为 3 个阶段：微观结构短裂纹（0-145 μm）、物理短裂纹（145-1000 μm）和长裂纹（1000 μm-断裂）。在对不同驱动力的 8 个半经验 FSCG 速率方程进行分析后，确定了可能影响 FCG 速率特征的 6 个影响变量。采用随机森林和皮尔逊相关分析法研究了各特征对 FCG 率的影响以及各特征之间的关系。结果发现，对短裂缝符号回归（SCSR）模型有影响的主要特征是|ΔK-ΔKat|、Δγxy、|a-at|和eα(1-R)。考虑了这 4 个输入特征后，SR 模型生成的预测 FSCG 率方程具有简明的数学结构。最后，提出了一种弹性网多元线性回归方法来确定预测方程的参数，同时保留了每个参数的物理特性。用于 SC 的 SCSR 模型在各种金属材料上都表现出了良好的预测性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Metals and Materials International 工程技术-材料科学：综合

CiteScore

7.10

自引率

8.60%

发文量

197

审稿时长

3.7 months

期刊介绍： Metals and Materials International publishes original papers and occasional critical reviews on all aspects of research and technology in materials engineering: physical metallurgy, materials science, and processing of metals and other materials. Emphasis is placed on those aspects of the science of materials that are concerned with the relationships among the processing, structure and properties (mechanical, chemical, electrical, electrochemical, magnetic and optical) of materials. Aspects of processing include the melting, casting, and fabrication with the thermodynamics, kinetics and modeling.