{"title":"A general framework of high-performance machine learning algorithms: application in structural mechanics","authors":"","doi":"10.1007/s00466-023-02386-9","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>Data-driven models utilizing powerful artificial intelligence (AI) algorithms have been implemented over the past two decades in different fields of simulation-based engineering science. Most numerical procedures involve processing data sets developed from physical or numerical experiments to create closed-form formulae to predict the corresponding systems’ mechanical response. Efficient AI methodologies that will allow the development and use of accurate predictive models for solving computational intensive engineering problems remain an open issue. In this research work, high-performance machine learning (ML) algorithms are proposed for modeling structural mechanics-related problems, which are implemented in parallel and distributed computing environments to address extremely computationally demanding problems. Four machine learning algorithms are proposed in this work and their performance is investigated in three different structural engineering problems. According to the parametric investigation of the prediction accuracy, the extreme gradient boosting with extended hyper-parameter optimization (XGBoost-HYT-CV) was found to be more efficient regarding the generalization errors deriving a 4.54% residual error for all test cases considered. Furthermore, a comprehensive statistical analysis of the residual errors and a sensitivity analysis of the predictors concerning the target variable are reported. Overall, the proposed models were found to outperform the existing ML methods, where in one case the residual error was decreased by 3-fold. Furthermore, the proposed algorithms demonstrated the generic characteristic of the proposed ML framework for structural mechanics problems.</p>","PeriodicalId":55248,"journal":{"name":"Computational Mechanics","volume":"17 1","pages":""},"PeriodicalIF":3.7000,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational Mechanics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s00466-023-02386-9","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Data-driven models utilizing powerful artificial intelligence (AI) algorithms have been implemented over the past two decades in different fields of simulation-based engineering science. Most numerical procedures involve processing data sets developed from physical or numerical experiments to create closed-form formulae to predict the corresponding systems’ mechanical response. Efficient AI methodologies that will allow the development and use of accurate predictive models for solving computational intensive engineering problems remain an open issue. In this research work, high-performance machine learning (ML) algorithms are proposed for modeling structural mechanics-related problems, which are implemented in parallel and distributed computing environments to address extremely computationally demanding problems. Four machine learning algorithms are proposed in this work and their performance is investigated in three different structural engineering problems. According to the parametric investigation of the prediction accuracy, the extreme gradient boosting with extended hyper-parameter optimization (XGBoost-HYT-CV) was found to be more efficient regarding the generalization errors deriving a 4.54% residual error for all test cases considered. Furthermore, a comprehensive statistical analysis of the residual errors and a sensitivity analysis of the predictors concerning the target variable are reported. Overall, the proposed models were found to outperform the existing ML methods, where in one case the residual error was decreased by 3-fold. Furthermore, the proposed algorithms demonstrated the generic characteristic of the proposed ML framework for structural mechanics problems.
摘要 在过去的二十年里，以数据为驱动的模型利用强大的人工智能（AI）算法在不同的模拟工程科学领域得到了应用。大多数数值程序涉及处理从物理或数值实验中开发的数据集，以创建闭式公式来预测相应系统的机械响应。高效的人工智能方法可以开发和使用精确的预测模型来解决计算密集型工程问题，但这仍然是一个有待解决的问题。在这项研究工作中，提出了用于结构力学相关问题建模的高性能机器学习（ML）算法，这些算法在并行和分布式计算环境中实施，以解决计算要求极高的问题。本研究提出了四种机器学习算法，并在三个不同的结构工程问题中对其性能进行了研究。根据对预测准确性的参数调查，发现在所有测试案例中，具有扩展超参数优化功能的极梯度提升算法（XGBoost-HYT-CV）在泛化误差方面更有效，其残差误差为 4.54%。此外，报告还对残差误差进行了综合统计分析，并对目标变量的预测因子进行了敏感性分析。总体而言，所提出的模型优于现有的 ML 方法，其中一个案例的残余误差降低了 3 倍。此外，所提出的算法还证明了所提出的 ML 框架在结构力学问题上的通用特性。
期刊介绍：
The journal reports original research of scholarly value in computational engineering and sciences. It focuses on areas that involve and enrich the application of mechanics, mathematics and numerical methods. It covers new methods and computationally-challenging technologies.
Areas covered include method development in solid, fluid mechanics and materials simulations with application to biomechanics and mechanics in medicine, multiphysics, fracture mechanics, multiscale mechanics, particle and meshfree methods. Additionally, manuscripts including simulation and method development of synthesis of material systems are encouraged.
Manuscripts reporting results obtained with established methods, unless they involve challenging computations, and manuscripts that report computations using commercial software packages are not encouraged.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
