arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2507.02005cs.CEcs.AI
收藏

基于特征工程与自动化可解释机器学习应用于焊接横向加劲肋的疲劳强度模型发现

Discovery of Fatigue Strength Models via Feature Engineering and automated eXplainable Machine Learning applied to the welded Transverse Stiffener

Institut für Stahlbau, RWTH Aachen University(钢结构研究所,亚琛RWTH大学)

Michael A. Kraus, Helen Bartsch

AI总结:

本文提出将AutoML与XAI相结合的方法,通过特征工程在焊接横向加劲肋疲劳试验数据上训练多种回归模型,发现领域知情模型性能最佳,并识别出应力比、应力幅、屈服强度和焊后处理等关键预测因子,实现了准确且可解释的疲劳强度建模。

摘要:

本研究引入了一种将自动化机器学习(AutoML)与可解释人工智能(XAI)相结合的统一方法,用于预测焊接横向加劲肋细节的疲劳强度。该方法将专家驱动的特征工程与算法化特征创建相集成,以提高准确性和可解释性。基于广泛的疲劳试验数据库,使用AutoML在三种特征方案下训练了回归模型——梯度提升、随机森林和神经网络:领域知情特征、算法生成特征以及二者组合特征。这使得能够系统比较基于专家的特征选择与自动化特征选择。集成方法(例如CatBoost、LightGBM)取得了最佳性能。领域知情模型$\mathcal M_2$实现了最佳平衡:在整个$Δσ_{c,50\\%}$范围内,测试RMSE约为30.6 MPa,$R^2$约为0.780%;在工程相关的0-150 MPa范围内,RMSE约为13.4 MPa,$R^2$约为0.527%。特征更密集的模型($\mathcal M_3$)在训练期间表现出轻微提升,但泛化能力较差,而更简单的基特征模型($\mathcal M_1$)表现相当,证实了极简设计的鲁棒性。XAI方法(SHAP和特征重要性)识别出应力比$R$、应力幅$Δσ_i$、屈服强度$R_{eH}$和焊后处理(TIG打磨与焊态)为主导预测因子。次要几何因素——板宽、焊喉厚度、加劲肋高度——也显著影响疲劳寿命。该框架表明,将AutoML与XAI相集成能够为焊接钢结构生成准确、可解释且鲁棒的疲劳强度模型。它桥接了数据驱动建模与工程验证,使AI辅助设计和评估成为可能。未来工作将探索概率疲劳寿命建模以及集成到数字孪生环境中。

英文摘要:

This research introduces a unified approach combining Automated Machine Learning (AutoML) with Explainable Artificial Intelligence (XAI) to predict fatigue strength in welded transverse stiffener details. It integrates expert-driven feature engineering with algorithmic feature creation to enhance accuracy and explainability. Based on the extensive fatigue test database regression models - gradient boosting, random forests, and neural networks - were trained using AutoML under three feature schemes: domain-informed, algorithmic, and combined. This allowed a systematic comparison of expert-based versus automated feature selection. Ensemble methods (e.g. CatBoost, LightGBM) delivered top performance. The domain-informed model $\mathcal M_2$ achieved the best balance: test RMSE $\approx$ 30.6 MPa and $R^2 \approx 0.780% over the full $Δσ_{c,50\%}$ range, and RMSE $\approx$ 13.4 MPa and $R^2 \approx 0.527% within the engineering-relevant 0 - 150 MPa domain. The denser-feature model ($\mathcal M_3$) showed minor gains during training but poorer generalization, while the simpler base-feature model ($\mathcal M_1$) performed comparably, confirming the robustness of minimalist designs. XAI methods (SHAP and feature importance) identified stress ratio $R$, stress range $Δσ_i$, yield strength $R_{eH}$, and post-weld treatment (TIG dressing vs. as-welded) as dominant predictors. Secondary geometric factors - plate width, throat thickness, stiffener height - also significantly affected fatigue life. This framework demonstrates that integrating AutoML with XAI yields accurate, interpretable, and robust fatigue strength models for welded steel structures. It bridges data-driven modeling with engineering validation, enabling AI-assisted design and assessment. Future work will explore probabilistic fatigue life modeling and integration into digital twin environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑