用于预测沥青混凝土劈裂强度的可解释机器学习：SHAP分析的启示
Interpretable machine learning for predicting splitting strength of asphalt concrete: insights from SHAP analysis
浏览论文内容
中文总结 AI 辅助
本研究构建可解释机器学习框架预测沥青混凝土劈裂强度，对比六种模型发现TabPFN性能最优，通过SHAP分析确定关键影响变量及参数范围，并开发集成预测与解释的GUI平台。
中文摘要 AI 辅助
本文提出一种用于预测沥青混凝土劈裂强度（ST）并支持数据驱动混合料设计的可解释机器学习框架。建立了包含296个样本的数据库，选取与沥青性能、骨料级配及纤维特性相关的14个输入变量用于建模。开发并比较了六种机器学习模型，分别为TabPFN、ANN、SVR、RF、XGBoost和LightGBM；采用NSGA-II对其中五种模型进行超参数优化，TabPFN则直接采用默认配置应用。结果显示，所有六种模型均取得令人满意的预测能力，其中TabPFN在测试集上表现最佳，其最低均方根误差（RMSE）为0.28，平均绝对误差（MAE）为0.21，平均绝对百分比误差（MAPE）为18.01%，平均绝对偏差（MAD）为0.14，最高决定系数（R²）为0.88，最高综合得分为0.91。SHAP分析进一步揭示，9个主导变量贡献了总平均贡献的92.0%，其中Ag9.5、FT、Ag4.75、AC和Du的影响最大；此外，量化了改善ST的有利参数范围，如Ag9.5<66.8%、Ag4.75<45.0%、AC<5.4 wt.%、AV<3.6%、Du>134.7 cm。最后，开发了集成预测与基于SHAP解释的GUI平台，以提升所提框架的可访问性和实用性。
英文摘要
This paper presents an interpretable machine-learning framework for predicting the splitting strength (ST) of asphalt concrete and supporting data-driven mixture design. A database consisting of 296 samples was established, and 14 input variables related to asphalt properties, aggregate gradation, and fiber characteristics were selected for modeling. Six machine-learning models, namely TabPFN, ANN, SVR, RF, XGBoost, and LightGBM, were developed and compared. Hyperparameter optimization was performed for five models using NSGA-II, while TabPFN was directly applied with its default configuration. The results show that all six models achieved satisfactory predictive capability, whereas TabPFN delivered the best overall performance on the testing set, with the lowest RMSE of 0.28, MAE of 0.21, MAPE of 18.01%, MAD of 0.14, the highest R^2 of 0.88, and the highest composite score of 0.91. SHAP analysis further revealed that nine dominant variables accounted for 92.0% of the total average contribution, among which Ag9.5, FT, Ag4.75, AC, and Du were the most influential. In addition, favorable parameter ranges for improving ST were quantified, such as Ag9.5 < 66.8%, Ag4.75 < 45.0%, AC < 5.4 wt.%, AV < 3.6%, and Du > 134.7 cm. Finally, a GUI platform integrating prediction and SHAP-based explanation was developed to improve the accessibility and practical applicability of the proposed framework.
