2025-09-26
【學術亮點】利用遷移學習和混合人工智慧增強瀝青混合料設計
字體大小
小
中
大
Intelligent Cultivation: Crop digital twin for growth adversity index and disaster damage assessment【Department of Civil Engineering / Ming-Der Yang / Tenured Distinguished Professor】
智慧栽培：數位分身作物生長逆境指標與災損監測【土木工程學系楊明德終身特聘教授】
上架日期2025-09-02
智慧栽培：數位分身作物生長逆境指標與災損監測【土木工程學系楊明德終身特聘教授】
| 論文篇名 | 英文：Enhancing asphalt mix design with transfer learning and hybrid artificial intelligence 中文：利用遷移學習和混合人工智慧增強瀝青混合料設計 |
| 期刊名稱 | Case Studies in Construction Materials |
| 發表年份, 卷數, 起迄頁數 | 2025, 23, no. e05258 |
| 作者 | Yang, Ming-Der (楊明德); Yared Bitew Kebede*; Henok Desalegn Shikur |
| DOI | 10.1016/j.cscm.2025.e05258 |
| 中文摘要 | 熱拌瀝青混合料中的瀝青含量 (AC) 是影響路面耐久性和性能的關鍵因素。傳統的測定方法勞力密集、成本高昂，且容易出現人為錯誤，限制了其可擴展性。人工智慧 (AI) 和機器學習 (ML) 提供了有效的替代方案，可以提高準確性並減少人工投入，但它們通常需要大量的訓練資料集。本研究透過提出混合遷移學習模型 (RF-DNN-T) 來應對這項挑戰，該模型利用基於文獻的 848 種混合料設計的綜合資料集進行預訓練，然後僅使用 96 個目標特定樣本進行微調。該框架將隨機森林 (RF) 的特徵選擇功能與深度神經網路 (DNN) 的非線性模式識別優勢相結合，以提高預測效率和可靠性。透過遷移來自多個實驗室的知識，該模型在保持高精度的同時最大限度地減少了實驗工作量。 RF-DNN-T 模型與使用 SHapley 加性解釋 (SHAP) 進行可解釋性測試的傳統機器學習方法進行了比較。結果表明，該模型實現了最低的測試誤差（MAE = 0.08，MSE = 0.02，MAPE = 1.61）和最高的R²（0.97），表明其具有出色的準確性、泛化能力以及預測與實驗數據之間的高度相關性。 SHAP分析確定空隙是影響最大的特徵，對預測影響的貢獻率為32%。這項研究表明，RF-DNN-T模型能夠以最少的實驗室數據準確預測AC，從而顯著減少實驗工作量，同時保持瀝青混合料設計的精確度。 |
| 英文摘要 | Asphalt content (AC) in hot mix asphalt is a critical factor influencing pavement durability and performance. Traditional determination methods are labor-intensive, costly, and prone to human error, limiting scalability. Artificial intelligence (AI) and machine learning (ML) offer efficient alternatives that improve accuracy and reduce manual effort, but they typically require large training datasets. This study addresses that challenge by proposing a hybrid transfer learning model (RF-DNN-T) that leverages a comprehensive literature-based dataset of 848 mix designs for pre-training, followed by fine-tuning with only 96 target-specific samples. The framework combines the feature-selection capabilities of Random Forest (RF) with the nonlinear pattern recognition strength of Deep Neural Networks (DNN) to enhance predictive efficiency and reliability. By transferring knowledge from multiple laboratories, the model minimizes experimental effort while maintaining high accuracy. The RF-DNN-T model is benchmarked against conventional ML approaches using SHapley Additive exPlanations (SHAP) for interpretability. Results show the model achieves the lowest testing errors (MAE = 0.08, MSE = 0.02, MAPE = 1.61) and the highest R² (0.97), indicating excellent accuracy, generalization, and a strong correlation between predictions and experimental data. SHAP analysis identifies voids as the most influential feature, contributing 32 % to prediction impact. This work demonstrates that the RF-DNN-T model can accurately predict AC with minimal laboratory data, significantly reducing experimental workload while preserving precision in asphalt mix design. |
| 發表成果與AI計畫研究主題相關性 | 目前發展的AI 模式以道路鋪面為溫度預測對象，可以應用在農地土壤分層溫度之預測。 |
