文献类型：期刊文献

英文题名：A monitoring framework for predicting laser directed energy deposition property

作者：Shen, Tao[1,2];Li, Bo[1,2];Ren, Facai[3];Fan, Enxiang[4];Zhang, Jianrui[1,2]

机构：[1]East China Univ Sci & Technol, Sch Mech & Power Engn, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Addit Mfg & Intelligent Equipment Res Inst, Shanghai 200237, Peoples R China;[3]Shanghai Inst Special Equipment Inspect & Tech Res, Shanghai 200062, Peoples R China;[4]Shanghai Elect Grp Co Ltd, Cent Academe, Shanghai 200070, Peoples R China

年份：2025

卷号：307

外文期刊名：INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES

收录：;EI(收录号：20254019257133);WOS:【SCI-EXPANDED(收录号:WOS:001586166300003)】；

基金：This work is sponsored by National Key R & D Program of China (Grant No. 2022YFB4602102) , Shanghai Explorer Program (Grant No. 24TS1411800) , AECC Industry-University-Research Cooperation Project (Grant No. HFZL2023CXY024) , and Research Project of Shanghai Municipal Administration for Market Regulation (No. 2023-46) .

语种：英文

外文关键词：Additive manufacturing; Machine learning; Process monitoring; Laser directed energy deposition; Multi-source information fusion; Tensile performance prediction

摘要：In Laser directed energy deposition (LDED) additive manufacturing, challenges such as porosity, surface defects, cracks, and the complex relationship between melt pool dynamics and mechanical properties still impede consistent quality control. Traditional monitoring and prediction remain fragmented and signal-specific, limiting early defect discovery and degrading reliability in safety-critical parts. To tackle these limitations, this study introduces a novel data-driven framework integrating multi-level feature fusion and dual-task learning, which significantly improves LDED process monitoring and prediction. This work proposes ResCIFNN, a ResNet-based framework that couples unsupervised, defect-aware clustering with supervised regression under a sliding timewindow, enabling defect-informed prediction of tensile behavior. Utilizing melt pool infrared images, simulation data, and quantitative features, ResCIFNN achieves a precise mapping of melt pool dynamics to mechanical properties. Five-fold validation shows robust clustering (Silhouette = 0.7588; DBI = 0.3480). For tensile property prediction, ResCIFNN delivers an RMSE of 0.1113 and R2 of 0.9875, surpassing ResNet18 (RMSE = 0.2821, R2 = 0.9207) by reducing RMSE by 60.5 % and improving R2 by 0.0668. Robustness tests under noise/occlusion yield RMSE <= 0.2011; Grad-CAM highlights high-temperature cores and edges, reinforcing interpretability. This pioneering approach not only elevates defect classification and mechanical property prediction but also provides a scalable, interpretable solution for quality assurance, with broad potential for additive manufacturing.