文献类型：期刊文献

英文题名：Physical model-guided machine learning for accelerating laser induced plasma micro-machining process optimization

作者：Zhang, Zhen[1,2];Jia, Mengyu[1,2];Wang, Lifei[3];Yu, Yu[1,2];Yang, Zenan[3];Wang, Jinliang[4];Wang, Yulei[1,2];Wang, Chenchong[5];Lv, Zhiwei[1,2];Xu, Wei[5]

机构：[1]Hebei Univ Technol, Ctr Adv Laser Technol, Sch Elect & Informat Engn, Tianjin 300401, Peoples R China;[2]Hebei Key Lab Adv Laser Technol & Equipment, Tianjin 300401, Peoples R China;[3]Beijing Inst Aeronaut Mat, Sci & Technol Adv High Temp Struct Mat Lab, Beijing 100095, Peoples R China;[4]Guangdong Ocean Univ, Sch Mech & Power Engn, Zhanjiang 524000, Peoples R China;[5]Northeastern Univ, Sch Mat Sci & Engn, State Key Lab Rolling & Automation, Shenyang 110819, Liaoning, Peoples R China

年份：2025

卷号：183

外文期刊名：OPTICS AND LASER TECHNOLOGY

收录：SCI-EXPANDED(收录号：WOS:001402439500001)、、EI(收录号：20250117635832)、Scopus(收录号：2-s2.0-85213863850)、WOS

基金：This work was supported by the National Natural Science Foundation of China (62075056, 61927815) and the Natural Science Foundation of Hebei Province (F2023202082, F2022202035, E2024202066) . The au-thors acknowledge the the support of Guangdong Basic and Applied Basic Research Foundation (Grant No: 2024A1515010726) .

语种：英文

外文关键词：Ultrashort pulse laser micromachining; Machine learning; Physical model; Process optimization

外文摘要：The demands for high precision and high efficiency in industrial manufacturing have driven the development of advanced laser-based manufacturing methods, especially laser-induced plasma micro-machining (LIPMM). Limited by incomplete physical understanding and costly, time-consuming experiments, finding the optimal process parameters across the entire process space presents a significant challenge. Although machine learning has been attempted for laser material processing, the lack of sufficient data remains a significant obstacle. To address this issue, a physical model-guided machine learning framework was developed, wherein intermediate mechanism parameters were generated based on the physical model, e.g. peak plasma density and plasma duration, and these were added to the original dataset vectors as extra dimensions to participate in and guide the model training process. The established framework accurately predicted the machining performance of LIPMM and, in combination with a genetic algorithm (GA), collaboratively optimized the multidimensional process parameters, resulting in a comprehensive improvement in both machining depth and material removal rate (MRR). The introduction of physical information enriched the data available for training, improving the model's prediction accuracy with small sample sizes and enhancing the superiority and rationality of the designed processes by avoiding suboptimal solutions. Additionally, coupling the intermediate information into the deep learning can further improve the prediction accuracy of LIPMM performance. The proposed physical modelguided machine learning provides a new strategy for significantly reducing the cost of process optimization, and can be applied to other complex laser processing processes to accelerate process development.