高电压技术2026，Vol.52Issue(7)：3064-3074,11.DOI:10.13336/j.1003-6520.hve.20251164
电弧增材制造中融合物理约束的小样本多层成型缺陷识别方法
Physics-constrained Small-sample Defect Recognition Method for Multi-layer Fabrication in Wire Arc Additive Manufacturing
摘要
Abstract
Wire arc additive manufacturing(WAAM)has become a key technology in the fabrication of electrical equipment due to its high deposition rate and excellent material utilization efficiency.However,this process is inherently influenced by coupled multi-physical fields,making it prone to the formation of structural defects during multilayer depo-sition,which can significantly compromise the forming quality and structural reliability.To address the challenges of defect recognition in multilayer deposition,including the scarcity of labeled samples,the high dimensionality of spectral inputs,and the limited physical interpretability of existing models,this paper proposes a spectral information-driven opti-mization method that integrates physical spectral mechanisms with machine learning strategies to tackle high-dimensional defect recognition under small-sample constraints.First,key spectral regions of interest(ROI)associated with metal evaporation and gas excitation processes are identified based on elemental radiation mechanisms and empirical knowledge,enabling initial feature compression.Subsequently,a physically-constrained genetic optimization framework is constructed,where spectral feature selection and model parameter tuning are jointly encoded.A fitness function incor-porating spectral retention ratio is further designed to guide each individual in the population toward a solution that balances classification performance with physical consistency.Finally,a lightweight extreme gradient boosting(XGBoost)classifier is employed for model training and prediction,ensuring both robustness and deployment efficiency.Experi-mental results demonstrate that the proposed method achieves an accuracy of 93.21％in recognizing multi-layer defects under limited sample conditions,exhibiting notable advantages over comparative methods in terms of accuracy,stability,and interpretability.关键词
电弧光谱/物理先验/遗传算法/电弧增材制造/XGBoost分类器/小样本缺陷Key words
arc spectrum/physical prior/genetic algorithm/wire arc additive manufacturing/XGBoost classifier/small-sample defect引用本文复制引用
陈琳,杨飞,李海晨,刁兆炜,吴翊,荣命哲..电弧增材制造中融合物理约束的小样本多层成型缺陷识别方法[J].高电压技术,2026,52(7):3064-3074,11.基金项目
国家自然科学基金(U22B20121) （U22B20121）
国家重点研发计划(2022YFB2403600) （2022YFB2403600）
陕西省"三秦学者"创新团队项目(西安交通大学先进直流电力装备关键技术及其产业化示范创新团队)(编号略).Project supported by National Natural Science Foundation of China(U22B20121),National Key R&D Program of China(2022YFB2403600),Shaanxi Province"Sanqin Scholars"Innovation Team Project(Demonstration Innovation Team of XJTU for the Key Technology of Advanced DC Power Equipment and Its In-dustrialization). （西安交通大学先进直流电力装备关键技术及其产业化示范创新团队）
