Мақола

Machine-learning-driven optimization of CMT welding for joint–base-metal property equivalence in thin 5052 aluminum alloy sheets

Zhenghao WangSchool of Materials Science and Physics, China University of Mining and Technology, Xuzhou 221116, Jiangsu, ChinaDexin ZhuInstitute for Carbon Neutrality, University of Science and Technology Beijing, Beijing 100083, ChinaZhiyuan ChengSchool of Materials Science and Physics, China University of Mining and Technology, Xuzhou 221116, Jiangsu, ChinaJinyong ZhangChongqing SanHang New Materials Technology Research Institute,Chongqing 401120, ChinaChangjiu ChenSchool of Materials Science and Physics, China University of Mining and Technology, Xuzhou 221116, Jiangsu, ChinaChuan LiuChongqing SanHang New Materials Technology Research Institute,Chongqing 401120, ChinaYu FanSchool of Materials Science and Physics, China University of Mining and Technology, Xuzhou 221116, Jiangsu, ChinaJiangkun FanState Key Laboratory of Solidification Processing, Northwestern Polytechnical University, Xi’an, Shaanxi 710072, ChinaUmida ZiyamukhamedovaDepartment of Material Science and Mechanical Engineering, Tashkent State Transport University, Tashkent 100067, UzbekistanJasurbek NafasovDepartment of Material Science and Mechanical Engineering, Tashkent State Transport University, Tashkent 100067, UzbekistanHonghui WuInstitute for Carbon Neutrality, University of Science and Technology Beijing, Beijing 100083, ChinaFan SunPSL University, Chimie ParisTech, CNRS, Institut de Recherche de Chimie Paris, Paris, France 75005

Review of Materials Researchjournal2026en

ABI

Аннотация

Heat-affected zone (HAZ) softening and corrosion degradation remain major obstacles to achieving property equivalence between welded joints and the base metal (BM) in thin 5052 aluminum alloy sheets. To overcome these limitations, a data-driven optimization strategy for cold metal transfer (CMT) welding was developed by coupling a Random Forest (RF) surrogate model with Bayesian active learning using an Expected Improvement (EI) acquisition function. This ML-guided approach successfully identified a set of optimal low–heat-input parameters. The optimized welded joints achieved tensile strengths exceeding 93% of that of the BM while maintaining comparable ductility and exhibiting nearly identical electrochemical behavior in acidic media. Integrated microstructural and compositional analyses reveal that weld metal grain refinement, spatial confinement of HAZ softening, and reduced compositional gradients collectively enable the simultaneous attainment of mechanical and corrosion property equivalence. This work provides a transferable machine-learning-assisted framework for parameter design and performance enhancement in welded thin aluminum alloy structures.

Ҳали таржима қилинмаган

Мавзулар

Welding Techniques and Residual Stresses Advanced Welding Techniques Analysis Machine Learning in Materials Science

Идентификаторлар

DOI: 10.1016/j.revmat.2026.100198

Иқтибослар ва манбалар

0 та иқтибос33 та фойдаланилган манба

Кўрсаткичлар — AkademScholar