Wire arc additive manufacturing (WAAM) offers a scalable route for fabricating lightweight structures made by magnesium-rare earth (Mg-RE) alloys. However, intrinsic heat treatment (IHT) caused by thermal cycling poses critical challenges to achieving uniform microstructure and isotropic mechanical performance. Here, we elucidate the in-situ phase transformation behavior of long-period stacking ordered (LPSO) phases in WAAM-deposited Mg-7Gd-3Y-1Zn-0.5Zr (VWZ731K, wt.%) alloy thin wall. By employing multiscale characterization, thermodynamic simulations, and mechanical testing, we correlate thermal cycling history with microstructural evolution across the building direction. Due to prolonged exposure to thermal cycling, the Bottom region of VWZ731K thin wall experiences a reduction in stacking fault energy, which promotes the in-situ phase transformation of eutectic (Mg,Zn)₃(Gd,Y)→18R-LPSO. The presence of blocky 18R-LPSO phases enhances yield strength, however, crack propagation along the LPSO structures leads to a reduction in ductility. In contrast, the Top region predominantly forms needle-like γ′ phases, which, although associated with a lower yield strength compared to the Bottom region, contribute to improved elongation. This study provides mechanistic insights into IHT-driven heterogeneity in microstructure and mechanical property of WAAM-deposited Mg-RE alloys.

In wire arc additive manufacturing (WAAM), a trade-off exists among deposition efficiency, microstructure, and mechanical properties. Addressing this challenge, this work proposes an innovative multi-objective optimization framework tailored for WAAM of AZ31 magnesium alloy components, which integrates deposition efficiency and microstructure as coupled objectives and is resolved through the NSGA-II algorithm. The proposed framework employs quadratic regression to correlate process parameters with deposition efficiency through geometric morphology mediation, while addressing uncertainties in WAAM by integrating theoretical insights with data-driven stacked ensemble learning for grain size prediction, establishing the hybrid physics-informed data method for WAAM microstructure prediction. The optimized process achieved a deposition rate of 6257 mm³/min, with effective width and average layer height maintained at 10.1 mm and 4.13 mm, respectively. Microstructural optimization produced a fine, uniform, fully equiaxed grain structure with an average grain size of 38 μm. These findings underscore the significant industrial potential of intelligent optimization strategies in WAAM for manufacturing lightweight, high-performance components in aerospace and transportation sectors.