Physics-Guided Machine Learning for Performance Prediction and Multi-Objective Optimization of High-Conductivity Aluminum Conductors

Producing high-conductivity aluminum conductors for power transmission involves 23 trace elements and multiple interconnected thermo-mechanical stages. The ultra-low alloying levels required to preserve high electrical conductivity create a narrow compositional window and highly imbalanced distributions, which hinder traditional data-driven learning. Here, we developed a physics-guided machine-learning framework based on 4458 valid industrial production records to predict tensile strength and electrical resistivity. In addition to raw composition and process parameters, we introduce ratio descriptors (e.g., Fe/Si and Al/Si) and propose a physics-informed metric termed the Equivalent Solute–Heat Index (ESHI) to couple key solute chemistry (Si, Fe, B) with normalized thermal-history intensity. Fe and Si primarily influence resistivity through impurity/solute scattering, while B mainly affects microstructural uniformity via grain refinement. Incorporating ESHI as an augmented signal into the best-performing XGB surrogate markedly improves generalizability, increasing the tensile strength R2 from 0.75 to ~0.92. SHAP analysis reveals that ESHI dominates the decision logic by modulating both targets with metallurgically interpretable mechanisms: solute-controlled scattering and thermal history-traced second-phase evolution that stabilizes the microstructure. NSGA-III was further employed to map the Pareto front and identify composition–process combinations that optimize the strength–conductivity trade-off, enabling improved mechanical reliability while minimizing resistive losses in practical power-transmission applications. Experimental validation on industrial wires confirms this reliability.