A High-Efficiency and Interpretable Framework for Microparameter Calibration via PSO-Optimized Machine Learning and SHAP Analysis

Key Points

• The framework enhances microparameter calibration efficiency and interpretability, yielding significant results.
• Key findings show a reduction in calibration error by 45% through the PSO optimization method.
• Utilizing PSO-optimized machine learning, the analysis presents robust calibration strategies on synthetic datasets.
• The results suggest a need for further real-world applications to validate and expand on these findings.