Machine Learning‐Assisted Prediction and Analysis of Viscosity and Fusion Characteristics for Coal and Biomass Ash

Abstract

Coal and biomass are important solid fuels, and the viscosity and fusion temperature of their ash have a significant impact on the stable operation of entrained‐flow gasifiers with liquid slag discharge. In this study, separate machine learning (ML) models were developed to predict the viscosity and fusion temperature of coal ash and biomass ash using six regression models: LightGBM, SVR, RF, XGBoost, DNN, and CatBoost. Model performance was evaluated using MAE, RMSE, and R 2 , whereas Bayesian optimization combined with 5‐fold cross‐validation was employed to validate ML models. CatBoost performed best in predicting coal ash fusion temperature and viscosity, with MAE ≤ 25.37°C, R 2  ≥ 0.91 for temperature, and MAE ≤ 0.20, R 2  ≥ 0.97 for viscosity. For biomass ash, LightGBM provided the performance in predicting fusion temperature, achieving an MAE ≤ 18.62°C and R 2  ≥ 0.86. Feature analyzing uncovered that temperature is the dominant factor governing coal ash viscosity. Furthermore, symbolic regression distillation yielded optimal empirical formulas for accurate and efficient prediction of the ash viscosity and temperature. This work provides a practical data‐driven framework for optimizing entrained‐flow gasifier operation and slagging control.