Demystifying hardgrove grindability index prediction using interpretable machine learning models

doi:10.1016/j.fuel.2026.139297

Demystifying hardgrove grindability index prediction using interpretable machine learning models

2026-03-28

0

PRE

AI

DOI：10.1016/j.fuel.2026.139297

Original

Original request for help

Save

Abstract

En 中文

• An interpretable ML framework is proposed for coal HGI prediction. • TabPFN outperforms RFR, GBRT, SVR, and XGB across two large datasets. • XAI (SHAP, ALE, ICE) reveals nonlinear effects of coal quality parameters. • Volatile matter shows an inverted-U relation; Rmax shows a U-shaped effect on HGI. • Framework combines high accuracy with clear explanation of key predictors.

Keywords:

HGI prediction

interpretable machine learning

TabPFN

SHAP

coal quality parameters

Demystifying hardgrove grindability index prediction using interpretable machine learning models

Abstract

Journal

Organization