.png){kind=icon}
.png){kind=icon}
Return
A hybrid prediction model for blast furnace gas generation under diverse operating conditions via multi-feature fusion clustering
.png){kind=icon}
PRE
AI
Y
W
DOI：10.1016/j.apenergy.2026.128667.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Multi-feature fusion K-medoids clustering for BFG prediction under special conditions. • MF-KMD integrates morphology, mechanism, and depth distances for meaningful clusters. • Hybrid MFC-HPM framework corrects predictions using prior knowledge from typical curves. • Model-agnostic framework enhances XGBoost, LSTM, TCN, and Patch TST models. • Real-world validation shows up to 85.99% MAPE reduction under special conditions.
Journal
IF:
11
Papers:
2.6W
Citations:
17.8W
Organization
Cited Papers