基于K-Means聚类与Ridge回归算法的煤炭发热量预测研究

乔世超, 陈衡, 李博, 潘佩媛, 徐钢

Research on Coal Calorific Value Prediction Based on K-Means Clustering and Ridge Regression Algorithm

Shichao QIAO, Heng CHEN, Bo LI, Peiyuan PAN, Gang XU

表5 K-Means聚类后对应不同煤种的回归模型评价指标

Tab. 5 Model evaluation indicators of regression models corresponding to different coal types after K-Means clustering

煤炭种类	回归方程	δ_MAE	δ_RMSE	R²
全部煤	$Q_{n e t, a r} = 26.569 15 - 0.337 01 M_{a r} - 0.291 46 A_{a r} + 0.103 12 F_{C, a r}$	0.248 45	0.592 63	0.945 63
高固定碳煤	$Q_{n e t, a r} = 28.753 18 - 0.345 87 M_{a r} - 0.315 47 A_{a r} + 0.076 18 F_{C, a r}$	0.172 61	0.236 73	0.967 57
高灰分煤	$Q_{n e t, a r} = 24.843 48 - 0.301 57 M_{a r} - 0.276 01 A_{a r} + 0.125 64 F_{C, a r}$	0.224 37	0.348 47	0.963 36
高水分煤	$Q_{n e t, a r} = 28.329 07 - 0.404 50 M_{a r} - 0.299 58 A_{a r} + 0.089 79 F_{C, a r}$	0.247 84	0.409 61	0.957 69