Online Prediction Method of Molten Aluminium Height in Electrolytic Cell Based on Extreme Learning Machine with Kernel Function

Table 1

Root mean square error value and time consumption of three prediction models.

Algorithm	RMSE	Training time (s)	Forecasting time (s)
K-ELM	0.1199	0.0813	0.0132
BP	0.2397	1.9844	0.0313
LSSVM	0.2656	0.2656	0.0469