Table 3
Validation of surrogate model performance. n-RMSE is the normalised root mean squared error, with normalisation by the mean.
Response | R 2 |
![]() |
RMSE | n-RMSE |
---|---|---|---|---|
Specific energy consumption | 0.9987 | 0.9987 | 0.068 | 0.013 |
Removal rate | 0.9873 | 0.9868 | 1.089 | 0.012 |
Reboiler duty | 0.9997 | 0.9997 | 309.1 | 0.008 |
Cooling duty | 0.9983 | 0.9982 | 713.1 | 0.025 |
Regenerator temperature | 0.9986 | 0.9985 | 0.302 | 0.002 |
Lean loading | 0.9985 | 0.9984 | 0.003 | 0.027 |
Rich loading | 0.9970 | 0.9969 | 0.005 | 0.010 |