Steady Modeling for an Ammonia Synthesis Reactor Based on a Novel CDEAS-LS-SVM Model

Table 3

The comparisons of training error and testing error of LS-SVM.

Method	Type of error	RE*	MAE*	MSE*
BP-NN	Training error	𝟗.𝟒𝟒𝟐𝟐×𝟏𝟎^−𝟎𝟒	𝟏.𝟎𝟓𝟒𝟒×𝟏𝟎^−𝟎𝟒	𝟏.𝟑𝟗𝟕𝟎×𝟏𝟎^−𝟎𝟒
	Testing error	0.008085	8.9666×10^−04	0.001188
LS-SVM	Training error	0.002231	2.4785×10^−04	4.1672×10^−04
	Testing error	0.005328	5.9038×10^−04	7.8169×10^−04
DE-LS-SVM	Training error	0.002739	3.04286×10^−04	4.08512×10^−04
	Testing error	0.005252	5.8241×10^−04	7.7032×10^−04
CDEAS-LS-SVM	Training error	0.002830	3.1415×10^−04	3.3131×10^−04
	Testing error	0.004661	𝟓.𝟏𝟕𝟓𝟐×𝟏𝟎^−𝟎𝟒	𝟔.𝟖𝟗𝟓𝟐×𝟏𝟎^−𝟎𝟒

∗RE: relative error; MAE: mean absolute error; MSE: mean square error.