Fault Diagnosis of Batch Reactor Using Machine Learning Methods

Table 11

Classifier performance comparison based on PCA and SVM.

Classifiers	Bayes net		MLP		RBF
	SVM	PCA	SVM	PCA	SVM	PCA
Correctly classified instance	13 (54%)	12 (50%)	24 (100%)	19 (79%)	24 (100%)	24 (100%)
Incorrectly classified instance	11 (45%)	12 (50%)	0 (0%)	5 (20%)	0	0
Kappa statistics	0.44	0.39	1	0.746	1	1
Mean absolute error	0.15	0.19	0.063	0.15	0.0001	0.0001
Root mean square error (%)	0.29	0.3	0.1074	0.245	0.04	0.006
Relative absolute error (%)	64	81	26	62	0.02	0.03
Root relative squared error (%)	83	86	31	71	0.11	0.31