Aeroengine Fault Diagnosis Using Optimized Elman Neural Network

Table 6

Average mean accuracy of 6 methods with different numbers of training samples.

Samples	Average mean accuracy/%
	QAPSO-ENN	BP	ENN	IPSO-ENN	PSO-ENN	SVM
1600	95.02	84.41	87.61	93.74	93.21	90.00
1200	94.26	85.39	87.35	93.43	92.47	89.75
800	94.63	86.40	87.42	93.44	91.71	90.00
400	92.72	83.93	85.79	92.10	91.03	90.25