Valve Fault Diagnosis in Internal Combustion Engines Using Acoustic Emission and Artificial Neural Network

Table 2

Confusion matrix of testing data for ANN.

Valve condition	Pressure (bar)	O1	O2	O3	O4	O5	O6	Sensitivity (%)	Valve condition	O1	O2	O3	O4	O5	O6	Sensitivity (%)
O1	1	100	0	0	0	0	0	100	O4	0	3	0	97	0	0	100
	2	100	0	0	0	0	0			0	0	0	100	0	0
	3	100	0	0	0	0	0			0	0	0	100	0	0
	4	100	0	0	0	0	0			0	0	0	100	0	0
	5	100	0	0	0	0	0			0	0	0	100	0	0
	6	100	0	0	0	0	0			0	0	0	100	0	0
O2	1	0	98	1	1	0	0	99	O5	0	0	0	0	88	12	79
	2	0	100	0	0	0	0			0	0	0	0	67	33
	3	0	98	2	0	0	0			0	0	0	0	75	25
	4	0	100	0	0	0	0			0	0	0	0	86	14
	5	0	100	0	0	0	0			0	0	0	0	88	12
	6	0	100	0	0	0	0			0	0	0	0	69	31
O3	1	0	1	99	0	0	0	100	O6	0	0	0	0	7	93	75
	2	0	0	100	0	0	0			0	0	0	0	27	73
	3	0	0	100	0	0	0			0	0	0	0	39	61
	4	0	0	100	0	0	0			0	0	0	0	28	72
	5	0	0	100	0	0	0			0	0	0	0	22	78
	6	0	2	98	0	0	0			0	0	0	0	27	73
Total average performance of ANN: 92%