Mathematical Problems in Engineering / 2013 / Article / Tab 9

Research Article

Simultaneous-Fault Diagnosis of Automotive Engine Ignition Systems Using Prior Domain Knowledge and Relevance Vector Machine

Table 9

Simultaneous fault diagnosis under -measure with classifiers trained with single faults (with DK + WPT + PCA and = 0.7147).

Test dataset
(simultaneous faults only)
Classification techniqueFault 2Fault 3Fault 5Fault 6Fault 7Fault 8Fault 9Fault 10

Faults (2, 6)PNN0.69170.6848
RVM0.71280.7067
PCRVM0.74350.7392
Faults (5, 7)PNN0.73210.7054
RVM0.75220.7214
PCRVM0.79260.7557
Faults (3, 10)PNN0.80030.4854
RVM0.79430.6159
PCRVM0.78440.6995
Faults (2, 5, 9)PNN0.74340.74570.6809
RVM0.71230.73590.7256
PCRVM0.78470.78580.7704
Faults (3, 8, 10)PNN0.68420.71180.6803
RVM0.67240.73190.6931
PCRVM0.73490.78280.6993

—: Indicates that the probability is lower than and hence ignored.