A Condition Monitoring Method of Hydraulic Gear Pumps Based on Multilevel Mechanism-Data Fusion

Table 9

Test results of SVC models at different fusion levels.

Fusion level	Metrics	SVC1linear kernel	SVC2polynomial kernel	SVC3Gaussian kernel	SVC4Sigmoid kernel	SVC5Laplacian kernel	SVC6MCMK-SVC
Data level	Accuracy	1.0	0.9375	1.0	1.0	1.0	1.0
	Precision	1.0	0.875	1.0	1.0	1.0	1.0
	Recall	1.0	1.0	1.0	1.0	1.0	1.0
	-score	1.0	0.9333	1.0	1.0	1.0	1.0
Feature level	Accuracy	1.0	0.9375	1.0	0.9375	1.0	1.0
	Precision	1.0	0.875	1.0	1.0	1.0	1.0
	Recall	1.0	1.0	1.0	0.8571	1.0	1.0
	-score	1.0	0.9333	1.0	0.9231	1.0	1.0
Decision level	Accuracy	0.9940	0.9190	0.9190	0.9440	0.9690	0.9690
	Precision	0.9940	0.9273	0.9273	0.9940	0.9940	0.9940
	Recall	0.9940	0.8797	0.8797	0.8797	0.9368	0.9368
	-score	0.9940	0.9017	0.9017	0.9273	0.9632	0.9632