Table 5.

Performance matrix of the used models in the fault diagnosis task.

Model	Fault Class	Accuracy	Precision	Recall	Sensitivity	Specificity	F1
LR	HCV_L	0.981	0.731	0.828	0.828	0.987	0.776
	HR_NW	0.995	0.932	0.971	0.971	0.996	0.951
	CCV_S	0.997	0.888	0.972	0.972	0.997	0.928
	FPES_M	0.999	0.996	1	1	0.999	0.998
	CCV_C	0.985	0.791	0.748	0.748	0.993	0.769
	Normal	0.883	0.954	0.889	0.889	0.861	0.920
	Weighted	0.859	0.943	0.900	0.900	0.893	0.887
RF	HCV_L	0.997	0.955	0.988	0.988	0.988	0.971
	HR_NW	0.999	0.997	0.997	0.997	0.999	0.997
	CCV_S	0.999	0.960	0.986	0.986	0.999	0.973
	FPES_M	0.999	0.996	1	1	0.999	0.998
	CCV_C	0.999	0.999	0.989	0.989	0.999	0.993
	Normal	0.995	0.996	0.994	0.994	0.998	0.997
	Weighted	0.993	0.996	0.994	0.994	0.998	0.994
XGB	HCV_L	0.998	0.974	0.982	0.982	0.998	0.978
	HR_NW	0.999	0.997	0.997	0.997	0.999	0.997
	CCV_S	0.999	0.973	1	1	0.999	0.986
	FPES_M	0.999	0.996	1	1	0.999	0.998
	CCV_C	1	1	1	1	1	1
	Normal	0.997	0.998	0.997	0.997	0.996	0.998
	Weighted	0.996	0.997	0.997	0.997	0.997	0.997

LR—logistic regression; RF—random forest; XGB—XGBoost.