A New Support Vector Regression Model for Equipment Health Diagnosis with Small Sample Data Missing and Its Application

Table 9

Prediction effect of missing data of Pump C for three different prediction models.

	Single-variable prediction		Multiple-variable prediction		Dynamic weight combination prediction
	RMSE	MAPE	RMSE	MAPE	RMSE	MAPE (%)
GA-SVR	0.0878	0.85	0.0621	0.59	0.0263	0.26
SVR	0.1439	1.69	0.1219	1.33	0.0498	0.73
BPNN	0.2293	2.12	0.1580	1.83	0.0724	1.20