Multistep Degradation Tendency Prediction for Aircraft Engines Based on CEEMDAN Permutation Entropy and Improved Grey–Markov Model

Table 5

Analysis of forecasting accuracy of eight models.

Models	Forecasting accuracy
	MAE	MAPE (%)	R^2
CEEMDAN-PE-IGMMW	0.047	6.691	0.982
EMD-PE-IGMMW	0.062	8.721	0.978
CEEMDAN-IGMMW	0.076	9.938	0.972
IGMMW	0.089	10.911	0.831
ELM	0.097	13.527	0.723
SVR	0.123	17.277	0.499
ARIMA	0.169	20.965	0.503
BPNN	0.167	21.319	0.474