Improved Particle Filter Using Clustering Similarity of the State Trajectory with Application to Nonlinear Estimation: Theory, Modeling, and Applications

Table 6

Comparison of RUL prediction results based on four nonlinear algorithms running 100 times.

Comparison items	SIR	APF	CSPF
			ECSPF	CCSPF
Mean	113	115	123	122
Variance	156.3	476.6	5.9	6.2
Error	15.0%	13.5%	7.5%	8.3%
RMSE	23.5%	26.8%	10.6%	11.1%

Note: SIR = sequential importance resampling; APF = auxiliary particle filter; ECSPF = Euclidean distance clustering similarity particle filter; CCSPF = Chebyshev distance clustering similarity particle filter; RMSE = root mean squared error.