A Hybrid Prognostic Approach for Remaining Useful Life Prediction of Lithium-Ion Batteries

Table 5

Comparison of the hybrid prognostic approach’s performances using different RVM learning algorithms.

Battery name	Inspection cycle (Ci)	Predicted RUL (Ci)			Actual RUL (Ci)
		SKE	BK	EA
A1	125	83	88	90	84
	146	63	60	67	63
	167	42	43	46	42
	188	20	23	25	21
A2	113	74	81	78	76
	132	58	61	60	57
	151	39	42	44	38
	170	20	23	24	19
A3	79	46	48	57	53
	92	38	36	35	40
	106	24	23	30	26
	119	13	10	16	13
A4	29	16	14	15	19
	34	14	16	12	14
	38	10	12	10	10
	43	5	4	6	5

SKE: the proposed hybrid prognostic approach that integrates selective kernel ensemble-based RVM and exponential regression; BK: another hybrid prognostic approach that integrates the best kernel-based (i.e., the best performing component kernel among all available basic kernels) RVM with exponential regression; BK: the other hybrid prognostic approach that integrates the Ensemble All-based (i.e., combining all of those available basic kernels) RVM with exponential regression.