State-of-Charge Estimation of Lithium-Ion Battery Pack Based on Improved RBF Neural Networks
Algorithm 1
Input selection using FRA algorithm.
Require the maximum voltage vector , the minimum voltage , the average voltage , the average temperature of the battery cells, the circuit current , the maximal order of time lags for inputs , the maximal order of time lags for output , the maximal number of selected terms , and the minimal training error .
Ensure the SOC vector of the battery pack .
(1)
Initialization: form the regression matrix for polynomial term selection.
(2)
for to do
(3)
calculate the recursive matrix , and is recursively calculated by
(4)
calculate the net contribution of the terms using equation (10).
(5)
select the significant term.
(6)
end for
(7)
Input selection: find the order of the time lags from the selected model terms.