RESUMO
The quick estimation and prediction of lithium-ion batteries' (LIBs) state of charge (SoC) are attracting growing attention, since the LIB has become one of the most essential power sources for daily consumer electronics. Most deep learning methods require plenty of data and more than two LIB parameters to train the model for predicting SoC. In this paper, a single-parameter SoC prediction based on deep learning is realized by cleaning the data for lithium-ion battery parameters and constructing the feature matrix based on the cleaned data. Then, by analyzing the feature matrix's periodicity and principal component to obtain two kinds of the original eigenmatrix's substitution matrices, the two substitutions are fused to obtain an excellent prediction effect. In the end, the minimization method is verified with newly measured lithium battery data, and the results show that the MAPE of the SoC prediction reaches 0.96%, the input data are reduced by 93.33%, and the training time is reduced by 96.68%. Fast and accurate prediction of the SoC is achieved by using only a minimum amount of voltage data.
RESUMO
This work explores the polynomial fuzzy stabilization for positive systems. The traditional quadratic Lyapunov function and basic stability analysis may not be favourable for stability investigation due to the absence of the positivity property and membership functions. Therefore, a fuzzy co-positive polynomial Lyapunov-Krasovskii (FCPL) function which considers the positivity is proposed firstly through an imperfect premise matching (IPM) approach. Secondly, the symbol transfer technique which takes into account fuzzy membership knowledge relaxes the stability conditions. The number of symbols is reduced by two constraints: (1) the last and next moments of the membership functions of the FCPL function; (2) membership functions of the fuzzy model and the controller. Finally, the polynomial fuzzy controller with symbols is obtained. Two examples are implemented to verify the proposed methods.