Ni–MH batteries state-of-charge prediction based on immune evolutionary network |
| |
Authors: | Bo Cheng Yanlu Zhou Jiexin Zhang Junping Wang Binggang Cao |
| |
Affiliation: | aSchool of Construction Machinery, Chang’an University, Xi’an, Shaanxi 710064, China;bSchool of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China |
| |
Abstract: | Based on clonal selection theory, an improved immune evolutionary strategy is presented. Compared with conventional evolutionary strategy algorithm (CESA) and immune monoclonal strategy algorithm (IMSA), experimental results show that the proposed algorithm is of high efficiency and can effectively prevent premature convergence. A three-layer feed-forward neural network is presented to predict state-of-charge (SOC) of Ni–MH batteries. Initially, partial least square regression (PLSR) is used to select input variables. Then, five variables, battery terminal voltage, voltage derivative, voltage second derivative, discharge current and battery temperature, are selected as the inputs of NN. In order to overcome the weakness of BP algorithm, the new algorithm is adopted to train weights. Finally, under the state of dynamic power cycle, the predicted SOC and the actual SOC are compared to verify the proposed neural network with acceptable accuracy (5%). |
| |
Keywords: | Immune algorithm Evolutionary strategy Neural network State-of-charge |
本文献已被 ScienceDirect 等数据库收录! |
|