Abstract
State of charge (SOC) estimations are an important part of lithium-ion battery management systems. Aiming at existing SOC estimation algorithms based on neural networks, the voltage increment is proposed in this paper as a new input feature for estimation of the SOC of lithium-ion batteries. In this method, the port voltage, current and voltage increment are taken as inputs and the current SOC is used as output to train a neural network. Different from the adaptive filtering algorithm, which requires complex equivalent circuit parameter identification, this algorithm uses the voltage increment instead of the open circuit voltage (OCV); hence, the complexity of the SOC estimation algorithm is reduced, and the problem of inaccurate estimation caused by neural network algorithms without considering the internal structure of the battery is avoided. The experimental results show that compared with the traditional neural network algorithm, the neural network SOC estimation algorithm based on the voltage increment could improve the accuracy of SOC estimation.
Highlights
Lithium batteries are one of the hotspots in the research field of energy storage, given their high specific energy and power
Based on the research on state of charge (SOC) estimation algorithms and neural networks, this paper introduces the incremental voltage as an input feature quantity to improve the estimation accuracy of SOC in a neural network algorithm
To measure the improvement of the algorithm obtained by introducing the voltage increment, mean absolute percentage error and relative error are selected for evaluation
Summary
Lithium batteries are one of the hotspots in the research field of energy storage, given their high specific energy and power. Zhao et al.: Estimation of the SOC of Energy-Storage Lithium Batteries Based on the Voltage Increment These methods are very sensitive to the selection of initial values. Machine learning algorithms usually take the lithium-ion battery port voltage, charge and discharge current and temperature as the inputs of the model and the SOC as the output of the model. Chaoui and Ibe-Ekeocha [13] proposed an accurate estimation method for SOC based on the combination of long-short-term memory (LSTM) and a recurrent neural network This method can be used in systems without using any battery model, filter or Kalman filter. To improve the GA-BP algorithm, Guo et al [17] proposed an SOC estimation model based on the fuzzy weighting algorithm and combined a GA-BP neural network with the ampere-hour integration method to achieve more accurate SOC estimation. Where t represents time, and u is the measured voltage across the battery terminals, u
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
