Battery State of Charge Estimation Based on Composite Multiscale Wavelet Transform

Abstract

The traditional battery state of charge (SOC) estimation method, which is based on neural networks, directly uses terminal voltage and terminal current as the input data. Although it is convenient to implement, it produces a large estimation error when the current and voltage change drastically. To solve this problem, a new method, which uses a composite multiscale wavelet transform, is proposed to estimate the battery SOC. In the proposed method, a wavelet transform is applied to the input data, and this process obtains the approximate coefficients and detail coefficients of the input data at different scales. A neural network then uses these coefficients as inputs to estimate the SOC. The experimental results show that the proposed method can improve the accuracy of the battery SOC estimation without changing the neural network structure or algorithm.

Performance Comparison of Long Short-Term Memory and a Temporal Convolutional Network for State of Health Estimation of a Lithium-Ion Battery using Its Charging Characteristics

“…The SOH predictions were performed for the experimental batteries based on the three charging features determined in this study regarding battery SOH. Although the input and output energies of the battery can be calculated by integrating the current against time using the ampere-hour integration method, the integration calculation and the degradation of the static flux caused by the degradation of the battery performance result in a large cumulative error and reduce the calculation accuracy [46][47][48][49]. Because it is difficult to directly measure the battery capacity, the internal resistance method was used to define the SOH of the battery in the experiment [50,51].…”

Application of grey feed forward back propagation-neural network model based on wavelet denoising to predict the residual settlement of goafs

“…The signal of the original monitoring data had to fluctuate noise signal, affecting the real monitoring information and accuracy of derived ground subsidence data. When dealing with such nonlinear signals, wavelet transform can reduce or eliminate random signals, extract system signals, and provide more accurate data support for deformation predictions [ 28 ].…”

Simulation of a non‐linear, time‐variant circuit using the Haar wavelet transform

“…The diversity of the potential uses of the Haar wavelet as an analysis tool of nonlinear, time-variant systems was demonstrated; linear impedance as well as non-linear, time-variant loads were evidently handled. The key step where linear and non-linear, time-variant loads were ultimately combined was in Equation (17), notably before applying the inverse Haar transform. The source current features are depicted in Figures 9 and 11.…”

“…network analysers and oscilloscopes) or education remains yet a slowly progressing aspect. Indicative recent advances are in applications such as digital audio signal processing [16], reactive elements circuit analysis [17], time-variant circuits [18,19], fault detection in linear circuits [20] and promising theoretical analyses such as the work by Ratas et al [21] for solving non-linear boundary values. Finally, a more complete summary of wavelet types and transforms as well as modern concepts and applications can be found in works such as the book by Akujuobi [22].…”