Improved Particle Swarm Optimization-Extreme Learning Machine Modeling Strategies for the Accurate Lithium-ion Battery State of Health Estimation and High-adaptability Remaining Useful Life Prediction

Lithium-ion batteries are complex electrochemical systems, and the degradation of their state-of-health (SOH) is a nonlinear process. Accurate SOH estimation is critical to lithium-ion battery life and safety. We used a data-driven approach to study SOH estimation of lithium-ion batteries. First, we used the singular value decomposition method to extract features from the battery charging history data. Second, the particle swarm (PSO) algorithm was used to optimize the parameter configuration of the group method of data handling (GMDH). Finally, the SOH estimation wa completed using the optimized GMDH. The results show that the proposed PSO-GMDH estimation model maintains an error within 0.89% for estimating its subsequent SOH using historical data of a certain battery, and maintains an error within 0.5% for estimating the SOH of another battery of the same model using historical data of multiple batteries. At the same time, the results also show that the PSO-GMDH estimation model has higher estimation accuracy than the GMDH model without parameter optimization.

mentioning

confidence: 99%

State-of-Health Estimation of Lithium-ion Batteries Based on Singular Value Decomposition and an Improved Group Method of Data Handling

Li,

Bai,

Yan

et al. 2024

“…[23][24][25][26][27] Moreover, the state of power (SOP) and the state of health (SOH) of the battery are also associated with the SOC. [28][29][30][31][32][33][34][35][36][37][38] Therefore, OCV identification is the basis for accurate estimation of SOC, SOP, and SOH.…”

mentioning

confidence: 99%

Identification and Fast Measurement Method of Open-circuit Voltage

Peng

Jin

Zhang

2023

Accurate measurement of the open-circuit voltage (OCV) promotes state of charge (SOC) accuracy. In this study, three transformation methods were employed to make the OCV identifiable, and factors affecting the accuracy of OCV identification were investigated. Furthermore, a fast OCV measurement method was proposed. The results show that the forward difference transformation and the adaptive differential evolution algorithm are more suitable for OCV identification. The accuracy of OCV identification is affected by pulse characteristics, sampling frequency, C-rate, and resting time between pulses. Positive-negative (PN) pulses of equal amplitude are more suitable for OCV identification than hybrid pulse power characteristics. A method for fast OCV measurement was developed based on the relationship between the identification error of the OCV and the number of PN pulses. A total of 57 PN pulses with an amplitude of 2 C are used to realize accurate OCV identification at various charge/discharge states, C-rate, and SOC, with an average error of -0.026% (about 1 mV). The proposed method only needs to obtain the battery voltage and current to achieve a fast measurement of OCV, which also serves as a foundation for an accurate estimation of the battery state.

“…It can be found that the increase of the feature input dimension will lead to a surge in the amount of calculation of the model, resulting in more abnormal noise, and overfitting. Researchers adjust the model through transfer learning, particle swarm optimization (PSO), 23,24 and other methods to improve the performance of the model, while improving the accuracy and robustness of the model. For example, ZHANG et al 24 predicted SOH and RUL on the PSO optimized extreme learning machine (ELM) based on multivariate information during the discharge process as input.…”

mentioning

confidence: 99%

“…Researchers adjust the model through transfer learning, particle swarm optimization (PSO), 23,24 and other methods to improve the performance of the model, while improving the accuracy and robustness of the model. For example, ZHANG et al 24 predicted SOH and RUL on the PSO optimized extreme learning machine (ELM) based on multivariate information during the discharge process as input. The optimized model proposed estimates the SOH and RUL with relatively high accuracy.…”

mentioning

confidence: 99%

Prediction of Battery SOH and RUL Based on Cooperative Characteristics in Voltage-Temperature-Time Dimensions

Tang,

Zhang,

Ning

et al. 2023

In the prognostics health management (PHM) of marine power lithium batteries, the estimation of the state of health (SOH) and the prediction of remaining useful life (RUL) are of great importance to ensure the battery operational safety and efficiency. In this study, an improved multivariate dimensionality-reduction for Bayesian optimized bi-directional long short-term memory (IMD-BiLSTM) algorithm is proposed and applied to realize SOH estimation and RUL prediction of lithium battery. Specifically, based on the discharging data of lithium battery under specific operating conditions, several health indicators are proposed for the work. On this basis, a collaborative dimensionality reduction algorithm based on Pearson correlation and principal component analysis is proposed to further retain feature information and reduce input dimensionality. Then, the prediction model based on BiLSTM is established, in which the hyperparameters are optimized by Bayesian algorithm. Finally, the effectiveness of the proposed IMD-BiLSTM method is verified by experiments based on the NASA PCoE dataset, and the prediction accuracies of SOH and RUL are emphatically analyzed. Numerical simulation results show that the proposed IMD-BiLSTM-method can effectively extract battery health characteristics and achieve dimensionality reduction. In addition, the proposed IMD-BiLSTM-method significantly outperforms the compared state-of-the-art algorithms in SOH/RUL prediction accuracy and robustness.