HFCM-LSTM: A novel hybrid framework for state-of-health estimation of lithium-ion battery

Gao, Mingyu; Bao, Zhengyi; Zhu, Chunxiang; Jiang, Jiahao; Dong, Zhekang; Song, Yining

doi:10.1016/j.egyr.2023.01.109

Cited by 24 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address the challenges associated with modeling and the limited accuracy of model-based approaches, researchers have increasingly turned to data-driven techniques for battery SOH estimation, which improve the accuracy of SOH estimation by Energies 2024, 17, 2487 2 of 14 analyzing high-throughput data from the battery charging and discharging process and using machine learning and data mining techniques to identify and model the features of the battery's SOH [11,12]. Such methods mainly include Gaussian process regression (GPR) [13][14][15], support vector machine (SVM) [16][17][18], long short-term memory (LSTM) networks [19][20][21], and convolutional neural networks (CNNs) [22][23][24]. However, the reliable acquisition of battery aging features remains a significant research challenge.…”

Section: Introductionmentioning

confidence: 99%

State of Health Estimation for Lithium-Ion Batteries with Deep Learning Approach and Direct Current Internal Resistance

Sun,

He,

Wang

et al. 2024

Energies

View full text Add to dashboard Cite

Battery state of health (SOH), which is a crucial parameter of the battery management system, reflects the rate of performance degradation and the aging level of lithium-ion batteries (LIBs) during operation. However, traditional machine learning models face challenges in accurately diagnosing battery SOH in complex application scenarios. Hence, we developed a deep learning framework for battery SOH estimation without prior knowledge of the degradation in battery capacity. Our framework incorporates a series of deep neural networks (DNNs) that utilize the direct current internal resistance (DCIR) feature to estimate the SOH. The correlation of the DCIR feature with the fade in capacity is quantified as strong under various conditions using Pearson correlation coefficients. We utilize the K-fold cross-validation method to select the hyperparameters in the DNN models and the optimal hyperparameter conditions compared with machine learning models with significant advantages and reliable prediction accuracies. The proposed algorithm is subjected to robustness validation, and the experimental results demonstrate that the model achieves reliable precision, with a mean absolute error (MAE) less than 0.768% and a root mean square error (RMSE) less than 1.185%, even when LIBs are subjected to varying application scenarios. Our study highlights the superiority and reliability of combining DNNs with DCIR features for battery SOH estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

State of Health Estimation for Lithium-Ion Batteries with Deep Learning Approach and Direct Current Internal Resistance

Sun,

He,

Wang

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…9,19-21 Gao et al aiming at the problem that the network construction of the existing state of health (SOH) estimation method is too simple, a new lithium-ion battery SOH evaluation hybrid framework hierarchical feature coupled module long-shortterm memory composed of two cascade modules is proposed. 22 Cai et al combining the characteristics of attention mechanism and domain adaptive neural network, a method for multiple fault detection of series battery packs based on domain adaptive neural network is proposed. 23 Dong et al propose an internal cascaded neuromorphic computing system via memristor circuits for electric vehicle (EV) SOC estimation.…”

Section: Introductionmentioning

confidence: 99%

Research on serial lithium‐ion battery alternating discharge equalization control systems

Zhang,

Sun,

Huang

et al. 2023

Energy Science & Engineering

View full text Add to dashboard Cite

To improve the discharge equalization efficiency of the battery and prevent the occurrence of overdischarge, in this paper, the 18,650 ternary lithium battery is taken as the object of investigation, and an alternating equalization control system for the discharge process of serial cells is proposed. The system implements the alternating discharge of serial cells by switching on and off, using state of charge (SOC) as the equalization variable, and eventually completes the equalization control of the entire battery pack. Discharge simulations were performed in Matlab/Simulink for faulty and normal operating conditions of the battery pack, respectively. The findings indicate that even in the presence of a malfunction, the battery pack can continue to operate continuously for a while; in contrast, under ideal circumstances, the battery pack is capable of maintaining SOC balance throughout the discharge process. Eventually, five batteries are used to construct the experimental platform for the alternating equalization system. The battery pack can still perform selective discharge under fault conditions until the battery pack reaches the discharge cutoff condition. Under normal conditions, the maximum SOC difference of all five batteries can stabilize at about 1%. The experimental results show that the proposed equalization control system can achieve the equalization of battery discharge and prolong the discharge time, and can prevent the occurrence of battery over discharge.

show abstract

“…In electric vehicles, the battery is the primary energy source that functions to run the engine so that the car can move and is a source of electricity for other systems [1], [2]. In contrast to conventional vehicles today, batteries are only used as an energy source for the vehicle's electrical system [3], [4], [5].…”

Section: Introductionmentioning

confidence: 99%

“…Battery capacity cannot be measured directly, so it also requires suitable parameters to be accurate and reliable. Apart from knowing the remaining battery capacity, SOC can be used to prevent the battery from overcharging or over-discharging to extend its service life [25], [1], [26]. Many SOH or SOC estimation methods have been developed.…”

Section: Introductionmentioning

confidence: 99%

Evaluating the Battery Management System's Performance Under Levels of State of Health (SOH) Parameters

Amifia,

Kamali

2023

Journal of Robotics and Control

View full text Add to dashboard Cite

Batteries in electric vehicles are the primary focus battery health care. The Battery Management System (BMS) maintains optimal battery conditions by evaluating the system's Htate of health (SOH). SOH identification can recommend the right time to replace the battery to keep the electric vehicle system working optimally. With suitable title and accuracy, the battery will avoid failure and have a long service life. This research aims to produce estimates and identify SOH parameters so that the performance of the battery management system increases. The central parameter values obtained are R0, Rp, and Cp based on Thevenin battery modeling. Then, to get good initialization and accurate results, the parameter identification is completed using an adaptive algorithm, namely Coulomb Counting and Open Circuit Voltage (OCV). The two algorithms compare the identification results of error, MAE, RSME, and final SOH. The focus of this research is to obtain data on estimation error values along with information regarding reliable BMS performance. The performance of the current estimation algorithm is known by calculating the error, which is presented in the form of root mean square error (RMSE) and mean absolute error (MAE). The SOH estimation results using Coulomb Counting have a better error than OCV, namely 1.770%, with a final SOH value of 17.33%. The Thevenin battery model can model the battery accurately with an error of 0.0451%.

show abstract

HFCM-LSTM: A novel hybrid framework for state-of-health estimation of lithium-ion battery

Cited by 24 publications

References 37 publications

State of Health Estimation for Lithium-Ion Batteries with Deep Learning Approach and Direct Current Internal Resistance

State of Health Estimation for Lithium-Ion Batteries with Deep Learning Approach and Direct Current Internal Resistance

Research on serial lithium‐ion battery alternating discharge equalization control systems

Evaluating the Battery Management System's Performance Under Levels of State of Health (SOH) Parameters

Contact Info

Product

Resources

About