Battery State Of Health Research Articles

Online fusion estimation method for state of charge and state of health in lithium battery storage systems

To ensure the safe and reliable operation of Li-ion battery energy storage systems, it is important to diagnose the operational status and aging degree of the batteries. In this study, an online fusion estimation method based on back propagation neural network and genetic algorithm (BP-GA) is used for estimating the state of charge (SoC) and state of health (SoH) of Li-ion batteries. First, the effective features of SoC and SoH of Li-ion batteries during charging and discharging are analyzed, and the relevant features are extracted. Subsequently, a conventional back propagation neural network (BPNN) for SoC and SoH estimation is described. The extracted feature quantities are then used as inputs to the neural network for the estimation of the SoC and SoH of Li-ion batteries. A comparison of the SoC and SoH estimation results using, respectively, a single BPNN and a fusion algorithm using a genetic algorithm (GA) to optimize the BPNN shows that the accuracy and efficiency of the estimation results using BP-GA are significantly higher than that of the BPNN. The experimental component of this paper is a comparison experiment using the Panasonic 18650PF and the real-world data from NASA. The results show that the feature extraction operation is relatively easy to perform and combined with the neural network method used in this paper can have good accuracy, reduce the complexity of the algorithm, and improve the detection efficiency.

Health Status Prediction of Lithium Battery Based on LSTM Model with Optimization Algorithms

Consider the current status of health (SOH) of lithium batteries, which presents challenging existing issues of accurately predicting and calculating. In this paper, an LSTM model and multi-optimization algorithm were used to estimate the battery health state. Taking advantage of the fast convergence speed and wide global optimization range of the optimization algorithm, optimized the number of layers and neurons in the LSTM model so the LSTM model was established, used to predict the health status of lithium batteries, and compared with the LSTM model prediction method without optimization. The results showed that the error of the battery health prediction model based on the proposed prediction model was less than 3%, the prediction accuracy was higher than the LSTM model without optimization, and the model had better accuracy and stability.

Performance simulation method and state of health estimation for lithium-ion batteries based on aging-effect coupling model

Accurate simulation of characteristics performance and state of health (SOH) estimation for lithium-ion batteries are critical for battery management systems (BMS) in electric vehicles. Battery simplified electrochemical model (SEM) can achieve accurate estimation of battery terminal voltage with less computing resources. To ensure the applicability of life-cycle usage, degradation physics need to be involved in SEM models. This work conducts deep analysis on battery degradation physics and develops an aging-effect coupling model based on an existing improved single particle (ISP) model. Firstly, three mechanisms of solid electrolyte interface (SEI) film growth throughout life cycle are analyzed, and an SEI film growth model of lithium-ion battery is built coupled with the ISP model. Then, a series of identification conditions for individual cells are designed to non-destructively determine model parameters. Finally, battery aging experiment is designed to validate the battery performance simulation method and SOH estimation method. The validation results under different aging rates indicate that this method can accurately estimate characteristics performance and SOH for lithium-ion batteries during the whole life cycle.

Feature–target pairing in machine learning for battery health diagnosis and prognosis: A critical review

AbstractLithium‐ion batteries (LIBs) have been dominating the markets of electric vehicles and grid energy storage. Accurate monitoring of battery health status has been one of the most critical challenges of the battery industry. Machine learning (ML) has been widely applied to battery health estimation as well as prediction. Here, by investigating the specific features and targets, we comprehensively discuss task‐oriented ML implementation in various application scenarios in the field of battery health. This review explores the tasks assisted by ML based on multi‐level cell degradation. We highlight opportunities and significance of considering the potential feature–target pair during the ML model training to identify more health information about LIBs as well as shed light into designing tasks for new application scenarios.image

State of health estimation method for lithium-ion batteries using incremental capacity and long short-term memory network

Knowing the battery state of health (SOH) is essential to ensure safety and reliability in the operation of electric vehicles (EVs). However, it is still difficult to accurately estimate the SOH values of batteries owing to the complexity of their aging mechanisms. In this context, an SOH estimation method using incremental capacity (IC) and long short-term memory (LSTM) network was investigated in this study. We proposed an improved IC curve acquisition method based on reference voltage, which can retain the important features of the IC curve and reduce computational efforts. Based on the correlation between the incremental capacity and SOH of the battery, health feature variables were extracted from the IC curves. Moreover, considering the time-series characteristics and long-term dependency of battery degradation, we adopted the LSTM network to develop the SOH estimation model. The accuracy and reliability of the proposed model were verified. The results showed that the proposed IC curve acquisition method reduced the calculation time by 11.49 % compared to that using the Gaussian filter. Compared with the estimation results obtained using the support vector machine (SVM) and artificial neural network (ANN), the estimation results of the proposed IC curve acquisition method combined with the LSTM network had the minimum mean absolute percentage error (MAPE). The MAPE of the estimation results was <2 % for all the different battery samples.

State of health and remaining useful life prediction of lithium-ion batteries based on a disturbance-free incremental capacity and differential voltage analysis method

State of health (SOH) and remaining useful life (RUL) prediction are crucial for battery management systems (BMS). However, accurate SOH and RUL prediction still need to be improved due to the complicated battery aging mechanism. This work combines incremental capacity analysis (ICA) and differential voltage analysis (DVA) based on the second-order RC model with an improved Bidirectional Gated Recurrent Unit (BiGRU) to develop SOH and RUL prediction framework. Firstly, the voltage is reconstructed through the second-order RC model to obtain the incremental capacity (IC) and differential voltage (DV) curves to avoid the influence of measurement noise and the complex parameter adjustment process in the filtering method on the IC and DV curves. Then, a new set of battery aging features are extracted from the reshaped IC and DV curves to improve SOH and RUL prediction accuracy and robustness. Next, the BiGRU method with attention mechanism (BiGRU-AM) is used to build the prediction models for battery aging features, SOH, and RUL. To reduce the impact of the capacity regeneration phenomenon, the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method is used to decompose the SOH prediction results, and the decomposed residual is used as the input to improve the prediction accuracy of RUL. The uncertainty of RUL prediction results is analyzed by Monte Carlo (MC) simulation. Finally, the proposed method is verified by experimental battery data from Center for Advanced Life Cycle Engineering (CALCE) and Sandia National Laboratory. Experimental results show that the voltage reconstruction results based on the second-order RC model are applied to ICA and DVA analysis, effectively avoiding the influence of noise. The RMSE of voltage reconstruction is within 0.0006, and the Pearson correlation coefficient between the four aging features extracted from the reconstructed IC/DV curve and SOH is above 0.9. Moreover, this method has good robustness to the cell inconsistency, temperature uncertainty, and a satisfied generalization ability to different battery chemistries, which the maximum RUL predicted AE of CALCE and Sandia battery is within 10 and 5, respectively.

Active acoustic emission sensing for fast co-estimation of state of charge and state of health of the lithium-ion battery

With the rapid development of clean energy technologies, the lithium-ion batteries have emerged as dominant power source. It is of great significance to monitor the state of charge (SOC) and state of health (SOH) accurately and efficiently for ensuing high safety and reliability. This paper proposes an active acoustic emission (AE) sensing technology and demonstrates the feasibility for co-estimation of SOC and SOH of the lithium-ion battery. The proposed method aims to achieve a fast monitoring of SOC and SOH by putting insights into the variation of material properties during operations. In the method, the appropriate power ultrasound is used to excite the battery and trigger elastic waves. A wide AE transducer can actively capture the released AE events of the battery material with different properties in a wide range of frequency band. Therefore, this allows the battery SOC/SOH to be fast characterised during charging, discharging, and ageing. Experimental studies have found that calculated RMS of AE signals in the frequency band 270–300 kHz, around the 7th harmonic of ultrasonic excitation, can successfully achieve the joint estimation of battery SOC and SOH at any operating phases. This new finding can be designed as a standalone method for fast SOC/SOH estimation.

A novel state of health estimation approach based on polynomial model for lithium-ion batteries

Energy management systems are one of the most critical components in a battery unit's safe and efficient operation. Many measurable or calculable parameters, such as voltage, current, capacity, and internal resistance, are considered when designing energy management systems. Parameters that cannot be measured or are costly to measure, such as battery state of charge (SOC) or battery health state (SOH), can be determined by estimation. SOH, which can be used as both an input and an output parameter for EMS, is an essential parameter for the long-life and high-efficiency use of the battery. Two different approaches, experimental-based and model-based, are used for SOH estimation. Experimental-based methods need all the real-time data of the batteries, which is caused the requirement of a very long time and data storage. The adaptive filtering technique, which is a model-based technique, requires a complete and accurate model of the battery. The nonlinear electrochemical structures of batteries make modeling difficult. On the other hand, optimization-based methods, a data-driven technique, need very high processing power to find the optimal result. In addition, separate data is needed for training and testing in machine learning-based methods and requires high processing power. Contrary to these disadvantages, high-accuracy predictions can be made using low processing power and very little data in the experimental curve fitting technique. In this study, experimental and curve-fitting-based SOH estimation is proposed by using polynomial-based system identification techniques. Polynomial-based identification methods can model the system with high accuracy, low cost, and low processing power. Battery degradation dataset belonging to Oxford University is used. In the aforementioned dataset, the general model inference is made using only %1 of the entire cycle life of the battery. Obtained proposed model's results were compared with different methods in the literature in terms of RMSE, and its superiority was demonstrated.

Accurate Prediction Approach of SOH for Lithium-Ion Batteries Based on LSTM Method

The deterioration of the health state of lithium-ion batteries will lead to the degradation of the battery performance, the reduction of the maximum available capacity, the continuous shortening of the service life, the reduction of the driving range of electric vehicles, and even the occurrence of safety accidents in electric vehicles driving. To solve the problem that the traditional battery management system is difficult to accurately manage and predict its health condition, this paper proposes the mechanism and influencing factors of battery degradation. The battery capacity is selected as the characterization of the state of health (SOH), and the long short-term memory (LSTM) model of battery capacity is constructed. The intrinsic pattern of capacity degradation is detected and extracted from the perspective of time series. Experimental results from NASA and CALCE battery life datasets show that the prediction approach based on the LSTM model can accurately predict the available capacity and the remaining useful life (RUL) of the lithium-ion battery.

State of health estimation of lithium-ion batteries based on remaining area capacity

Accurate state of health (SOH) estimation can ensure the safe and reliable operation of the battery and prolong its service life. A new SOH evaluation method including the concepts of characteristic probability (CP) and remaining area capacity (RAC) are introduced in the framework of probability density function (PDF). Battery SOH evaluation models are respectively established for the lithium-iron phosphate (LFP) battery module and nickel-cobalt-aluminium (NCA) cell based on laboratory data at 1/3C-rate and 1C-rate at the sampling frequency of 1 min, and the effects of different CP values on the RAC - SOH models are investigated. The results show that there is a strong linear positive correlation between RAC and SOH whether charge and discharge conditions, while the model with the maximum PDF peak height as health factor is not ideal to assess battery SOH during discharging. The smaller the CP value, the better the effect of the RAC - SOH model. The R2 values of RAC - SOH models of NCA cell and LFP battery module are up to 0.99 at appropriate characteristic probability. The RMSE between the real and the estimated value of NASA battery SOH is not >1.2 % based on the RAC - SOH model. The improved PDF method has accurate and robust performance for the SOH estimation of different batteries.

Battery management solutions for li-ion batteries based on artificial intelligence

The automobile industry is currently undergoing a paradigm change from conventional, diesel, and gasoline-powered vehicles to hybrid and electric vehicles of the second generation. Lithium-ion (Li-ion) batteries have sparked the automotive industry’s interest for quite some time. One of the most crucial components of an electric car is the battery management system (BMS). Since the battery pack is an electric vehicle's most significant and expensive component, it must be carefully monitored and controlled. The precise measurement and calculation of the many states of a Li-ion battery's cells, such as the State of Health (SOH) and State of Charge (SOC) is a difficult procedure as they cannot be monitored directly. This paper examines various methodologies and approaches for estimating the SOC and SOH of Li-ion batteries using Artificial Intelligent methods. Six machine learning algorithms are intensively utilized to investigate the Li-ion battery state estimation. The employed methods are linear, random forest, gradient boost, light gradient boosting (light-GBM), extreme gradient boosting (XGB), and support vector machine (SVM) regressors. In comparison to all other models employed in this study, the discharge prediction made using random forest exhibits significantly greater performance at a low loss of accuracy. For instance, with the highest R2-score of 0.999, the random forest regressor achieves only 0.0035, 0.0013, and 0.0097 for mean and median absolute error, and root means squared error (RMSE), respectively. We showed that the state estimation of Li-ion batteries can be precisely predicted using AI methods, which can be combined with a battery management system to improve electric vehicle performance.

Lithium-ion battery health assessment method based on belief rule base with interpretability

Health assessment is important for the safe and reliable operation of lithium-ion battery. However, there exist two typical issues in existing health assessment models for lithium-ion battery: uncertainty of the chemical reaction inside the battery and lack of interpretability of the evaluation results. The belief rule base (BRB) is a rule-based modelling approach and can deal with uncertain information in health state assessment. However, the interpretability of the lithium-ion battery health state assessment model based on BRB needs to be preserved effectively. Thus, a new lithium-ion battery health state assessment model based on belief rule base with interpretability (BRB-I) is proposed in this paper. In the BRB-I model, both structural interpretability and optimization interpretability are constructed through the mechanism analysis of lithium-ion batteries. Moreover, a new interpretability evaluation criterion is defined as the objective function to achieve a balanced optimization between interpretability and accuracy. In addition, an improved optimization method based on the whale optimization algorithm (WOA) is proposed to enhance the interpretability of the model and the optimization process. A case study on the health state assessment of B0006 lithium-ion battery is conducted to illustrate the effectiveness of the proposed method.

State of Health Estimation Methods for Lithium-Ion Batteries

Contemporary lithium-ion batteries (LIBs) are one of the main components of energy storage systems that need effective management to extend service life and increase reliability and safety. Their characteristics depend highly on internal and external conditions (ageing, temperature, and chemistry). Currently, the state of batteries is determined using two parameters: the state of charge (SOC) and the state of health (SOH). Applying these two parameters makes it possible to calculate the expected battery life and a battery’s performance. There are many methods for estimating the SOH of batteries, including experimental, model-based, and machine learning methods. By comparing model-based estimations with experimental techniques, it can be concluded that the use of experimental methods is not applicable for commercial cases. The electrochemical model-based SOH estimation method clearly explains processes in the battery with the help of multidifferential equations. The machine learning method is based on creating a program trained to predict the battery’s state of health with the help of past ageing data. In this review paper, we analyze the research available in the literature in this direction. It is found that all methods used to assess the SOH of an LIB play an essential role, and each method has its pros and cons.

A Hybrid Battery Equivalent Circuit Model, Deep Learning, and Transfer Learning for Battery State Monitoring

The accurate estimation of state of health (SOH) for lithium-ion batteries is significant to improve the reliability and safety of batteries in operation. However, many existing studies on battery SOH estimation are conducted on the premise of large sizable labeled training data acquisition without considering the time cost and experimental cost. To solve such issues, this article proposes a novel capacity prediction method for SOH estimation based on the battery equivalent circuit model (ECM), deep learning, and transfer learning. First, an actual charge–discharge experiment is carried out, and a simulation of the corresponding cycling process is conducted for virtual data acquisition using the battery equivalent model. Second, a convolutional neural network (CNN)-based feature extraction network is selected by conducting a performance comparison. Then, a capacity estimation model consisting of a feature extraction network, regressor, and feature alignment metric calculation modules is generated. Several transfer learning methods are chosen for feature alignment metric calculation. Finally, a capacity estimation performance comparison is done for the final selection of the feature alignment metric calculation methods. The results illustrate that the capacity prediction model established using virtual data and the generative adversarial network (GAN)-based transfer learning method has ideal prediction performance (with the 0.0941 of the maximum test error in all capacity estimation situation).

An Early Minor-Fault Diagnosis Method for Lithium-Ion Battery Packs Based on Unsupervised Learning

Dear Editor, Any fault of a battery system that is not handled timely can cause catastrophic consequences. Therefore, it is significant to diagnose battery faults early and accurately. Due to the complex nonlinear features and inconsistency of lithium batteries, traditional fault diagnosis methods usually fail to detect battery minor faults in the early stages. Therefore, this letter proposes a real-time unsupervised learning diagnosis approach for early battery faults based on improved principal component analysis. The technique rotates the battery pack voltage sequence into a new coordinate space through linear combination, while the detection metrics of square prediction errors and modified contribution plots are employed to achieve minor fault traceability. In addition, the training sample relies on the voltage sequence of the battery health state instead of the fault data, which is difficult to collect. Moreover, this approach can not only locate the battery cell where the fault occurs but also diagnose battery open-circuit and short-circuit faults as well as the occurrence and duration of the fault in real-time. Furthermore, the feasibility and stability of the proposed method are verified by applying different experimental data. In summary, the presented approach provides an easy-to-implement option that does not require accurate mathematical modeling, expert understanding, and complex computational processes.

Prediction of State of Health of Lithium-Ion Battery Using Health Index Informed Attention Model

State-of-health (SOH) is a measure of a battery's capacity in comparison to its rated capacity. Despite numerous data-driven algorithms being developed to estimate battery SOH, they are often ineffective in handling time series data, as they are unable to utilize the most significant portion of a time series while predicting SOH. Furthermore, current data-driven algorithms are often unable to learn a health index, which is a measurement of the battery's health condition, to capture capacity degradation and regeneration. To address these issues, we first present an optimization model to obtain a health index of a battery, which accurately captures the battery's degradation trajectory and improves SOH prediction accuracy. Additionally, we introduce an attention-based deep learning algorithm, where an attention matrix, referring to the significance level of a time series, is developed to enable the predictive model to use the most significant portion of a time series for SOH prediction. Our numerical results demonstrate that the presented algorithm provides an effective health index and can precisely predict the SOH of a battery.

Review of Degradation Mechanism and Health Estimation Method of VRLA Battery Used for Standby Power Supply in Power System

As the backup power supply of power plants and substations, valve-regulated lead-acid (VRLA) batteries are the last safety guarantee for the safe and reliable operation of power systems, and the batteries’ status of health (SOH) directly affects the stability and safety of power system equipment. In recent years, serious safety accidents have often occurred due to aging and failure of VRLA batteries, so it is urgent to accurately evaluate the health status of batteries. Accurate estimation of battery SOH is conducive to real-time monitoring of single-battery health information, providing a reliable guarantee for fault diagnosis and improving the overall life and economic performance of the battery pack. In this paper, first, the floating charging operation characteristics and aging failure mechanism of a VRLA battery are summarized. Then, the definition and estimation methods of battery SOH are reviewed, including an experimental method, model method, data-driven method and fusion method. The advantages and disadvantages of various methods and their application conditions are analyzed. Finally, for a future big data power system backup power application scenario, the existing problems and development prospects of battery health state estimation are summarized and prospected.

An overview of data-driven battery health estimation technology for battery management system

Battery degradation, caused by multiple coupled degradation mechanisms, severely affects the safety and sustainability of a battery management system (BMS). The battery state of health (SOH) is a commonly-adopted metric to evaluate a battery’s degradation condition, which should be carefully modeled to facilitate the safety and reliability of a BMS. Recently, owing to the rapid progress of data science-related techniques, data-driven models for battery SOH estimation have attracted great attentions from both academia and industry communities. This paper aims to provide the scientists and engineers with a general overview of data-driven battery SOH estimation technology for BMSs. State-of-the-art models published during 2018–2022 are reviewed with care, including a) feature extraction and selection methods; b) benchmarks, variants and extensions of data-driven SOH estimation models; and c) publicly-available battery SOH datasets. Afterwards, experiments are conducted and analyzed on the Toyota & Stanford-MIT battery SOH datasets for benchmark study. Finally, existing challenges and feature trends are summarized.

State of Health Assessment of Lithium-ion Batteries Based on Deep Gaussian Process Regression Considering Heterogeneous Features

With the continuous development of the global new energy industry, lithium-ion batteries as new energy and the heart of intelligent manufacturing have attracted much attention. But the performance of lithium-ion battery systems has been deteriorating for a long time. An accurate assessment of its state of health (SOH) can effectively avoid unnecessary loss of lithium-ion batteries due to unexpected failure. Therefore, a method for evaluating the SOH of deep Gaussian process regression (DGPR) lithium-ion batteries based on the Gaussian process and deep network is presented. Firstly, the heterogeneous features reflecting the SOH of lithium-ion batteries were extracted from the aspects of charging and discharging time, the peak of incremental capacity curve (ICC), internal resistance, and energy. Then, through grey correlation analysis (GRA), significant features are introduced into the DGPR model to establish the SOH estimation method for lithium-ion batteries. Finally, the data sets provided by CALCE and NASA are used as an experimental object to compare with different data-driven models to verify the accuracy, reliability and applicability of the proposed models. The experimental results show that the method proposed in this paper has high accuracy in SOH estimation, RMSE is less than 0.7 %, and R2 is more than 98.2 % in each lithium-ion battery. It shows that this method can provide a reliable basis for the health management of lithium-ion batteries.

Data-driven state of health estimation in retired battery based on low and medium-frequency electrochemical impedance spectroscopy

Electrochemical impedance spectroscopy (EIS) is one of the critical techniques to characterize the state of health (SoH) of lithium-ion batteries, which has different performances under different SoH and dynamic working conditions. However, the identification parameters of full-frequency EIS will consume too much computing time. Considering that low and medium-frequency EIS plays a dominant role in battery aging, the present paper constructs a simplified equivalent circuit (SECM) based on low and medium-frequency EIS. Based on the fitted SECM parameters, three SECM parameters are selected as features by grey correlation analysis. Combined with the ambient temperature and SoC under dynamic conditions, the Gated recurrent unit neural network estimates the SoH of lithium-ion batteries. The proposed method has good accuracy and robustness for different SoC states and ambient temperature variations. This method's error values are less than 2 %, which proves the critical value of low and medium-frequency EIS signals in battery management systems.