State Of Charge Estimation Model Research Articles

State of charge estimation for lithium-ion battery based on whale optimization algorithm and multi-kernel relevance vector machine.

Lithium-ion batteries are key elements of electric vehicles and energy storage systems, and their accurate State of Charge (SOC) estimation is momentous for battery energy management, safe operation, and extended service life. In this paper, the Multi-Kernel Relevance Vector Machine (MKRVM) and Whale Optimization Algorithm (WOA) are used to estimate the SOC of lithium-ion batteries under different operating conditions. In order to better learn and estimate the battery SOC, MKRVM is used to establish a model to estimate lithium-ion battery SOC. WOA is used to automatically adjust and optimize weights and kernel parameters of MKRVM to improve estimation accuracy. The proposed model is validated with three lithium-ion batteries under different operating conditions. In contrast to other optimization algorithms, WOA has a better optimization effect and can estimate the SOC more accurately. In contrast to the single kernel function, the proposed multi-kernel function greatly improves the precision of the SOC estimation model. In contrast to the traditional method, the WOA-MKRVM has a higher precision of SOC estimation.

State of Charge Estimation Model Based on Genetic Algorithms and Multivariate Linear Regression with Applications in Electric Vehicles

Nowadays, the use of renewable, green/eco-friendly technologies is attracting the attention of researchers, with a view to overcoming recent challenges that must be faced to guarantee the availability of Electric Vehicles (EVs). Therefore, this work proposes a methodology based on Genetic Algorithms (GA) and multivariate regression for estimating and modeling the State of Charge (SOC) in Electric Vehicles. Indeed, the proposal considers the continuous monitoring of six load-related variables that have an influence on the SOC (State of Charge), specifically, the vehicle acceleration, vehicle speed, battery bank temperature, motor RPM, motor current, and motor temperature. Thus, these measurements are evaluated in a structure comprised of a Genetic Algorithm and a multivariate regression model in order to find those relevant signals that better model the State of Charge, as well as the Root Mean Square Error (RMSE). The proposed approach is validated under a real set of data acquired from a self-assembly Electric Vehicle, and the obtained results show a maximum accuracy of approximately 95.5%; thus, this proposed method can be applied as a reliable diagnostic tool in the automotive industry.

An improved state of charge estimation of lithium-ion battery based on a dual input model

ABSTRACT The state of charge (SOC) is critical for the safety and reliable utilization of the battery. However, SOC estimation accuracy of lithium iron phosphate (LiFePO4) battery is a challenging task because of its flat voltage plateau and its performance is affected greatly by temperature. An improved open circuit voltage (OCV) combined with coulomb counting (CC) method based on the dual input model of ambient temperature and OCV is proposed. This approach is employed to obtain the initial value of SOC based on the dual input model over a wide range of temperature, and to establish SOC estimation model of modified CC with Simulink. The temperature entropy coefficient and differential analysis has been analyzed under different SOC conditions. The SOC maximum errors predicted by the proposed OCV-CC method maintain within 3.10%, while the maximum errors of the traditional OCV-CC increase from 4.78% to 23.64% under the temperature of 35°C ~−15°C. The results show the estimation accuracy of SOC using the proposed OCV-CC method is improved obviously, especially under low temperature.

Extreme learning machine–radial basis function neural network–based state-of-charge estimation of lithium-ion batteries assisted with fiber Bragg grating sensor measurements

Lithium-ion batteries have been widely used in power systems for accepting large-scale renewable energy generations and in the transport sector to facilitate vehicle decarbonization, the accuracy of state-of-charge (SOC) estimation is extremely crucial for the battery systems to operate safely and reliably. Many approaches have been developed for battery SOC estimation based on the measurable electrical signals. However, the electrical measurements are usually corrupted by sensor noise and are also limited by insulation, corrosion, and electromagnetic compatibility. To address these problems, fiber Bragg grating (FBG) sensors are used to replace thermocouple sensors, the battery SOC therefore can be estimated based on the measurement of the strain information. In order to train the SOC estimation model for lithium-ion batteries, an FBG sensor–based battery SOC estimator, namely, ELM-RBFNN, is developed using the radial basis function neural network (RBFNN) identified by extreme learning machine (ELM). According to the ELM principle, the ELM-RBFNN model randomly selects the radial basis function (RBF) centers and determines the parameters of the hidden-layer nodes without any manual adjustment. The ELM-RBFNN estimation model has the advantages of fast learning speed, global optimization, and excellent generalization. Experimental results confirm that compared to the linear estimator and the polynomial estimator, the developed SOC estimator is able to produce more accurate results.

Algorithm of BPNN‐UKF based on a fusion model for SOC estimation in lithium‐ion batteries

AbstractLithium‐ion batteries (LIBs) are widely used as energy storage devices. Accurately estimating the state of charge (SOC) is critical for the safe operation of LIBs, but the complex internal characteristics of LIBs make this a difficult task. In this study, an algorithm called BPNN‐UKF, which combines the backpropagation neural network (BPNN) and unscented Kalman filtering (UKF), is proposed. First, a fusion model construction method incorporating AdaBoost and recursive least squares (RLS) is developed to enhance the accuracy and generalization of the battery model. Next, the fusion model is applied to create BPNN‐UKF, which reduces the model dependence of UKF and the training requirements of BPNN. In this method, UKF estimates the SOC, and then BPNN learns the nonlinear relationship between SOC estimation error and process variables in UKF preliminary estimation. The BPNN output is used to update the state vector in real time during the new UKF estimation process. Experimental results reveal that the proposed method can drastically improve estimation accuracy compared with the UKF and the simple combined BPNN‐UKF, and it exhibits considerable generalization to common disturbances in SOC estimation and various battery working conditions.

Online Model Parameter and State of Charge Estimation of Li-Ion Battery Using Unscented Kalman Filter Considering Effects of Temperatures and C-Rates

This paper proposed a technique for online modeling and state of charge (SoC) estimation of Li-ion batteries considering the effects of operating temperatures and C-rates. The proposed battery model, which is updated in real-time, is incorporated with the unscented Kalman filter (UKF) for accurate and online SoC estimation. In the proposed technique, Thevenin-based equivalent circuit model of Li-ion battery is used. Each of the RC networks of the Thevenin model is represented as a first-order linear time-invariant (LTI) system. The offline RC parameters are extracted as the parameters of the first-order LTI system using the final value theorem. Then the offline RC parameters are converted to the online model parameters compensating the effects of operating temperatures and C-rates. Finally, the UKF technique is augmented with the proposed online battery model for higher accurate and online SoC estimation. An experimental setup has been developed in the LabVIEW platform to validate the proposed battery model and apply it for online SoC estimation. The proposed online battery model and UKF are developed in Matlab and then integrated with the LabVIEW program using the Matlab-LabVIEW interface called Math Script. The proposed technique has been rigorously validated in the laboratory under hybrid pulse power characterization (HPPC) and federal urban driving schedule (FUDS) tests under wide range of varying operating temperatures and C-rates. In the HPPC test, the SoC estimated using the proposed technique has a maximum absolute relative percentage error (ARPE) of less than 2%, whereas the battery model that does not account for temperature and C-rate effects has a maximum ARPE of 8.79 percent, which is 4.30 times higher than the proposed technique. The proposed approach yielded mean ARPE of 0.30%, 1.02%, and 0.81% in the FUDS test at 25 °C, 0 °C, and 40 °C, respectively, which is performed in dynamic identical C-rates. Furthermore, higher accuracy and effectiveness of the proposed technique have been validated under the presence of white and coloured measurement noises.

An optimized long short-term memory-weighted fading extended Kalman filtering model with wide temperature adaptation for the state of charge estimation of lithium-ion batteries

Accurate state of charge (SOC) estimation at different operating temperatures is essential for the reliable and safe operation of battery management systems (BMS) for lithium-ion batteries in electric vehicles (EVs). In this paper, an optimized long-short-term memory-weighted fading extended Kalman filtering (LSTM-WFEKF) model with wide temperature adaptation is proposed as a temperature-conditioned model for SOC estimation. Firstly, the input datasets are categorized based on the operating temperatures for EVs in the United States Advanced Battery Consortium manual: cold (−10 °C), normal (25 °C), and hot (50 °C) temperatures and optimized with an attention mechanism for faster training of the LSTM model to cross-train and test to specifically study the effects of temperature on the SOC estimation through a transfer learning mechanism. Secondly, the SOC estimated by the LSTM model is input into a WFEKF method, which introduces adaptive weighing and fading factors to correct, denoise, and optimize the final SOC for each temperature variation under complex working conditions. Finally, the results show that the training and testing temperatures have distinctive SOC effects using the LSTM model. Also, the proposed LSTM-WFEKF model estimates the SOC with overall best mean absolute error (MAE), root mean square error (RMSE), and R-squared (R2) values of 0.0697%, 0.0784%, and 99.9965%, respectively, under different temperatures and complex working conditions, which is optimal compared to other existing models. Based on the MAE, RMSE, and R2 values under different operating temperatures and complex working conditions, this paper concludes that the 25 °C training dataset ensures a more accurate SOC estimation. Meanwhile, the −10 °C and 50 °C training datasets cause more and less noisy estimates, respectively. The proposed LSTM-WFEKF model has wide temperature and working condition adaptability for real-time BMS applications in EVs.

Lebesgue Sampling-Based Li-Ion Battery Simplified First Principle Model for SOC Estimation and RDT Prediction

The state-of-charge (SOC) estimation and remaining-dischargeable-time (RDT) prediction are critical and challenging to safe operation of Li-ion batteries. The main challenges are the limited accuracy of traditional equivalent circuit model and computation-inefficiency of electrochemical battery models. To address this problem, this article proposes a Lebesgue-sampling-based extended Kalman filter (LS-EKF) approach that integrates the high fidelity of a simplified first principle (SFP) model with the low computation of Lebesgue sampling (LS) in a Bayesian estimation framework. In this framework, the SFP model is first introduced along with its design and validation. The LS-EKF is employed with the SFP model to estimate the SOC and predict the RDT. The proposed method is verified with a series of experiments under different operating conditions. The results and comparisons demonstrate the effectiveness of the proposed method in terms of the accuracy of estimation and prediction, as well as the computational efficiency.

SOC Estimation of E-Cell Combining BP Neural Network and EKF Algorithm

Power lithium battery is an important core component of electric vehicles (EV), which provides the main power and energy for EV. In order to improve the estimation accuracy of the state of charge (SOC) of the electric vehicle battery (E-cell), the extended Kalman filter (EKF) algorithm, and backpropagation neural network (BPNN) are used to build the SOC estimation model of the E-cell, and the self-learning characteristic of BP neural network is used to correct the error and track the SOC of the E-cell. The results show that the average error of SOC estimation of BP-EKF model is 0.347%, 0.0231%, and 0.0749%, respectively, under the three working conditions of constant current discharge, pulse discharge, and urban dynamometer driving schedule (UDDS). Under the influence of different initial value errors, the average estimation errors of BP-EKF model are 0.2218%, 0.0976%, and 0.5226%. After the noise interference is introduced, the average estimation errors of BP-EKF model under the three working conditions are 1.2143%, 0.2259%, and 0.5104%, respectively, which proves that the model has strong robustness and stability. Using the BP-EKF model to estimate and track the SOC of E-cell can provide data reference for vehicle battery management and is of great significance to improve the battery performance and energy utilization of EV.

Robust state of charge estimation for Li-ion batteries based on cubature kalman filter with generalized maximum correntropy criterion

Kalman filters (KFs) are widely used for state-of-charge (SOC) estimation of Li-ion batteries due to their excellent dynamic tracking capability. Especially the cubature KF (CKF), with the computational efficiency and nonlinear processing ability, is an outstanding candidate for SOC estimation. However, the actual working conditions are complex and changeable, and the measurement data is usually accompanied by non-Gaussian noise (outliers). Therefore, the performance of the original CKF with minimum mean square error (MMSE) criterion may be degraded seriously in these cases. In order to enhance the robustness of CKF, the MMSE in the CKF framework is substituted by the generalized maximum correntropy criterion (GMCC), and thus a robust CKF with GMCC (GMCC-CKF) is developed by fixed point iteration approach in this work. Furthermore, a SOC estimation model via the GMCC-CKF is proposed to improve estimation accuracy under non-Gaussian noise environments. The simulation results show that, compared with the traditional KFs, the proposed GMCC-CKF can accurately estimate the SOC of lithium batteries under different temperatures and operating conditions considering non-Gaussian noise interference. The results of mean absolute error (MAE) and root mean square error (RMSE) are less than 1%, which verifies the excellent performance of GMCC-CKF.

Improved wild horse optimizer with deep learning enabled battery management system for internet of things based hybrid electric vehicles

Internet of Things (IoT) become an emergent platform in wireless technologies in design of electric vehicles (EVs) and hybrid electric vehicles (HEVs). Dynamic energy storage systems, batteries can be damaged due to overcharging/discharging and their mass penetration deeply affects the grid. For circumventing the likelihood of damage, the EVs and HEVs require an accurate state of charge (SOC) estimation approach for improving the lifetime and safety. An efficient battery management system (BMS) remains a challenging problem in HEVs, commonly utilized to indicate the battery state-of-charge (SOC). As over-charge and over-discharge outcome from predictable damage to the batteries, precise SOC estimation model is needed for HEVs. In this aspect, this study presents an improved wild horse optimizer with deep learning enabled battery management system (IWHODL-BMS) for IoT based HEVs. The presented IWHODL-BMS employs attention based bidirectional long short-term memory (ABiGRU) approach to accurately estimate SOC in HEVs. For enhancing SOC estimation performance of the ABiGRU technique, the IWHO algorithm is utilized as hyperparameter optimizer. The application of the ABiGRU model results in simpler and accurate representation of the input. A comprehensive simulation result portrayed the enhanced outcomes of the IWHODL-BMS model over the other methods under varying measures.

A Data-Driven Model Framework Based on Deep Learning for Estimating the States of Lithium-Ion Batteries

The accurate estimation of state of charge (SOC) and state of health (SOH) of lithium-ion battery is crucial to ensure the safe and stable operation of the battery. In this paper, a data-driven model framework based on deep learning for estimating SOC and SOH is proposed, which mainly consists of long short-term memory (LSTM) neural network and back propagation (BP) neural network. The switch between SOC estimation model and SOH estimation model can be realized by adjusting the output mode of LSTM. When estimating SOC, the LSTM is set to have corresponding output at each input. The model takes 10 consecutive voltage sampling points as input and the estimated value of SOC at the last sampling moment as output. When estimating SOH, the LSTM is set to have a corresponding output only at the last input. The model takes the sequence of 150 sampling points on the charging voltage curve as input and the SOH value at the current cycle as output. Experiments are carried out on the Oxford battery degradation dataset, and the results show that the proposed model framework can obtain accurate and reliable estimates of SOC and SOH.

Design of peer-to-peer energy trading in transactive energy management for charge estimation of lithium-ion battery on hybrid electric vehicles

Transactive energy is a next big thing in the energy sector which considerably transform the association between utility, consumer, and the environment. Transactive energy management (TEM) system comprises a collection of economical and controlling strategies which helps to dynamically balance the power infrastructure. Peer-to-Peer (P2P) trading becomes familiar, which mainly based on the process of power generation and consumption is completely decentralized. At the same time, Hybrid electric vehicles (HEV) have become an important technology to accomplish energy efficiency and environmental sustainability. Battery Management System (BMS) evaluates the power and State of Charge (SOC), confirms the well-being depending upon the measurement. Accurate SOC estimation is crucial to ensure the unfailing functioning of Li-ion battery that is mainly employed in HEVs. A reliable SOC prediction model is needed to assure the precise measurement of the residual driving range of the vehicle and appropriate battery balancing. In this view, this paper presents an optimal machine learning based SOC estimation (OML-SOCE) model for HEVs in TEM. The OML-SOCE is aimed for estimating an accurate capacity of SOC of Li-ion batteries on HEVs. The OML-SOCE technique involves a two stage process namely stacked sparse autoencoder (SSAE) based prediction and salp swarm algorithm (SSA). At the first stage, SSAE is used for the prediction of SOC. Sparse auto-encoder (AE) is an enhanced AE technique that improves any some sparsity restrictions in the hidden layer of standard AE. A stack of multiple sparse AE forms a deep network framework that is named as SSAE. Next, in the second stage, the parameters involved in the SSAE are optimally adjusted by the use of SSA in such a way that the prediction performance can be considerably improved. A wide range of experiments take place and the results are investigated under varying temperature levels. The experimental outcomes showcased the supremacy of the presented technique the recent techniques with respect to different measures.

A Novel Deep Learning-Based State-of-Charge Estimation for Renewable Energy Management System in Hybrid Electric Vehicles

In recent years, alternative engine technologies are necessary to resolve the problems related to conventional vehicles. Electric vehicles (EVs) and hybrid electric vehicles (HEVs) are effective solutions to decarbonize the transportation sector. It also becomes important to shift from traditional houses to smart houses and from classical vehicles to EVs or HEVs. It is needed to combine renewable energy sources (RESs) such as solar photovoltaics, wind energy systems, and various forms of bio-energies. Among various HEV technologies, an effective battery management system (BMS) still remains a crucial issue that is majorly used for indicating the battery state of charge (SOC). Since over-charging and over-discharging result in inevitable impairment to the batteries, accurate SOC estimation desires to be presented by the BMS. Although several SOC estimation techniques exist to regulate the SOC of the battery cell, it is needed to improvise the SOC estimation performance on HEVs. In this view, this paper focuses on the design of a novel deep learning (DL) with SOC estimation model for secure renewable energy management (DLSOC-REM) technique for HEVs. The presented model employs a hybrid convolution neural network and long short-term memory (HCNN-LSTM) model for the accurate estimation of SOC. In order to improve the SOC estimation outcomes of the HCNN-LSTM model, the barnacles mating optimizer (BMO) is applied for the hyperpower tuning process. The utilization of the HCNN-LSTM model makes the modeling process easier and offers a precise depiction of the input–output relationship of the battery model. The design of BMO based HCNN-LSTM model for SOC estimation shows the novelty of the work. An extensive experimental analysis highlighted the supremacy of the proposed model over other existing methods in terms of different aspects.

A Particle-Swarm-Optimization-Based Approach for the State-of-Charge Estimation of an Electric Vehicle When Driven Under Real Conditions

Recent developments in lithium-ion (Li-ion) storage technology have enabled a revolution in the automotive industry. Fully electric vehicles (EVs) operate under the most diverse combination of driving and environmental conditions affecting the autonomy range. In other words, an equal state-of-charge (SOC) on two same model EV does not mean the same traveling distance since the conditions such as the state-of-health (SOH) of the battery, type of driver and even the type of route will influence the EV performance. Typically, SOC estimation algorithms are proposed and validated under controlled laboratory conditions. However, when real conditions are present, it is necessary to incorporate new tools capable of handling the diverse variability present in all the conditions. For instance, the topography of the route influences the current that the battery pack delivers, and the performance on the same route can be affected by the SOH. One of the main concerns for EV owners is that once a battery pack is installed, it becomes almost impossible to perform laboratory tests under controlled conditions. This paper proposes a novel approach to estimate the SOC by extending an existing SOC model (obtained in laboratory conditions) with the novelty of the assistance of Particle-Swarm-Optimization (PSO) to estimate the model parameters using real EV driving data. The data was obtained by a real-driving experiment, which consists on driving the EV in a complete discharge cycle on a highway. During this experiment, the initial SOC was at 100\%, and the idea was to discharge the battery pack driving through a highway where the driving conditions are almost uniform making it possible to characterize the SOC curve. Then, PSO is used to estimate the model parameters, and afterwards the model is validated in different types of routes. The obtained results show that the proposed approach can estimate the SOC satisfactorily. In this regard, this type of real-driving experiment can be performed by any driver, and by combining the particular results with the proposed approach, the users can personalize the SOC estimation model to their vehicles, and even more, create their own knowledge base of their EV performance through time. Therefore, the real-driving experiment can be replicated when needed to update the model parameters, thus allowing a better understanding of the actual SOH of the battery pack. Furthermore, by combining the obtained model with the elevation profile of a given route, the user can assess where to stop in case that a recharge is necessary.

A Physically Inspired Equivalent Neural Network Circuit Model for SoC Estimation of Electrochemical Cells

Battery Management System (BMS) design for Lithium-ion batteries State of Charge (SoC) prediction has a crucial role in Electric Vehicles (EVs) and smart grids development. The need to design compact, light and fast devices requires finding a suitable trade-off between effectiveness and efficiency. In the literature, it is well emphasized that the application of electrochemical-based methods such as the Pseudo-Two-Dimensional (P2D) model is computationally prohibitive and requires significant simplifications. Conversely, plain Equivalent Circuit Models (ECM) are too simple and unable to represent the cell dynamics. The application of an Ensemble Neural Network (ENN) as Equivalent Neural Network Circuit (ENNC) emerged as a promising solution able to synthesize expressive and computationally efficient models. Indeed, with the support of a suitable dataset, an ENN can be configured to represent a given ECM, modeling each lumped parameter through an assigned Neural Network (NN). Accordingly, the ENNC system is able to keep a physical description of the battery cell while approximating the non-linear dynamic of each component. The paper proposes a novel ENNC battery named Physical Inspired-Equivalent Neural Network Circuit (PI-ENNC) whose ensemble architecture relies on a fractional-order Extended Single Particle (ESP) Lithium-ion cell formulation. The PI-ENNC is designed to approximate the ESP transfer functions referred to the ohmic effects, the electrolyte diffusion and the non-uniform charge distribution in the cell. The proposed model has been tested with three publicly available datasets, investigating the model behavior according to two different training strategies and with different input configurations. In order to prove its effectiveness, results have been compared with a simpler version proposed in a previous work. Results highlight the effectiveness of PI-ENNC in SoC prediction, underlining the importance of designing an ENN architecture that leverages on equations and constraints that reflect the physical phenomena of the cell.

Design of an Effective State of Charge Estimation Method for a Lithium-Ion Battery Pack Using Extended Kalman Filter and Artificial Neural Network

Currently, Lithium-ion batteries (LiB) are widely applied in energy storage devices in smart grids and electric vehicles. The state of charge (SOC) is an indication of the available battery capacity, and is one of the most important factors that should be monitored to optimize LiB’s performance and improve its lifetime. However, because the SOC relies on many nonlinear factors, it is difficult to estimate accurately. This paper presented the design of an effective SOC estimation method for a LiB pack Battery Management System (BMS) based on Kalman Filter (KF) and Artificial Neural Network (ANN). First, considering the configuration and specifications of the BMS and LiB pack, an ANN was constructed for the SOC estimation, and then the ANN was trained and tested using the Google TensorFlow open-source library. An SOC estimation model based on the extended KF (EKF) and a Thevenin battery model was developed. Then, we proposed a combined mode EKF-ANN that integrates the estimation of the EKF into the ANN. Both methods were evaluated through experiments conducted on a real LiB pack. As a result, the ANN and KF methods showed maximum errors of 2.6% and 2.8%, but the EKF-ANN method showed better performance with less than 1% error.

State-of-Charge Estimation of Li-ion Battery Using Gated Recurrent Unit With One-Cycle Learning Rate Policy

Deep learning has gained much traction in application to state-of-charge (SOC) estimation for Li-ion batteries in electric vehicle applications. However, with the vast selection of architectures and hyperparameter combinations, it remains challenging to design an accurate and robust SOC estimation model with a sufficiently low computation cost. Therefore, this study provides a comparative evaluation among commonly used deep learning models from the recurrent, convolutional, and feedforward architecture benchmarked on an openly available Li-ion battery dataset. To evaluate model robustness and generalization capability, we train and test models on different drive cycles at various temperatures and compute the root mean squared error (RMSE) and mean absolute error metric. To evaluate model computation costs, we run models in real-time and record the model size, floating-point operations per second (FLOPS), and run-time duration per datapoint. This study proposes a two-hidden layer stacked gated recurrent unit model trained with a one-cycle policy learning rate scheduler. The proposed model achieves a minimum RMSE of 0.52% on the train dataset and 0.65% on the test dataset while maintaining a relatively low computation cost. Executing the proposed model in real-time takes up approximately 1 MB in disk space, 300K FLOPS, and 0.03 ms run-time per datapoint. This makes the proposed model feasible to be executed on lightweight battery management system processors.

Transfer Learning-Based State of Charge Estimation for Lithium-Ion Battery at Varying Ambient Temperatures

Accurate and reliable state of charge (SoC) estimation becomes increasingly important to provide a stable and efficient environment for Lithium-ion batteries (LiBs) powered devices. Most data-driven SoC models are built for a fixed ambient temperature, which neglect the high sensitivity of LiBs to temperature and may cause severe prediction errors. Nevertheless, a systematic evaluation of the impact of temperature on SoC estimation and ways for a prompt adjustment of the estimation model to new temperatures using limited data has been hardly discussed. To solve these challenges, a novel SoC estimation method is proposed by exploiting temporal dynamics of measurements and transferring consistent estimation ability among different temperatures. First, temporal dynamics, which is presented by correlations between the past fluctuation and the future motion, are extracted using canonical variate analysis. Next, two models, including a reference SoC estimation model and an estimation ability monitoring model, are developed with temporal dynamics. The monitoring model provides a path to quantitatively evaluate the influences of temperature on SoC estimation ability. After that, once the inability of the reference SoC estimation model is detected, consistent temporal dynamics between temperatures are selected for transfer learning. Finally, the efficacy of the proposed method is verified through a benchmark. Our proposed method not only reduces prediction errors at fixed temperatures (e.g., reduced by 24.35% at -20 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">°</sup> C, 49.82% at 25 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">°</sup> C) but also improves prediction accuracies at new temperatures.

State-of-Charge Estimation of Lithium-Ion Batteries in the Battery Degradation Process Based on Recurrent Neural Network

Due to the rapidly increasing energy demand and the more serious environmental pollution problems, lithium-ion battery is more and more widely used as high-efficiency clean energy. State of Charge (SOC) representing the physical quantity of battery remaining energy is the most critical factor to ensure the stability and safety of lithium-ion battery. The novelty SOC estimation model, which is two recurrent neural networks with gated recurrent units combined with Coulomb counting method is proposed in this paper. The estimation model not only takes voltage, current, and temperature as input feature but also takes into account the influence of battery degradation process, including charging and discharging times, as well as the last discharge charge. The SOC of the battery is estimated by the network under three different working conditions, and the results show that the average error of the proposed neural network is less than 3%. Compared with other neural network structures, the proposed network estimation results are more stable and accurate.