Abstract: State of health (SOH) is a key parameter to assess lithium-ion battery feasibility for secondary usage applications. SOH estimation based on machine learning has attracted great
Based on previous research, lithium-ion battery SOH estimation methods are roughly divided into two categories: model-based and data-driven. Particularly in the electrochemical model, the characterization of the aging mechanism is clear and accurate, with a robust interpretative ability .However, to build a model, numerous electrochemical reactions
To tackle these challenges, this study proposed a novel fusion deep learning architecture based on BiLSTM and N-BEATS. BiLSTM has been extensively applied in LIBs SOC estimation and is considered a mature modeling network that conducts preliminary SOC estimation using voltage and current , .As a regression model, N-BEATS can sufficiently
State of health (SOH) is a key parameter to assess lithium-ion battery feasibility for secondary usage applications. SOH estimation based on machine learning has attracted great attention in recent years and holds potentials for battery informatization and cloud battery management techniques. In this article, a comprehensive study of the data-driven SOH estimation methods
In view of the shortage of related research on the SOC estimation of lithium-ion batteries, a novel fusion method for SOC estimation based on improved Genetic Algorithm BP
In this paper, we propose a multi-feature fusion-based battery SOH estimation based on bidirectional long short-term memory neural networks. According to the aging mechanism of
The results show that the proposed feature extraction and fusion decision methods can identify abnormal states and hazard levels in a timely and accurate manner, and this RF-based classification, warning and evaluation framework shows the promise of machine learning algorithms for interpretable early warning studies of battery failures, which can use
The aim of the TARANIS project is to demonstrate the economic viability of a nuclear fusion reaction based on a high-gain fusion scheme, with a targeted gain of over 100 MW (for every 1 MW of electrical power used, the reactor generates 100 MW of fusion power). This technology is based on the principle of inertial confinement fusion (ICF
Some mathematical models based on battery dynamics also have been developed to facilitate the prognostics, Supervision, Project administration, Writing – review & editing. Min Xie: Supervision, Project administration, Writing – review & editing. Acknowledgments. This work was supported by National Natural Science Foundation of China
The widespread adoption and utilization of electric vehicles has been constrained by power battery performance. We proposed a fault diagnosis method for power batteries based on multiple-model fusion. The method effectively fused the advantages of various classification models and avoided the bias of a single model towards certain fault types. Firstly,
Battery inconsistency detection mainly includes direct measurement method, statistically based method, model method and machine learning. Duan et al. proposed a battery inconsistency analysis method based on information entropy, which takes capacity, internal resistance and the ratio of constant current charging capacity to constant voltage
Based on the above analysis, for the field of electric vehicles, a multi-state joint estimation algorithm based on a new MDM is proposed to improve the dynamic characteristics of the battery pack model under complex operating conditions, take into account the computational complexity, and improve the accuracy and robustness of multi-state estimation of the battery
In recent years, amounts of related research have been carried out for battery SOH estimation and RUL prediction [, , ].Due to the unmeasurable battery capacity online, some health indexes extract from external parameters including terminal voltage, current and temperature to map the battery capacity degradation through artificial intelligence and machine
Perhaps one of the most comprehensive descriptions of physics based battery degradation models is that of Reniers et al. Battery digital twins: the fusion of models, data and artificial intelligence . In many applications where an abundance of data is now becoming available due to low-cost sensing and the increased deployment of IOT enabled devices, they
Due to the high complexity of the degradation process of lithium-ion batteries and their susceptibility to the actual working environment and usage conditions, accurately assessing battery SOH has turned out to be a challenging task the last few years, numerous researchers and engineers have conducted in-depth studies on SOH estimation of lithium-ion
If the charging state of the lithium-ion battery can be accurately predicted, overcharge and overdischarge of the battery can be avoided, and the service life of the battery can be improved. In
Model-based estimation methods combine battery models with numerical filters (such as Kalman filter (KF) , particle filter (PF) [16, 17], and Gaussian filter (GF) ) to track the degradation trends of the SOH.Yang et al. established the quantitative relationship between the current time constant and the normalized capacity based on the first-order
The model is based on a fusion technique for optimizing the tandem fusion of the Convolutional Neural Network (CNN) and the Long Short-Term Memory Network (LSTM). Firstly, the improved adaptive noise fully
2.1 UKF. As an extension of traditional Kalman filter, UKF is a nonlinear system state estimation filtering algorithm, which approximates the probability distribution of nonlinear system by introducing unscented transform [].The state of battery charge is a kind of state of nonlinear system, so it can estimate its state effectively and provide accurate estimation results.
Make fusion models using convolution neural network, temporal convolution network, long-short-term memory and bi-directional LSTM. Optimization of hyperparameters using Bayesian
Hu et al. classified the battery diagnostic methods into the model-based [13, 14], data-driven [15, 16], and knowledge-based .For model-based fault diagnostics, Feng et al. proposed a fault diagnosis algorithm based on an electro-thermal model, which diagnosed faults through capacity and internal resistance.Sidhu et al. used an extended
The widespread adoption and utilization of electric vehicles has been constrained by power battery performance. We proposed a fault diagnosis method for power batteries based on multiple-model fusion.
Tang P, Hua J, Wang P et al (2023) Prediction of lithium-ion battery SOC based on the fusion of MHA and ConvolGRU. Sci Rep 13(1):16543. Article Google Scholar Chuanbin W (2023) Research on State of Charge Estimation of Electric Vehicle Power Batteries Based on Neural Networks. Tianjin Vocational and Technical Normal University.
This paper investigates an innovative fusion method based on the information fusion technique for battery capacity estimation, considering the actual working conditions of EVs. Firstly, a...
Therefore, the effective fusion of multiple feature parameters is worth further research. Based on the above analysis, this paper proposed a battery SOH estimation method based on the multi-feature fusion model using the stacking algorithm. The main contributions of this article are summarized as follows: 1)
The current life-prediction models for lithium-ion batteries have several problems, such as the construction of complex feature structures, a high number of feature dimensions, and inaccurate prediction results. To overcome these problems, this paper proposes a deep-learning model combining an autoencoder network and a long short-term memory
In this study, we propose a novel fusion model combining Convolutional Neural Networks (CNNs), Long Short-term Memory networks (LSTMs), and Convolutional LSTM
Electric vehicles (EVs) are progressively replacing traditional fossil fuel-based internal combustion engine vehicles, offering an effective means to reduce emissions of CO 2, nitrogen oxides, and sulfur dioxide [1,2].As the primary energy source for EVs, the performance of the power battery directly influences the power, economy, safety, and service life of these
Research on consistency assessment method for energy storage battery based on operating data fusion. Distrib. Util., 34 (4) (2017), pp. 29-35. View in Scopus Google Scholar Fang W., Chen H., Zhou F. Fault diagnosis for cell voltage inconsistency of a battery pack in electric vehicles based on real-world driving data. Comput. Electr. Eng., 102 (2022), Article
Based on the study of the battery degradation mechanism, distribution of relaxation times (DRT) will be used to extract the degradation mechanism information in the frequency domain, to guide the acquisition of time-frequency fusion features from time domain charging data. Finally, a nonlinear mapping of time-frequency fusion features and SOH is
Lithium–ion batteries have become a vital component of the electronic industry due to their excellent performance, but with the development of the times, they have gradually revealed some shortcomings. Here, sodium–ion batteries have become a potential alternative to commercial lithium–ion batteries due to their abundant sodium reserves and safe and low-cost
Fusion estimation methods based on battery model and observer, including neural network method, fuzzy controller method and support vector machine. The accuracy of this method depends on the accuracy of the model. To improve the accuracy of the model, a large number of data samples need to be trained. 2 The Working Principle of Lead Acid Storage
The model-based method estimates SOC through battery model and nonlinear state estimation algorithms, which has the advantages of real-time and closed-loop feedback. Common battery models include electrochemical models and equivalent circuit models (ECMs). The electrochemical model is the most accurate and interpretable way to characterize batteries
This study proposed a multi-feature fusion framework based on the AM, called the AM-MFF, for robust and interpretable lithium-ion battery SOH estimation. The main conclusions are
The main innovations of this paper include: (1) To identify the battery SOH curves with the high similarity among multiple batteries in the same charge-discharge conditions, an early-stage SOH similarity analysis method based on bicorrelation is developed to obtain a representative battery SOH. (2) To reduce the amount of required voltage data during feature
To address the above issues, this study proposes a multi-feature fusion framework based on attention mechanism (AM) for robust and interpretable lithium-ion battery SOH estimation. First, independent CNN modules are used to extract ageing features from the partial data of multiple operational stages to overcome inconsistencies between data sources. Second, the AM is
The RUL of the battery means the quantity of cycles that the battery undergoes from the present time until it reaches the failure threshold . Currently, there exists three main approaches for predicting battery RUL: model-based method, data-driven method, and fusion-models method. Among them, the data-driven method eliminates the need for
In this paper, an advanced fusion estimation method for battery SOC and SOH is proposed considering the effects of temperature and aging. Firstly, to reduce the computational
In this paper, an advanced fusion estimation method is proposed for battery SOC and SOH with consideration of the temperature and aging statuses. The main contributions and conclusions can be summarized as below: The offline and online combined method is proposed for parameter identification based on the sensitivity of battery model parameters.
The CNN-LSTM-ASAN fusion model is used to predict the RUL of lithium-ion batteries, and the performance of the model is evaluated using various statistical error terms on NASA, CALCE, and self-use datasets. 2. Methodology The framework of the RUL prediction for lithium batteries proposed by this article is shown in Figure 1.
Unpredictability of battery lifetime has been a key stumbling block to technology advancement of safety-critical systems such as electric vehicles and stationary energy storage systems. In this work, we present a novel hybrid fusion strategy that combines physics-based and data-driven approaches to accurately predict battery capacity.
The results show that the combination of the fusion-based selection method and GPR has an overall superior estimation performance in terms of both accuracy and computational efficiency. State of health (SOH) is a key parameter to assess lithium-ion battery feasibility for secondary usage applications.
In addition, to evaluate the performance of the proposed estimation method other two commonly used estimation methods, including EKF and UKF, are employed for comparison. The reference SOCs are determined by the ampere-hour integration which is dependent on the test data documented by the battery test system.
By leveraging a thoroughly validated physics-based battery model, we extract typical aging patterns from laboratory aging data and extend them into a more comprehensive parameter space, encompassing diverse battery aging states in potential real-world applications while accounting for practical cell-to-cell variations.
Contact us for competitive quotes on any of our energy monitoring and control products
Get a Quote