State-of-Charge Estimation of Li-Ion Battery in Electric Vehicles: A Deep Neural Network Approach
The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
Abstract
The state of charge (SOC) is a crucial parameter of a battery management system for Li-ion batteries. The SOC indicates the amount of charge left in the battery of electric vehicles-akin to the fuel gauge in combustion vehicles. An accurate SOC knowledge contributes largely to the longevity, performance, and reliability of the battery. However, the SOC of Li-ion batteries cannot be easily measured by any apparatus. Furthermore, the SOC can also be influenced by numerous incalculable factors such as battery chemistry, ambient environment, aging factor, etc. In this article, we propose an SOC estimation model for a Li-ion battery using an improved deep neural network (DNN) approach for electric vehicle applications. We found that a DNN with a sufficient number of hidden layers is capable of predicting the SOC of the unseen drive cycles during training. We developed a series of DNN models with a varying number of hidden layers, and its training algorithm was to investigate their respective performance when evaluated on different drive cycles. We observe that the increasing number of hidden layers in the DNN (up to four hidden layers) decreases the error rate and improves SOC estimation. An additional increase in the number of hidden layers beyond that increases the error rate. In this study, we show that a four-hidden-layer DNN trained on Dynamic Stress Test drive cycle is capable of predicting SOC values unexpectedly well of other unseen drive cycles such as Federal Urban Driving Schedule, Beijing Dynamic Stress Test, and Supplemental Federal Test Procedure, respectively.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Their results revealed a U-shaped relationship: too few layers hinder learning capacity, while excessive layers increase overfitting and estimation error for unknown cycles[63].”
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [63]
In the citing paper
“MLP estimators have become less prevalent in SOC estimation due to their inability to effectively handle temporal data, which is critical for accurate and stable SOC estimations[63].”
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [63]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 2×
“Moreover, it is also worth noting that the main advantage of the DNN compared with recurrent models (such as LSTM and gated recurrent unit (GRU)) is the computation cost and complexity [25].”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“However, many recent advances suggest the use of a faster optimization algorithm such as the Adam optimization algorithm to update the weights of the DNN instead of the classical SGD [32].”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570 · cited 1×
“However, many developments in recent years had augmented the conventional ANN into becoming state of the art [21].”
BackgroundTensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
(2016) · Cited by 11,679
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215
Dynamic Routing Between Capsules
Sabour, S., Frosst, N., & Hinton, G. E. (2017) · arXiv · doi:10.48550/arxiv.1710.09829 · Cited by 4,167 · cited 1×
“Coupled with more intelligent training schemes and tweaks, the DNN is the current record holder in domains such as computer vision [23], speech recognition [24], and natural language processing [25].”
A review of the features and analyses of the solid electrolyte interphase in Li-ion batteries
Verma, P., Maire, P., & Novák, P. (2010) · Electrochimica Acta · doi:10.1016/j.electacta.2010.05.072 · Cited by 2,903 · cited 1×
“Attractive features such as high voltage, high energy density, long lifespan, low self-discharge, and low memory effect make the Li-ion battery superior to other ESSs [3].”
BackgroundSafety mechanisms in lithium-ion batteries
Balakrishnan, P. G., Ramesh, R., & Prem Kumar, T. (2006) · Journal of Power Sources · doi:10.1016/j.jpowsour.2005.12.002 · Cited by 1,132 · cited 1×
“Nevertheless, the SOC of the battery must be estimated as accurately as possible to ensure optimal battery performance, lifespan, and safe operation [8].”
BackgroundCritical Review on the Battery State of Charge Estimation Methods for Electric Vehicles
Xiong, R., Cao, J., Yu, Q., He, H., & Sun, F. (2018) · IEEE Access · doi:10.1109/access.2017.2780258 · Cited by 1,004 · cited 2×
“Numerous recent works can be found in the literature that pertains to the SOC estimation problem [9]–[11].”
BackgroundXing, Y., He, W., Pecht, M., & Tsui, K. L. (2014) · Applied Energy · doi:10.1016/j.apenergy.2013.07.008 · Cited by 977 · cited 3×
“The authors of the dataset in [38] stated that the initial SOC of the batteries is 80%.”
BackgroundMethodLong Short-Term Memory Networks for Accurate State-of-Charge Estimation of Li-ion Batteries
Chemali, E., Kollmeyer, P. J., Preindl, M., Ahmed, R., & Emadi, A. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2787586 · Cited by 906 · cited 1×
“In [26], the authors utilized a long short-term memory (LSTM) network trained and evaluated on customized drive cycles.”
MethodThe Expressive Power of Neural Networks: A View from the WidthPreprint
Zhou, L., Pu, H., Wang, F., Hu, Z., & Wang, L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.02540 · Cited by 864 · cited 1×
“01% moreparametersthatcould leadtoimprovingthegeneralizationcapability[45].”
Chemali, E., Kollmeyer, P. J., Preindl, M., & Emadi, A. (2018) · Journal of Power Sources · doi:10.1016/j.jpowsour.2018.06.104 · Cited by 818 · cited 4×
“In another work, the same authors proposed using multilayer perceptron DNN [27] to predict the SOC.”
BackgroundMethodInfluentialHow, D. N. T., Hannan, M. A., Hossain Lipu, M. S., & Ker, P. J. (2019) · IEEE Access · doi:10.1109/access.2019.2942213 · Cited by 812
Self-citationBattery-Management System (BMS) and SOC Development for Electrical Vehicles
Cheng, K. W. E., Divakar, B. P., Wu, H., Ding, K., & Ho, H. F. (2011) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2010.2089647 · Cited by 692 · cited 1×
“The Li-ion battery is monitored and controlled by a battery management system (BMS), which evaluates charge estimation, health prediction, thermal control, charge equalization, protection, and optimal energy and power consumption [4].”
BackgroundNovikov, A., Podoprikhin, D., Osokin, A., & Vetrov, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.06569 · Cited by 558
Ali, M. U., Zafar, A., Nengroo, S. H., Hussain, S., Junaid Alvi, M., & Kim, H.-J. (2019) · Energies · doi:10.3390/en12030446 · Cited by 442 · cited 1×
“Numerous recent works can be found in the literature that pertains to the SOC estimation problem [9]–[11].”
BackgroundDeep Neural Network Approaches to Speaker and Language Recognition
Richardson, F., Reynolds, D., & Dehak, N. (2015) · IEEE Signal Processing Letters · doi:10.1109/lsp.2015.2420092 · Cited by 404 · cited 1×
“Coupled with more intelligent training schemes and tweaks, the DNN is the current record holder in domains such as computer vision [23], speech recognition [24], and natural language processing [25].”
Rahimi-Eichi, H., Baronti, F., & Chow, M.-Y. (2014) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2013.2263774 · Cited by 380 · cited 1×
“Using the sampled value of instantaneous voltage and current of the cell, the corresponding SOC is calculated using the following Coulomb counting [39] formula: where SOC( t ) denotes the SOC at the current time, SOC( t − 1 ) denotes the previous SOC value, I ( t ) denotes the instantaneous…”
MethodBatch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
Ioffe, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.03275 · Cited by 367 · cited 1×
“In order to mitigate the chances of overfitting, a batch normalization (BN) layer [31] is implemented after each successive hidden layer.”
BackgroundMeng, J., Luo, G., & Gao, F. (2016) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2015.2439578 · Cited by 349 · cited 1×
“Typically traditional machine learning algorithms, such as support vector machine [18], fuzzy controller [19], and artificial neural network (ANN) [20], and various combinations of the algorithms were often employed.”
MethodJoining Technologies for Automotive Battery Systems Manufacturing
Das, A., Li, D., Williams, D., & Greenwood, D. (2018) · World Electric Vehicle Journal · doi:10.3390/wevj9020022 · Cited by 292 · cited 1×
“In electrical vehicle testing, drive cycles are often used to evaluate vehicle characteristics such as energy consumption and emissions [36].”
MethodHannan, M. A., Lipu, M. S. H., Hussain, A., Saad, M. H., & Ayob, A. (2018) · IEEE Access · doi:10.1109/access.2018.2797976 · Cited by 288 · cited 3×
“However, these methods have known limitations and have been gradually superseded by more sophisticated methods such as the Model-Based estimation method [12].”
BackgroundMethodSelf-citationUniversal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations
Hanin, B. (n.d.) · RePEc: Research Papers in Economics · Cited by 278
State-of-Charge Estimation of Lithium-Ion Batteries via Long Short-Term Memory Network
Yang, F., Song, X., Xu, F., & Tsui, K.-L. (2019) · IEEE Access · doi:10.1109/access.2019.2912803 · Cited by 234 · cited 1×
“This is because models with more parameters offer more expressive power [43].”
BackgroundMohanty, D., Hockaday, E., Li, J., Hensley, D. K., Daniel, C., & Wood, D. L. (2016) · Journal of Power Sources · doi:10.1016/j.jpowsour.2016.02.007 · Cited by 226 · cited 1×
“(agglomeration, pinholes, nonuniform coatings, and metal contamination) [6].”
Lin, C., Mu, H., Xiong, R., & Shen, W. (2016) · Applied Energy · doi:10.1016/j.apenergy.2016.01.010 · Cited by 217 · cited 1×
“Typical algorithms found in the literature include Kalman filter [13], Luenberger observer [14],proportional–integralobserver[15],H (cid:2) observer[16],and sliding-mode observer [17].”
MethodEarly Stopping Criteria for Energy-Efficient Low-Latency Belief-Propagation Polar Code Decoders
Yuan, B., & Parhi, K. K. (2014) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2014.2366712 · Cited by 216 · cited 1×
“The equations of all the error metric are expressed as follows: In order to prevent overfitting, backpropagation training is used in conjunction with the early stopping training scheme [33].”
MethodNeural Network-Based State of Charge Observer Design for Lithium-Ion Batteries
Chen, J., Ouyang, Q., Xu, C., & Su, H. (2018) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2017.2664726 · Cited by 216 · cited 1×
“Typically traditional machine learning algorithms, such as support vector machine [18], fuzzy controller [19], and artificial neural network (ANN) [20], and various combinations of the algorithms were often employed.”
MethodHossain Lipu, M. S., Hannan, M. A., Hussain, A., Saad, M. H., Ayob, A., & Uddin, M. N. (2019) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2019.2902532 · Cited by 188 · cited 1×
“and its parameters, accurately estimating the SOC of the Li-ion battery is not trivial [7].”
BackgroundSelf-citationHuang, Z., Yang, F., Xu, F., Song, X., & Tsui, K.-L. (2019) · IEEE Access · doi:10.1109/access.2019.2928037 · Cited by 188
A method for state-of-charge estimation of LiFePO4 batteries based on a dual-circuit state observer
Tang, X., Wang, Y., & Chen, Z. (2015) · Journal of Power Sources · doi:10.1016/j.jpowsour.2015.07.028 · Cited by 161 · cited 1×
“Typical algorithms found in the literature include Kalman filter [13], Luenberger observer [14],proportional–integralobserver[15],H (cid:2) observer[16],and sliding-mode observer [17].”
MethodDey, S., Ayalew, B., & Pisu, P. (2015) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2014.2382635 · Cited by 158 · cited 1×
“Typical algorithms found in the literature include Kalman filter [13], Luenberger observer [14],proportional–integralobserver[15],H (cid:2) observer[16],and sliding-mode observer [17].”
MethodHardware accelerators for recurrent neural networks on FPGA
Chang, A. X. M., & Culurciello, E. (2017) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2017.8050816 · Cited by 118 · cited 1×
“Recurrent models such as the LSTM and the GRU require more resources and memory bandwidthandlatencytotrainandrun[47].”
MethodLoss-Minimization-Based Charging Strategy for Lithium-Ion Battery
Chen, Z., Xia, B., Mi, C. C., & Xiong, R. (2015) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2015.2417118 · Cited by 83 · cited 1×
“Careful handling and special monitoring are essential to avoid serious catastrophe and performance degradation [2].”
BackgroundAn On-Board Model-Based Condition Monitoring for Lithium-Ion Batteries
Kim, T., Adhikaree, A., Pandey, R., Kang, D.-W., Kim, M., Oh, C.-Y., & Baek, J.-W. (2019) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2018.2881183 · Cited by 78 · cited 1×
“Typical algorithms found in the literature include Kalman filter [13], Luenberger observer [14],proportional–integralobserver[15],H (cid:2) observer[16],and sliding-mode observer [17].”
MethodExtended Kalman Filter with a Fuzzy Method for Accurate Battery Pack State of Charge Estimation
Sepasi, S., Roose, L., & Matsuura, M. (2015) · Energies · doi:10.3390/en8065217 · Cited by 74
A Novel Battery State of Charge Estimation Method Based on a Super-Twisting Sliding Mode Observer
Huangfu, Y., Xu, J., Zhao, D., Liu, Y., & Gao, F. (2018) · Energies · doi:10.3390/en11051211 · Cited by 57 · cited 1×
“Typical algorithms found in the literature include Kalman filter [13], Luenberger observer [14],proportional–integralobserver[15],H (cid:2) observer[16],and sliding-mode observer [17].”
MethodE-PUR: an energy-efficient processing unit for recurrent neural networks
Silfa, F., Dot, G., Arnau, J.-M., & Gonzàlez, A. (2018) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1145/3243176.3243184 · Cited by 46 · cited 1×
“SinceBMShardwaretypicallydoesnotencompassso-phisticatedhardware,implementingtherecurrentmodelsonthe BMSmayprovetobeachallenge[49].”
Chen, Y., Huang, D., Zhu, Q., Liu, W., Liu, C., & Xiong, N. (2017) · Energies · doi:10.3390/en10091313 · Cited by 44
State-of-Charge Estimation of Li-ion Battery in Electric Vehicles: A Deep Neural Network Approach
How, D. N. T., Hannan, M. A., Lipu, M. S. H., Sahari, K. S. M., Ker, P. J., & Muttaqi, K. M. (2019) · 2019 IEEE Industry Applications Society Annual Meeting · doi:10.1109/ias.2019.8912003 · Cited by 36 · cited 2×
“Every hidden layer activation h is computed as follows: where σ is the rectified linear unit (ReLU) [30] activation function is given by At the output layer, the SOC is computed as follows: where L is the last hidden layer and η is the sigmoid activation function given by (5)”
MethodSelf-citationRechargeable lithium batteries : from fundamentals to applications
Franco, A. A. (2015) · Cited by 35
State-of-Charge Estimation with State-of-Health Calibration for Lithium-Ion Batteries
Wu, T.-H., & Moo, C.-S. (2017) · Energies · doi:10.3390/en10070987 · Cited by 34
Research works printed but not linked: 4
- 2019, Vehicle and fuel emissions testing dynamometer drive schedules
- gharehpetian, 2017, Distributed Generation Systems Design Operation and Grid Integration
- plett, 2015, Battery Management Systems Battery Modeling, 1
- goodfellow, 2016, Deep Learning
Cited by
Overview of batteries and battery management for electric vehicles
Liu, W., Placke, T., & Chau, K. T. (2022) · Energy Reports · doi:10.1016/j.egyr.2022.03.016 · Cited by 715
Hannan, M. A., Wali, S. B., Ker, P. J., Rahman, M. S. A., Mansor, M., Ramachandaramurthy, V. K., Muttaqi, K. M., Mahlia, T. M. I., & Dong, Z. Y. (2021) · Journal of Energy Storage · doi:10.1016/j.est.2021.103023 · Cited by 676
Self-citationAcharige, S. S. G., Haque, M. E., Arif, M. T., Hosseinzadeh, N., Hasan, K. N., & Oo, A. M. T. (2023) · IEEE Access · doi:10.1109/access.2023.3267164 · Cited by 590
Nyamathulla, S., & Dhanamjayulu, C. (2024) · Journal of Energy Storage · doi:10.1016/j.est.2024.111179 · Cited by 518
Review of battery state estimation methods for electric vehicles - Part I: SOC estimation
Demirci, O., Taskin, S., Schaltz, E., & Acar Demirci, B. (2024) · Journal of Energy Storage · doi:10.1016/j.est.2024.111435 · Cited by 312
Metadata
- Authors
- How, D. N. T., Hannan, M. A., Lipu, M. S. H., Sahari, K. S. M., Ker, P. J., & Muttaqi, K. M.
- Affiliations
- Universiti Tenaga Nasional (MY)
- National University of Malaysia (MY)
- University of Wollongong (AU)
- Venue
- IEEE Transactions on Industry Applications
- Published
- 2020-09
- Volume
- 56
- Issue
- 5
- Pages
- 5565-5574
- ISSN
- 0093-9994 (ISSN-L)
- 1939-9367
- OpenAlex
- W3035785571
- Cited by
- 337
- References
- 47
- Citations by year
- 2026: 32 · 2025: 69 · 2024: 82 · 2023: 63 · 2022: 57 · 2021: 29 · 2020: 5
- FWCI
- 14.24
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Industry Applications (publishedVersion)
- Funders
- Ministry of Higher Education, Malaysia
- Universiti Tenaga Nasional (20190101LRGS)
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Battery Modeling and Management
- Physical Sciences › Engineering › Automotive Engineering › Electric and Hybrid Vehicle Technologies
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advancements in Battery Materials
- Keywords
- state of charge estimation, lithium-ion batteries, electric vehicles, battery management systems, deep neural network, hidden layer number, battery degradation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.