{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T15:09:17Z","timestamp":1777043357680,"version":"3.51.4"},"reference-count":47,"publisher":"Wiley","license":[{"start":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T00:00:00Z","timestamp":1685923200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Pimpri Chinchwad College of Engineering"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Computational Intelligence and Soft Computing"],"published-print":{"date-parts":[[2023,6,5]]},"abstract":"<jats:p>Lithium battery-based electric vehicles (EVs) are gaining global popularity as an alternative to combat the adverse environmental impacts caused by the utilization of fossil fuels. State of charge (SOC) and state of health (SOH) are vital parameters that assess the battery\u2019s remaining charge and overall health. Precise monitoring of SOC and SOH is critical for effectively operating the battery management system (BMS) in a lithium battery. This article presents an experimental study for the artificial intelligence (AI)-based data-driven prediction of lithium battery parameters SOC and SOH with the help of deep learning algorithms such as Long Short-Term Memory (LSTM) and bidirectional LSTM (BiLSTM). We utilized various gradient descent optimization algorithms with adaptive and constant learning rates with other default parameters. Compared between various gradient descent algorithms, the selection of the optimal one depends on mean absolute error (MAE) and root mean squared error (RMSE) accuracy. We developed an LSTM and BiLSTM model with four hidden layers with 128 LSTM or BiLSTM units per hidden layer that use Panasonic 18650PF Li-ion dataset released by NASA to predict SOC and SOH. Our experimental results advise that the selection of the optimal gradient descent algorithm impacts the model\u2019s accuracy. The article also addresses the problem of overfitting in the LSTM\/BiLSTM model. BiLSTM is the best choice to improve the model\u2019s performance but increase the cost. We trained the model with various combinations of parameters and tabulated the accuracies in terms of MAE and RMSE. This optimal LSTM model can predict the SOC of the lithium battery with MAE more minor than 0.0179%, RMSE 0.0227% in the training phase, MAE smaller than 0.695%, and RMSE 0.947% in the testing phase over a 25\u00b0C dataset. The BiLSTM can predict the SOC of the 18650PF lithium battery cell with MAE smaller than 0.012% for training and 0.016% for testing. Similarly, using the Adam optimization algorithm, RMSE for training and testing is 0.326% and 0.454% over a 25\u00b0C dataset, respectively. BiLSTM with an adaptive learning rate can improve performance. To provide an alternative solution to high power consuming processors such as central processing unit (CPU) and graphics processing unit (GPU), we implemented the model on field programmable gate Aarray (FPGA) PYNQ Z2 hardware device. The LSTM model using FPGA performs better.<\/jats:p>","DOI":"10.1155\/2023\/2060808","type":"journal-article","created":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T13:20:08Z","timestamp":1685971208000},"page":"1-18","source":"Crossref","is-referenced-by-count":22,"title":["Accelerating AI-Based Battery Management System\u2019s SOC and SOH on FPGA"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1080-3870","authenticated-orcid":true,"given":"Satyashil D.","family":"Nagarale","sequence":"first","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Pimpri Chinchwad College of Engineering, Savitribai Phule Pune University, Pune, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7369-0645","authenticated-orcid":true,"given":"B. P.","family":"Patil","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Army Institute of Technology, Savitribai Phule Pune University, Pune, India"}]}],"member":"311","reference":[{"issue":"5","key":"1","doi-asserted-by":"crossref","first-page":"4110","DOI":"10.1109\/TVT.2018.2864688","article-title":"Lithium-ion battery health prognosis based on a real battery management system used in electric vehicles","volume":"68","author":"R. Xiong","year":"2019","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"2","volume-title":"Energy and Air Pollution","author":"IEA","year":"2016"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1039\/C8RA05564E"},{"key":"4","article-title":"Bureau of energy efficiency","author":"Bureau of Energy Efficiency","year":"2022"},{"key":"5","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.jpowsour.2014.02.064","article-title":"Critical review of the methods for monitoring lithium-ion batteries in electric and hybrid vehicles","volume":"258","author":"W. Waag","year":"2014","journal-title":"Journal of Power Sources"},{"key":"6","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1016\/j.rser.2017.05.001","article-title":"A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: challenges and recommendations","volume":"78","author":"M. A. Hannan","year":"2017","journal-title":"Renewable and Sustainable Energy Reviews"},{"key":"7","doi-asserted-by":"crossref","DOI":"10.1016\/j.est.2021.102572","article-title":"Classification, summarization and perspectives on the state-of-charge estimation of lithium-ion batteries used in electric vehicles: a critical comprehensive survey","volume":"39","author":"B. Yang","year":"2021","journal-title":"Journal of Energy Storage"},{"key":"8","article-title":"Understanding lstm and its diagrams","author":"S. Yan","year":"2022"},{"issue":"1","key":"9","doi-asserted-by":"crossref","first-page":"21","DOI":"10.3390\/futuretransp1010003","article-title":"Short-term traffic forecasting: an LSTM network for spatial-temporal speed prediction","volume":"1","author":"R. L. Abduljabbar","year":"2021","journal-title":"Future Transp"},{"issue":"3","key":"10","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1145\/2678373.2665678","article-title":"A reconfigurable fabric for accelerating large scale datacenter services","volume":"42","author":"A. Putnam","year":"2014","journal-title":"ACM SIGARCH - Computer Architecture News"},{"issue":"2","key":"11","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MIE.2013.2250351","article-title":"Battery management system: an overview of its application in the smart grid and electric vehicles","volume":"7","author":"H. Rahimi-Eichi","year":"2013","journal-title":"\u2019 in IEEE Industrial Electronics Magazine"},{"key":"12","article-title":"Battery and its management for E-rickshaw","volume-title":"ICDSMLA 2020. Lecture Notes in Electrical Engineering","author":"R. S. Kumar","year":"2022"},{"key":"13","article-title":"Critical Review on Battery Management Systems","author":"K. V. Raj"},{"key":"14","first-page":"2020","article-title":"Toward enhanced state of charge estimation of lithium-ion batteries using optimized machine learning techniques,\u2019 scientific reports","volume-title":"Nature","author":"M. A. Hannan"},{"key":"15","doi-asserted-by":"crossref","DOI":"10.1016\/j.jclepro.2020.124110","article-title":"How, Data-driven state of charge estimation of lithium-ion batteries: algorithms, implementation factors, limitations and future trends","volume":"277","author":"M. S. Hossain Lipu","year":"2020","journal-title":"Journal of Cleaner Production"},{"key":"16","first-page":"754","article-title":"D-ukf based state of health estimation for 18650 type lithium battery","author":"Y. Cai"},{"issue":"10","key":"17","doi-asserted-by":"crossref","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","article-title":"Deep neural networks approach to a speaker and language recognition","volume":"22","author":"F. Richardson","year":"2015","journal-title":"IEEE Signal Processing Letters"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2022.104761"},{"key":"19","article-title":"Data-driven ICA-Bi-LSTM-Combined lithium battery SOH estimation","volume":"2022","author":"H. Sun","year":"2022","journal-title":"Mathematical Problems in Engineering"},{"key":"20","doi-asserted-by":"crossref","first-page":"7064","DOI":"10.3390\/en14217064","article-title":"FPGA implementation of an ant colony optimization based SVM algorithm for state of charge estimation in Li-ion batteries","volume":"14","author":"M. Stighezza","year":"2021","journal-title":"Energies"},{"issue":"8","key":"21","doi-asserted-by":"crossref","first-page":"6730","DOI":"10.1109\/TIE.2017.2787586","article-title":"Long short-term memory networks for accurate state-of-charge estimation of Li-ion batteries","volume":"65","author":"E. Chemali","year":"2018","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932719"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10222828"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.3390\/en12040660"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.3390\/en12091592"},{"key":"26","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1049\/pel2.12283","article-title":"Pure hardware design and implementation on FPGA of an EKF based accelerated SoC estimator for a lithium-ion battery in electric vehicles","volume":"15","author":"S. Jemmali","year":"2022","journal-title":"IET Power Electronics"},{"key":"27","article-title":"An FPGA-Based LSTM Acceleration Engine for Deep Learning Frameworks","author":"D. He","year":"2021"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6626948"},{"key":"29","article-title":"GPU vs. CPU performance in deep learning models","author":"GPU vs. CPU performance in deep learning models","year":"2022"},{"key":"30","article-title":"Why gpu can process image much faster than cpu?","author":"C. Ashish","year":"2021"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-804547-3.00008-5"},{"key":"32","article-title":"Accelerating state-of-charge estimation in FPGA-based battery management systems","author":"X. Tian"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.3390\/ai2040030"},{"key":"34","article-title":"The architecture of LSTM","author":"LSTM","year":"2021"},{"key":"35","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"A. Graves","year":"2015","journal-title":"Neural Networks"},{"issue":"8","key":"36","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S. Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"37","article-title":"PYNQ-Z2 setup guide","author":"PYNQ-Z2","year":"2022"},{"key":"38","article-title":"Panasonic 18650PF Li-ion battery data","volume":"1","author":"P. Kollmeyer","year":"2018","journal-title":"Mendeley Data"},{"key":"39","article-title":"Experiments on Li-ion batteries","author":"NASA Prognostic Center","year":"2022"},{"key":"40","doi-asserted-by":"crossref","first-page":"2408","DOI":"10.3390\/en11092408","article-title":"A study on the open circuit voltage and state of charge characterization of high capacity lithium-ion battery under different temperature","volume":"11","author":"R. Zhang","year":"2018","journal-title":"Energies"},{"key":"41","doi-asserted-by":"crossref","first-page":"53792","DOI":"10.1109\/ACCESS.2019.2912803","article-title":"State-of-charge estimation of lithium-ion batteries via long short-term memory network","volume":"7","author":"F. Yang","year":"2019","journal-title":"IEEE Access"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpowsour.2022.231027"},{"key":"43","author":"Early stopping","year":"2022"},{"issue":"56","key":"44","first-page":"1929","article-title":"A simple way to prevent neural networks from overfitting nitish srivastava","volume":"15","year":"2014","journal-title":"Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov"},{"key":"45","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2022.125375"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.3390\/en14030758"},{"key":"47","doi-asserted-by":"publisher","DOI":"10.3390\/en15155580"}],"container-title":["Applied Computational Intelligence and Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/acisc\/2023\/2060808.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/acisc\/2023\/2060808.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/acisc\/2023\/2060808.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T13:20:28Z","timestamp":1685971228000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/acisc\/2023\/2060808\/"}},"subtitle":[],"editor":[{"given":"Yiming","family":"Tang","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,6,5]]},"references-count":47,"alternative-id":["2060808","2060808"],"URL":"https:\/\/doi.org\/10.1155\/2023\/2060808","relation":{},"ISSN":["1687-9732","1687-9724"],"issn-type":[{"value":"1687-9732","type":"electronic"},{"value":"1687-9724","type":"print"}],"subject":[],"published":{"date-parts":[[2023,6,5]]}}}