Version 1
: Received: 11 April 2023 / Approved: 11 April 2023 / Online: 11 April 2023 (05:41:54 CEST)
Version 2
: Received: 15 April 2023 / Approved: 17 April 2023 / Online: 17 April 2023 (04:30:34 CEST)
Version 3
: Received: 18 April 2023 / Approved: 18 April 2023 / Online: 18 April 2023 (04:19:53 CEST)
Version 4
: Received: 18 April 2023 / Approved: 19 April 2023 / Online: 19 April 2023 (03:34:32 CEST)
How to cite:
Aryal, A.; Hossain, J.; Khalilpour, K. State of Charge Estimation Using Deep Neural Networks for Lithium-Ion Batteries. Preprints2023, 2023040203. https://doi.org/10.20944/preprints202304.0203.v4
Aryal, A.; Hossain, J.; Khalilpour, K. State of Charge Estimation Using Deep Neural Networks for Lithium-Ion Batteries. Preprints 2023, 2023040203. https://doi.org/10.20944/preprints202304.0203.v4
Aryal, A.; Hossain, J.; Khalilpour, K. State of Charge Estimation Using Deep Neural Networks for Lithium-Ion Batteries. Preprints2023, 2023040203. https://doi.org/10.20944/preprints202304.0203.v4
APA Style
Aryal, A., Hossain, J., & Khalilpour, K. (2023). State of Charge Estimation Using Deep Neural Networks for Lithium-Ion Batteries. Preprints. https://doi.org/10.20944/preprints202304.0203.v4
Chicago/Turabian Style
Aryal, A., Jahangir Hossain and Kaveh Khalilpour. 2023 "State of Charge Estimation Using Deep Neural Networks for Lithium-Ion Batteries" Preprints. https://doi.org/10.20944/preprints202304.0203.v4
Abstract
This paper presents an improved SOC estimation method for lithium ion batteries in Electric Vehicles using Bayesian optimized feedforward network. This innovative bayesian optimized neural network method attempts to minimize a scalar objective function by extracting hyperpa-rameters (hidden neurons in both layers) using a surrogate model. Furthemore, the hyperparameters are built and data samples are trained and validated. The performance of the proposed deep learning neural network is evaluated. Two reasonable size data samples are ex-tracted from Panasonic 18650PF Li-ion Mendeley datasets that are used for training and valida-tion. RNN and LSTM neural network algorithms offer the common core property of retaining past information and/or hidden states for better SOC estimation. However, the feature of this pro-posed method is the inclusion of Bayesian optimization that chooses optimal double layer hidden neurons. Analysis of results shows that Bayesian optimized feedforward algorithm with average MAPE (0.20%) is the lowest and is the best selection compared with average MAPE for other five deep learning algorithms. In the last quarter of fuel gauge, where fuel anxiety is severe, feed-forward with Bayesian Optimization algorithm is still the best selection (with MAPE of 0.64%).
Keywords
Electric Vehicles; Battery Management System; Lithium-ion batteries; Deep Learning
Subject
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Commenter: Amit Aryal
Commenter's Conflict of Interests: Author