Deep convolutional neural network based closed-loop SOC estimation for lithium-ion batteries in hierarchical scenarios

Wang, Qiao; Ye, Min; Wei, Meng; Lian, Gaoqi; Li, Yan

doi:10.1016/j.energy.2022.125718

Cited by 14 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One such example is the use of convolutional neural network (CNN). Innovative research has centered on crafting a universal SOC estimator capable of addressing variations in battery type and sensor noise [34]. A unique closed-loop paradigm, employing a deep convolutional neural network (DCNN), was put forward in this study, employing transfer learning and pruning techniques for swift adaptability in distinct scenarios.…”

Section: Current Methods For Soc Estimationmentioning

confidence: 99%

Spatial-Temporal Self-Attention Transformer Networks for Battery State of Charge Estimation

et al. 2023

View full text Add to dashboard Cite

Over the past ten years, breakthroughs in battery technology have dramatically propelled the evolution of electric vehicle (EV) technologies. For EV applications, accurately estimating the state-of-charge (SOC) is critical for ensuring safe operation and prolonging the lifespan of batteries, particularly under complex loading scenarios. Despite progress in this area, modeling and forecasting the evaluation of multiphysics and multiscale electrochemical systems under realistic conditions using first-principles and atomistic calculations remains challenging. This study proposes a solution by designing a specialized Transformer-based network architecture, called Bidirectional Encoder Representations from Transformers for Batteries (BERTtery), which only uses time-resolved battery data (i.e., current, voltage, and temperature) as an input to estimate SOC. To enhance the Transformer model’s generalization, it was trained and tested under a wide range of working conditions, including diverse aging conditions (ranging from 100% to 80% of the nominal capacity) and varying temperature windows (from 35 °C to −5 °C). To ensure the model’s effectiveness, a rigorous test of its performance was conducted at the pack level, which allows for the translation of cell-level predictions into real-life problems with hundreds of cells in-series conditions possible. The best models achieve a root mean square error (RMSE) of less than 0.5 test error and approximately 0.1% average percentage error (APE), with maximum absolute errors (MAE) of 2% on the test dataset, accurately estimating SOC under dynamic operating and aging conditions with widely varying operational profiles. These results demonstrate the power of the self-attention Transformer-based model to predict the behavior of complex multiphysics and multiscale battery systems.

show abstract

Section: Current Methods For Soc Estimationmentioning

confidence: 99%

Spatial-Temporal Self-Attention Transformer Networks for Battery State of Charge Estimation

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This is particularly critical for the second-hand EV market as battery state of health determines the price of the vehicle. Machine learning-based SoC estimation plays a critical role in assessing and preserving battery health [115]. The related health monitoring applications are presented below.…”

Section: Battery Health Monitoringmentioning

confidence: 99%

Advancing State of Charge Management in Electric Vehicles With Machine Learning: A Technological Review

Mousaei,

Naderi,

Bayram

2024

IEEE Access

View full text Add to dashboard Cite

As the share of electric vehicles increases, electric vehicles are exposed to broader of driving conditions (e.g., extreme weather), which reduce the performance and driving ranges of electric vehicles below their nameplate rating. To ensure customer confidence and support steady growth in electric vehicle adoption rates, accurate estimation of battery state of charge and maintaining battery state of health through optimal charge/discharge decisions are critical. Recently, vehicle manufacturers have begun to employ machine learning techniques to improve state-of-charge management to better inform drivers about both short-term (state of charge) and long-term (state of health) performance of their vehicles. This comprehensive review article explores the intersection of machine learning and state of charge management in electric vehicles. Recognizing the critical importance of state of charge in optimizing electric vehicle performance, the article starts by evaluating traditional state of charge estimation methods. Subsequently, it delves into the transformative impact of machine learning techniques and associated algorithms on state of charge management. Through the lens of various case studies, this article demonstrates how machine learning-based state of charge estimation empowers electric vehicles to make informed and dynamic energy usage decisions, enhancing efficiency and extending battery life. The challenges of data availability, model interpretability, and real-time processing constraints are acknowledged as impediments to the widespread adoption of machine learning techniques. Despite these challenges, the future outlook for machine learning in state of charge management appears promising, with emerging trends such as deep learning and reinforcement learning poised to refine state of charge estimation accuracy. Moreover, this study sheds light on the transformative potential of machine learning in enhancing state of charge management efficiency and effectiveness for electric vehicles, offering critical insights.. Machine learning emerges as a game-changing force in state of charge management for electric vehicles, paving the way for intelligent and adaptive vehicles that are both environmentally friendly and efficient. This evolving field invites further research and development, making it a vital and exciting area within the automotive industry.

show abstract

“…Various methods have been used for battery SOH estimation, such as the support vector machines (SVM) 25 , random forests (RF) 26 , long short term memory (LSTM) network 27 , and convolutional neural networks (CNN) 28 . Extracting correlation features, including peak area, peak position, and peak width from incremental capacity curves for estimating battery SOH is considered as mature technique [29][30][31] . However, most of these features are collected on the basis of complete charge and discharge curves, which involves high frequency data acquisition to obtain the incremental capacity and differential voltage curves, processing of large amount of data, imposes a certain burden on battery management system 32 .…”

Section: Introductionmentioning

confidence: 99%

Efficient estimating and clustering Lithium-ion batteries with a deep-learning approach

He,

Sun,

et al. 2024

Preprint

View full text Add to dashboard Cite

Identifying the state of health (SOH) of batteries is critical for estimating batteries from unknown states or grouping retired batteries for secondary utilization to promote recycling sustainability. However, batteries perform distinct capacity fading behaviours in real scenarios and service activities. The energy conversion process is reflected by electrical signals, but proceeds via electrochemical reactions associated with temperature and strain variation. Herein, we develop a deep-learning framework for rapid, accurate, and transferable estimation of battery SOH. This framework incorporates deep neural networks with interconnected electrochemical, mechanical and thermal features as expanded segments. Our model delivers optimal accuracy with mean absolute error (MAE) of 0.519% and root mean square error (RMSE) of 0.795% based on combined features. The model is valid in various conditions and is capable of realizing rapid and accurate prediction merely with one previous cycle. More importantly, the well-trained material domain could be transferred to other electrode systems with few samples. Our work highlights the value of relevant features on battery SOH estimation, and provides guidance on efficient and reliable classification of batteries in the sustainable cycle.

show abstract

Deep convolutional neural network based closed-loop SOC estimation for lithium-ion batteries in hierarchical scenarios

Cited by 14 publications

References 40 publications

Spatial-Temporal Self-Attention Transformer Networks for Battery State of Charge Estimation

Spatial-Temporal Self-Attention Transformer Networks for Battery State of Charge Estimation

Advancing State of Charge Management in Electric Vehicles With Machine Learning: A Technological Review

Efficient estimating and clustering Lithium-ion batteries with a deep-learning approach

Contact Info

Product

Resources

About