A compact unified methodology via a recurrent neural network for accurate modeling of lithium-ion battery voltage and state-of-charge

Zhao, Ruxiu; Kollmeyer, Phillip J.; Lorenz, Robert D.; Jahns, T.M.

doi:10.1109/ecce.2017.8096879

Cited by 33 publications

(17 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chemali et al [38], used the data set for the exact SOC prognostic of LIB. An unified approach was developed with a recurrent neural network for exact modelling of Li-ion cell potential and SOC [39].…”

Section: ) Data Set Applicationmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Review of Available Battery Datasets, RUL Prediction Approaches, and Advanced Battery Management

et al. 2021

View full text Add to dashboard Cite

Battery ensures power solutions for many necessary portable devices such as electric vehicles, mobiles, and laptops. Owing to the rapid growth of Li-ion battery users, unwanted incidents involving Li-ion batteries have also increased to some extent. In particular, the sudden breakdown of industrial and lightweight machinery due to battery failure causes a substantial economic loss for the industry. Consequently, battery state estimation, management system, and estimation of the remaining useful life (RUL) have become a topic of interest for researchers. Considering this, appropriate battery data acquisition and proper information on available battery data sets may require. This review paper is mainly focused on three parts. The first one is battery data acquisitions with commercially and freely available Li-ion battery data set information. The second is the estimation of the states of battery with the battery management system. And third is battery RUL estimation. Various RUL prognostic methods applied for Li-ion batteries are classified, discussed, and reviewed based on their essential performance parameters. Information on commercially and publicly available data sets of many battery models under various conditions is also reviewed. Various battery states are reviewed considering advanced battery management systems. To that end, a comparative study of Li-ion battery RUL prediction is provided together with the investigation of various RUL prediction algorithms and mathematical modelling.INDEX TERMS Battery datasets, battery data repository, remaining useful life (RUL), battery management, li-ion battery, RUL prediction methods.

show abstract

Section: ) Data Set Applicationmentioning

confidence: 99%

“…In [39], the authors analysed the Lithium-ion cell model operation for automotive operating cycles with Electrochemical Impedance Spectroscopy (EIS) parameterization and the current pulse. Additionally, a Battery-Electric Light-Duty [40], [41] using these data sets.…”

Section: ) Data Set Applicationmentioning

confidence: 99%

A Comprehensive Review of Available Battery Datasets, RUL Prediction Approaches, and Advanced Battery Management

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The reset gate controls how much the candidate state depends on the previous hidden state. W z , W h , W r are the weights matrices for update gate, candidate state, and reset gate 21 …”

Section: Gated Recurrent Neural Network—grumentioning

confidence: 99%

Online state of health prediction method for lithium‐ion batteries, based on gated recurrent unit neural networks

2020

View full text Add to dashboard Cite

Summary Online state of health (SOH) prediction of lithium‐ion batteries remains a very important problem in assessing the safety and reliability of battery‐powered systems. Deep learning techniques based on recurrent neural networks with memory, such as the long short‐term memory (LSTM) and gated recurrent unit (GRU), have very promising advantages, when compared to other SOH estimation algorithms. This work addresses the battery SOH prediction based on GRU. A complete BMS is presented along with the internal structure and configuration parameters. The neural network was highly optimized by adaptive moment estimation (Adam) algorithm. Experimental data show very good estimation results for different temperature values, not only at room value. Comparisons performed against other relevant estimation methods highlight the performance of the recursive neural network algorithms such as GRU and LSTM, with the exception of the battery regeneration points. Compared to LSTM, the GRU algorithm gives slightly higher estimation errors, but within similar prediction error range, while needing significantly fewer parameters (about 25% fewer), thus making it a very suitable candidate for embedded implementations.

show abstract

“…These studies applied machine learning on features extracted from the charging or discharging curve to predict discharge capacity [11], remaining useful life [12], and abrupt capacity decays [13,14]. Innovations in extracting features from charge/discharge curves [15] and machine learning approaches for modelling time-series data [16,17] have enabled significant improvements in the accuracy of predictions. Going beyond charging and discharging curves, approaches such as electrochemical impedance spectroscopy (EIS) [18] and acoustic time-of-flight analysis [19,20] have been used for degradation forecasting.…”

Section: Introductionmentioning

confidence: 99%

Impedance-based forecasting of battery performance amid uneven usage

Jones

Stimming

Lee

2021

Preprint

View full text Add to dashboard Cite

Accurate forecasting of lithium-ion battery performance is important for easing consumer concerns about the safety and reliability of electric vehicles. Most research on battery health prognostics focuses on the R&D setting where cells are subjected to the same usage patterns, yet in practice there is great variability in use across cells and cycles, making forecasting much more challenging. Here, we address this challenge by combining electrochemical impedance spectroscopy (EIS), a non-invasive measurement of battery state, with probabilistic machine learning. We generated a dataset of 40 commercial lithium-ion coin cells cycled under multistage constant current charging/discharging, with currents randomly changed between cycles to emulate realistic use patterns. We show that future discharge capacities can be predicted with calibrated uncertainties, given the future cycling protocol and a single EIS measurement made just before charging, and without any knowledge of usage history. Our method is data-efficient, requiring just eight cells to achieve a test error of less than 10%, and robust to dataset shifts. Our model can forecast well into the future, attaining a test error of less than 10% when projecting 32 cycles ahead. Further, we find that model performance can be boosted by 25% by augmenting EIS with additional features derived from historical capacity-voltage curves. Our results suggest that battery health is better quantified by a multidimensional vector rather than a scalar State of Health, thus deriving informative electrochemical `biomarkers' in tandem with machine learning is key to predictive battery management and control.

show abstract

A compact unified methodology via a recurrent neural network for accurate modeling of lithium-ion battery voltage and state-of-charge

Cited by 33 publications

References 10 publications

A Comprehensive Review of Available Battery Datasets, RUL Prediction Approaches, and Advanced Battery Management

A Comprehensive Review of Available Battery Datasets, RUL Prediction Approaches, and Advanced Battery Management

Online state of health prediction method for lithium‐ion batteries, based on gated recurrent unit neural networks

Impedance-based forecasting of battery performance amid uneven usage

Contact Info

Product

Resources

About