Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards a Probabilistic Fusion Approach for Robust Battery Prognostics (2405.15292v1)

Published 24 May 2024 in cs.LG and cs.AI

Abstract: Batteries are a key enabling technology for the decarbonization of transport and energy sectors. The safe and reliable operation of batteries is crucial for battery-powered systems. In this direction, the development of accurate and robust battery state-of-health prognostics models can unlock the potential of autonomous systems for complex, remote and reliable operations. The combination of Neural Networks, Bayesian modelling concepts and ensemble learning strategies, form a valuable prognostics framework to combine uncertainty in a robust and accurate manner. Accordingly, this paper introduces a Bayesian ensemble learning approach to predict the capacity depletion of lithium-ion batteries. The approach accurately predicts the capacity fade and quantifies the uncertainty associated with battery design and degradation processes. The proposed Bayesian ensemble methodology employs a stacking technique, integrating multiple Bayesian neural networks (BNNs) as base learners, which have been trained on data diversity. The proposed method has been validated using a battery aging dataset collected by the NASA Ames Prognostics Center of Excellence. Obtained results demonstrate the improved accuracy and robustness of the proposed probabilistic fusion approach with respect to (i) a single BNN model and (ii) a classical stacking strategy based on different BNNs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. \APACrefYearMonthDay2021\APACmonth12. \BBOQ\APACrefatitleA Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges A review of uncertainty quantification in deep learning: Techniques, applications and challenges.\BBCQ \APACjournalVolNumPagesInformation Fusion76243–297. {APACrefDOI} 10.1016/j.inffus.2021.05.008 \PrintBackRefs\CurrentBib
  2. \APACrefYearMonthDay2023\APACmonth11. \BBOQ\APACrefatitleGradient Boosting Bayesian Neural Networks via Langevin MCMC Gradient boosting Bayesian neural networks via Langevin MCMC.\BBCQ \APACjournalVolNumPagesNeurocomputing558126726. {APACrefDOI} 10.1016/j.neucom.2023.126726 \PrintBackRefs\CurrentBib
  3. \APACinsertmetastarbarrett1974{APACrefauthors}Barrett, J\BPBIP.  \APACrefYearMonthDay1974. \BBOQ\APACrefatitleThe coefficient of determination—some limitations The coefficient of determination—some limitations.\BBCQ \APACjournalVolNumPagesThe American Statistician28119–20. \PrintBackRefs\CurrentBib
  4. \APACrefYearMonthDay2015. \BBOQ\APACrefatitleWeight Uncertainty in Neural Network Weight uncertainty in neural network.\BBCQ \BIn F. Bach \BBA D. Blei (\BEDS), \APACrefbtitleInternational conference on machine learning International conference on machine learning (\BVOL 37, \BPGS 1613–1622). \APACaddressPublisherLille, FrancePMLR. \PrintBackRefs\CurrentBib
  5. \APACrefYearMonthDay2000. \BBOQ\APACrefatitleNegative log-likelihood and statistical hypothesis testing as the basis of model selection in IDEAs Negative log-likelihood and statistical hypothesis testing as the basis of model selection in ideas.\BBCQ \BIn \APACrefbtitleProceedings of the Tenth Dutch–Netherlands Conference on Machine Learning. Tilburg University. Proceedings of the tenth dutch–netherlands conference on machine learning. tilburg university. \PrintBackRefs\CurrentBib
  6. \APACrefYearMonthDay2024\APACmonth01. \BBOQ\APACrefatitlePredictive Health Assessment for Lithium-Ion Batteries with Probabilistic Degradation Prediction and Accelerating Aging Detection Predictive health assessment for lithium-ion batteries with probabilistic degradation prediction and accelerating aging detection.\BBCQ \APACjournalVolNumPagesReliability Engineering & System Safety241109603. {APACrefDOI} 10.1016/j.ress.2023.109603 \PrintBackRefs\CurrentBib
  7. \APACrefYearMonthDay2021. \BBOQ\APACrefatitleUncertainty Toolbox: an Open-Source Library for Assessing, Visualizing, and Improving Uncertainty Quantification Uncertainty toolbox: an open-source library for assessing, visualizing, and improving uncertainty quantification.\BBCQ \APACjournalVolNumPagesarXiv preprint arXiv:2109.10254. \PrintBackRefs\CurrentBib
  8. \APACrefYearMonthDay2019\APACmonth06. \BBOQ\APACrefatitleAn Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval.\BBCQ \APACjournalVolNumPagesThe Astronomical Journal158133. {APACrefDOI} 10.3847/1538-3881/ab2390 \PrintBackRefs\CurrentBib
  9. \APACrefYearMonthDay2023\APACmonth02. \BBOQ\APACrefatitleBayesian Fusion: Scalable Unification of Distributed Statistical Analyses Bayesian fusion: Scalable unification of distributed statistical analyses.\BBCQ \APACjournalVolNumPagesJournal of the Royal Statistical Society Series B: Statistical Methodology85184–107. {APACrefDOI} 10.1093/jrsssb/qkac007 \PrintBackRefs\CurrentBib
  10. \APACrefYearMonthDay2017\APACmonth11. \APACrefbtitleTensorFlow Distributions TensorFlow Distributions (\BNUM arXiv:1711.10604). \APACaddressPublisherarXiv. \PrintBackRefs\CurrentBib
  11. \APACrefYearMonthDay2017. \BBOQ\APACrefatitleA Bayesian posterior predictive framework for weighting ensemble regional climate models A bayesian posterior predictive framework for weighting ensemble regional climate models.\BBCQ \APACjournalVolNumPagesGeoscientific Model Development1062321–2332. \PrintBackRefs\CurrentBib
  12. \APACrefYearMonthDay2005. \BBOQ\APACrefatitleCalibrated Probabilistic Forecasting Using Ensemble Model Output Statistics and Minimum CRPS Estimation Calibrated probabilistic forecasting using ensemble model output statistics and minimum CRPS estimation.\BBCQ \APACjournalVolNumPagesMonthly Weather Review13351098–1118. {APACrefDOI} 10.1175/MWR2904.1 \PrintBackRefs\CurrentBib
  13. \APACrefYearMonthDay2015. \BBOQ\APACrefatitleOn uncertainty quantification of lithium-ion batteries: Application to an LiC6/LiCoO2 cell On uncertainty quantification of lithium-ion batteries: Application to an lic6/licoo2 cell.\BBCQ \APACjournalVolNumPagesJournal of Power Sources300507–524. \PrintBackRefs\CurrentBib
  14. \APACinsertmetastarhodson2022{APACrefauthors}Hodson, T\BPBIO.  \APACrefYearMonthDay2022. \BBOQ\APACrefatitleRoot mean square error (RMSE) or mean absolute error (MAE): When to use them or not Root mean square error (rmse) or mean absolute error (mae): When to use them or not.\BBCQ \APACjournalVolNumPagesGeoscientific Model Development Discussions20221–10. \PrintBackRefs\CurrentBib
  15. \APACrefYearMonthDay2022\APACmonth06. \BBOQ\APACrefatitleStatistical Model Calibration and Design Optimization under Aleatory and Epistemic Uncertainty Statistical model calibration and design optimization under aleatory and epistemic uncertainty.\BBCQ \APACjournalVolNumPagesReliability Engineering & System Safety222108428. {APACrefDOI} 10.1016/j.ress.2022.108428 \PrintBackRefs\CurrentBib
  16. \APACrefYearMonthDay2018\APACmonth07. \BBOQ\APACrefatitleAccurate Uncertainties for Deep Learning Using Calibrated Regression Accurate uncertainties for deep learning using calibrated regression.\BBCQ \BIn J. Dy \BBA A. Krause (\BEDS), \APACrefbtitleProceedings of the 35th International Conference on Machine Learning Proceedings of the 35th international conference on machine learning (\BVOL 80, \BPGS 2796–2804). \APACaddressPublisherPMLR. \PrintBackRefs\CurrentBib
  17. \APACrefYearMonthDay1996. \BBOQ\APACrefatitleCombining estimates in regression and classification Combining estimates in regression and classification.\BBCQ \APACjournalVolNumPagesJournal of the American Statistical Association914361641–1650. \PrintBackRefs\CurrentBib
  18. \APACrefYearMonthDay2023. \BBOQ\APACrefatitleA Convolutional Neural Network Model for SOH Estimation of Li-ion Batteries with Physical Interpretability A convolutional neural network model for SOH estimation of Li-ion batteries with physical interpretability.\BBCQ \APACjournalVolNumPagesMechanical Systems and Signal Processing188110004. {APACrefDOI} 10.1016/j.ymssp.2022.110004 \PrintBackRefs\CurrentBib
  19. \APACrefYearMonthDay2023\APACmonth05. \BBOQ\APACrefatitleA Novel Remaining Useful Life Prediction Method for Lithium-Ion Battery Based on Long Short-Term Memory Network Optimized by Improved Sparrow Search Algorithm A novel remaining useful life prediction method for lithium-ion battery based on long short-term memory network optimized by improved sparrow search algorithm.\BBCQ \APACjournalVolNumPagesJournal of Energy Storage61106645. {APACrefDOI} 10.1016/j.est.2023.106645 \PrintBackRefs\CurrentBib
  20. \APACrefYearMonthDay2021. \BBOQ\APACrefatitleDiversity Matters When Learning from Ensembles Diversity matters when learning from ensembles.\BBCQ \BIn M. Ranzato, A. Beygelzimer, Y. Dauphin, P. Liang\BCBL \BBA J\BPBIW. Vaughan (\BEDS), \APACrefbtitleAdvances in Neural Information Processing Systems Advances in neural information processing systems (\BVOL 34, \BPGS 8367–8377). \APACaddressPublisherCurran Associates, Inc. \PrintBackRefs\CurrentBib
  21. \APACrefYearMonthDay2023. \BBOQ\APACrefatitleUncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial.\BBCQ \APACjournalVolNumPagesMechanical Systems and Signal Processing205110796. {APACrefDOI} 10.1016/j.ymssp.2023.110796 \PrintBackRefs\CurrentBib
  22. \APACrefYearMonthDay2007. \BBOQ\APACrefatitleNASA Ames prognostics data repository Nasa ames prognostics data repository.\BBCQ \APACjournalVolNumPagesNASA Ames, Moffett Field, CA, USA. \PrintBackRefs\CurrentBib
  23. \APACrefYearMonthDay2022. \BBOQ\APACrefatitleState of Health Estimation and Remaining Useful Life Assessment of Lithium-Ion Batteries: A Comparative Study State of health estimation and remaining useful life assessment of lithium-ion batteries: A comparative study.\BBCQ \APACjournalVolNumPagesJournal of Energy Storage51104520. {APACrefDOI} 10.1016/j.est.2022.104520 \PrintBackRefs\CurrentBib
  24. \APACrefYearMonthDay2020\APACmonth05. \BBOQ\APACrefatitleMethods for Comparing Uncertainty Quantifications for Material Property Predictions Methods for comparing uncertainty quantifications for material property predictions.\BBCQ \APACjournalVolNumPagesMachine Learning: Science and Technology12025006. {APACrefDOI} 10.1088/2632-2153/ab7e1a \PrintBackRefs\CurrentBib
  25. \APACrefYearMonthDay2021\APACmonth11. \BBOQ\APACrefatitleData-Driven State of Health Modelling—A Review of State of the Art and Reflections on Applications for Maritime Battery Systems Data-driven state of health modelling—A review of state of the art and reflections on applications for maritime battery systems.\BBCQ \APACjournalVolNumPagesJournal of Energy Storage43103158. {APACrefDOI} 10.1016/j.est.2021.103158 \PrintBackRefs\CurrentBib
  26. \APACrefYearMonthDay2022. \BBOQ\APACrefatitleInternal short circuit and thermal runaway evolution mechanism of fresh and retired lithium-ion batteries with LiFePO4 cathode during overcharge Internal short circuit and thermal runaway evolution mechanism of fresh and retired lithium-ion batteries with lifepo4 cathode during overcharge.\BBCQ \APACjournalVolNumPagesApplied Energy328120224. \PrintBackRefs\CurrentBib
  27. \APACrefYearMonthDay2023\APACmonth02. \BBOQ\APACrefatitlePrediction of State of Health and Remaining Useful Life of Lithium-Ion Battery Using Graph Convolutional Network with Dual Attention Mechanisms Prediction of state of health and remaining useful life of lithium-ion battery using graph convolutional network with dual attention mechanisms.\BBCQ \APACjournalVolNumPagesReliability Engineering & System Safety230108947. {APACrefDOI} 10.1016/j.ress.2022.108947 \PrintBackRefs\CurrentBib
  28. \APACrefYearMonthDay2023. \BBOQ\APACrefatitleState of Health Assessment of Lithium-Ion Batteries Based on Deep Gaussian Process Regression Considering Heterogeneous Features State of health assessment of lithium-ion batteries based on deep gaussian process regression considering heterogeneous features.\BBCQ \APACjournalVolNumPagesJournal of Energy Storage61106797. \PrintBackRefs\CurrentBib
  29. \APACrefYearMonthDay2018\APACmonth09. \BBOQ\APACrefatitleUsing Stacking to Average Bayesian Predictive Distributions (with Discussion) Using Stacking to Average Bayesian Predictive Distributions (with Discussion).\BBCQ \APACjournalVolNumPagesBayesian Analysis133. {APACrefDOI} 10.1214/17-BA1091 \PrintBackRefs\CurrentBib
  30. \APACrefYearMonthDay2018\APACmonth02. \BBOQ\APACrefatitleEstimation of the Continuous Ranked Probability Score with Limited Information and Applications to Ensemble Weather Forecasts Estimation of the Continuous Ranked Probability Score with Limited Information and Applications to Ensemble Weather Forecasts.\BBCQ \APACjournalVolNumPagesMathematical Geosciences502209–234. {APACrefDOI} 10.1007/s11004-017-9709-7 \PrintBackRefs\CurrentBib
  31. \APACrefYearMonthDay2022. \BBOQ\APACrefatitleA Bayesian Mixture Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries A bayesian mixture neural network for remaining useful life prediction of lithium-ion batteries.\BBCQ \APACjournalVolNumPagesIEEE Transactions on Transportation Electrification844708–4721. {APACrefDOI} 10.1109/TTE.2022.3161140 \PrintBackRefs\CurrentBib
  32. \APACrefYearMonthDay2024\APACmonth02. \BBOQ\APACrefatitleReliability Enhancement of State of Health Assessment Model of Lithium-Ion Battery Considering the Uncertainty with Quantile Distribution of Deep Features Reliability enhancement of state of health assessment model of lithium-ion battery considering the uncertainty with quantile distribution of deep features.\BBCQ \APACjournalVolNumPagesReliability Engineering & System Safety110002. {APACrefDOI} 10.1016/j.ress.2024.110002 \PrintBackRefs\CurrentBib
  33. \APACrefYearMonthDay2023. \BBOQ\APACrefatitleState of Health Estimation for Lithium-Ion Batteries Based on Hybrid Attention and Deep Learning State of health estimation for lithium-ion batteries based on hybrid attention and deep learning.\BBCQ \APACjournalVolNumPagesReliability Engineering & System Safety232109066. {APACrefDOI} 10.1016/j.ress.2022.109066 \PrintBackRefs\CurrentBib
  34. \APACrefYearMonthDay2024\APACmonth01. \BBOQ\APACrefatitleInvestigation into Impedance Measurements for Rapid Capacity Estimation of Lithium-ion Batteries in Electric Vehicles Investigation into Impedance Measurements for Rapid Capacity Estimation of Lithium-ion Batteries in Electric Vehicles.\BBCQ \APACjournalVolNumPagesJournal of Dynamics, Monitoring and Diagnostics. {APACrefDOI} 10.37965/jdmd.2024.475 \PrintBackRefs\CurrentBib
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets