Capacity Prediction and Validation of Lithium-Ion Batteries Based on Long Short-Term Memory Recurrent Neural Network
Open Access
- 22 September 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 172783-172798
Abstract
Capacity prediction of lithium-ion batteries represents an important function of battery management systems. Conventional machine learning-based methods for capacity prediction are inefficient to learn long-term dependencies during capacity degradations. This paper investigates the deep learning method for lithium-ion battery’s capacity prediction based on long short-term memory recurrent neural network, which is employed to capture the latent long-term dependence of degraded capacity. The neural network is adaptively optimized by the Adam optimization algorithm, and the dropout technique is exploited to prevent overfitting. Based on the offline cycling aging data of batteries, the capacity prediction performance is validated and evaluated. The experimental results demonstrate that the proposed algorithm can accurately track the nonlinear degradation trend of capacity within the whole lifespan with a maximum error of only 2.84%.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFB0104000)
- National Natural Science Foundation of China (61763021)
- EU-funded Marie Skłodowska-Curie Individual Fellowships Project (845102-HOEMEV-H2020-MSCA-IF-2018)
This publication has 34 references indexed in Scilit:
- Analysis and Optimization of Star-Structured Switched-Capacitor Equalizers for Series-Connected Battery StringsIEEE Transactions on Power Electronics, 2017
- State-of-Health Estimation for Lithium-Ion Batteries Based on the Multi-Island Genetic Algorithm and the Gaussian Process RegressionIEEE Access, 2017
- A multi-timescale estimator for battery state of charge and capacity dual estimation based on an online identified modelApplied Energy, 2017
- Efficient Online Learning Algorithms Based on LSTM Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2017
- A Lithium-Ion Battery-in-the-Loop Approach to Test and Validate Multiscale Dual H Infinity Filters for State-of-Charge and Capacity EstimationIEEE Transactions on Power Electronics, 2017
- Adaptive State of Charge Estimation of Lithium-Ion Batteries With Parameter and Thermal UncertaintiesIEEE Transactions on Control Systems Technology, 2016
- A novel multistage Support Vector Machine based approach for Li ion battery remaining useful life estimationApplied Energy, 2015
- Show and tell: A neural image caption generator2015
- The effects of electrode thickness on the electrochemical and thermal characteristics of lithium ion batteryApplied Energy, 2015
- Remaining capacity estimation of Li-ion batteries based on temperature sample entropy and particle filterJournal of Power Sources, 2014