A Novel Sequence-to-Sequence Prediction Model for Lithium-Ion Battery Capacity Degradation Based on Improved Particle Swarm Optimization
Open Access
Abstract
The state of health (SOH) evaluation and remaining useful life (RUL) prediction for lithium-ion batteries (LIBs) are crucial for health management. This paper proposes a novel sequence-to-sequence (Seq2Seq) prediction method for LIB capacity degradation based on the gated recurrent unit (GRU) neural network with the attention mechanism. An improved particle swarm optimization (IPSO) algorithm is developed for automatic hyperparameter search of the Seq2Seq model, which speeds up parameter convergence and avoids getting stuck in local optima. Before model training, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm decomposes the capacity degradation sequences. And the intrinsic mode function (IMF) components with the highest correlation are employed to reconstruct the sequences, reducing the influence of noise in the original data. A real-cycle-life data set under fixed operating conditions is employed to validate the superiority and effectiveness of the method. The comparison results demonstrate that the proposed model outperforms traditional GRU and RNN models. The predicted mean absolute percent error (MAPE) in SOH evaluation and RUL prediction can be as low as 0.76% and 0.24%, respectively.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB2502304, 8091B022130, 52222708, 52177206, 51977007)
- Joint Fund of Ministry of Education of China for Equipment Pre-Research (2022YFB2502304, 8091B022130, 52222708, 52177206, 51977007)
- Natural Science Foundation for Young Scientists of Shanxi Province (2022YFB2502304, 8091B022130, 52222708, 52177206, 51977007)
- National Natural Science Foundation of China (2022YFB2502304, 8091B022130, 52222708, 52177206, 51977007)
This publication has 50 references indexed in Scilit:
- An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networksApplied Energy, 2016
- A dynamic capacity degradation model and its applications considering varying load for a large format Li-ion batteryApplied Energy, 2016
- A Survey on Evolutionary Computation Approaches to Feature SelectionIEEE Transactions on Evolutionary Computation, 2015
- Comparison of a particle filter and other state estimation methods for prognostics of lithium-ion batteriesJournal of Power Sources, 2015
- Simplification of pseudo two dimensional battery model using dynamic profile of lithium concentrationJournal of Power Sources, 2015
- Improved complete ensemble EMD: A suitable tool for biomedical signal processingBiomedical Signal Processing and Control, 2014
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Remaining useful life prediction of lithium-ion battery with unscented particle filter techniqueMicroelectronics Reliability, 2013
- A comparative study of equivalent circuit models for Li-ion batteriesJournal of Power Sources, 2012
- A comparative study of Artificial Bee Colony algorithmApplied Mathematics and Computation, 2009