IIP-Mixer:Intra-Inter Patch Mixing Architecture for Battery Remaining Useful Life Prediction (2403.18379v1)
Abstract: Accurately estimating the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for maintaining the safe and stable operation of rechargeable battery management systems. However, this task is often challenging due to the complex temporal dynamics involved. Recently, attention-based networks, such as Transformers and Informer, have been the popular architecture in time series forecasting. Despite their effectiveness, these models with abundant parameters necessitate substantial training time to unravel temporal patterns. To tackle these challenges, we propose a simple MLP-Mixer-based architecture named 'Intra-Inter Patch Mixer' (IIP-Mixer), which is an architecture based exclusively on multi-layer perceptrons (MLPs), extracting information by mixing operations along both intra-patch and inter-patch dimensions for battery RUL prediction. The proposed IIP-Mixer comprises parallel dual-head mixer layers: the intra-patch mixing MLP, capturing local temporal patterns in the short-term period, and the inter-patch mixing MLP, capturing global temporal patterns in the long-term period. Notably, to address the varying importance of features in RUL prediction, we introduce a weighted loss function in the MLP-Mixer-based architecture, marking the first time such an approach has been employed. Our experiments demonstrate that IIP-Mixer achieves competitive performance in battery RUL prediction, outperforming other popular time-series frameworks
- “A Review of Expert Hybrid and Co-Estimation Techniques for SOH and RUL Estimation in Battery Management System with Electric Vehicle Application” In Expert Systems with Applications Elsevier, 2024, pp. 123123
- “Remaining useful life prediction of lithium-ion batteries based on Monte Carlo Dropout and gated recurrent unit” In Energy Reports 7 Elsevier, 2021, pp. 2862–2871
- “A hybrid ensemble deep learning approach for early prediction of battery remaining useful life” In IEEE/CAA Journal of Automatica Sinica 10.1 IEEE, 2023, pp. 177–187
- “Review of models for predicting the cycling performance of lithium-ion batteries” In Journal of power sources 156.2 Elsevier, 2006, pp. 620–628
- Paulo Kemper, Shengbo Eben Li and Dongsuk Kum “Simplification of pseudo two-dimensional battery model using dynamic profile of lithium concentration” In Journal of Power Sources 286 Elsevier, 2015, pp. 510–525
- “A data-driven method with mode decomposition mechanism for remaining useful life prediction of lithium-ion batteries” In IEEE Transactions on Power Electronics 37.11 IEEE, 2022, pp. 13684–13695
- “Improved anti-noise adaptive long short-term memory neural network modeling for the robust remaining useful life prediction of lithium-ion batteries” In Reliability Engineering & System Safety 230 Elsevier, 2023, pp. 108920
- “A data-model interactive remaining useful life prediction approach of lithium-ion batteries based on PF-BiGRU-TSAM” In IEEE Transactions on Industrial Informatics IEEE, 2023
- Daoquan Chen, Weicong Hong and Xiuze Zhou “Transformer network for remaining useful life prediction of lithium-ion batteries” In Ieee Access 10 IEEE, 2022, pp. 19621–19628
- “Prediction with time-series mixer for the S&P500 index” In 2023 IEEE 39th International Conference on Data Engineering Workshops (ICDEW), 2023, pp. 20–27 IEEE
- “Are transformers effective for time series forecasting?” In Proceedings of the AAAI conference on artificial intelligence 37.9, 2023, pp. 11121–11128
- “State of health and remaining useful life prediction of lithium-ion batteries with conditional graph convolutional network” In Expert Systems with Applications 238 Elsevier, 2024, pp. 122041
- “Mlp-mixer: An all-mlp architecture for vision” In Advances in neural information processing systems 34, 2021, pp. 24261–24272
- Junyuan Liang, Hui Liu and Ning-Cong Xiao “A hybrid approach based on neural network and double exponential model for remaining useful life prediction” In Expert Systems with Applications Elsevier, 2024, pp. 123563
- Ji Wu, Chenbin Zhang and Zonghai Chen “An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks” In Applied energy 173 Elsevier, 2016, pp. 134–140
- Ilya Sutskever, Oriol Vinyals and Quoc V Le “Sequence to sequence learning with neural networks” In Advances in neural information processing systems 27, 2014
- “Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries” In IEEE Transactions on Vehicular Technology 67.7 IEEE, 2018, pp. 5695–5705
- “A dual-LSTM framework combining change point detection and remaining useful life prediction” In Reliability Engineering & System Safety 205 Elsevier, 2021, pp. 107257
- “Attention is all you need” In Advances in neural information processing systems 30, 2017
- “Tsmixer: An all-mlp architecture for time series forecasting” In arXiv preprint arXiv:2303.06053, 2023
- “Feature importance measures from random forest regressor using near-infrared spectra for predicting carbonization characteristics of kraft lignin-derived hydrochar” In Journal of Wood Science 69.1 Springer, 2023, pp. 1
- Zeying Gong, Yujin Tang and Junwei Liang “Patchmixer: A patch-mixing architecture for long-term time series forecasting” In arXiv preprint arXiv: 2310.00655, 2023
- “Informer: Beyond efficient transformer for long sequence time-series forecasting” In Proceedings of the AAAI conference on artificial intelligence 35.12, 2021, pp. 11106–11115
- “A method for capacity prediction of lithium-ion batteries under small sample conditions” In Energy 238 Elsevier, 2022, pp. 122094
- Guangzai Ye (1 paper)
- Li Feng (87 papers)
- Jianlan Guo (2 papers)
- Yuqiang Chen (10 papers)