Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder
Using lithium-ion (Li-ion) batteries exceeding their useful lifetime may be dangerous for users, and hence, developing an accurate prediction system for batteries that remain useful for life is necessary. Many deep learning models, such as gated recurrent units and long short-term memory (LSTM), hav...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Indonesian Institute of Sciences
2024-07-01
|
| Series: | Journal of Mechatronics, Electrical Power, and Vehicular Technology |
| Subjects: | |
| Online Access: | https://mev.brin.go.id/mev/article/view/905 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849688559568551936 |
|---|---|
| author | Asri Rizki Yuliani Hilman Ferdinandus Pardede Ade Ramdan Vicky Zilvan Raden Sandra Yuwana M Faizal Amri R. Budiarianto Suryo Kusumo Subrata Pramanik |
| author_facet | Asri Rizki Yuliani Hilman Ferdinandus Pardede Ade Ramdan Vicky Zilvan Raden Sandra Yuwana M Faizal Amri R. Budiarianto Suryo Kusumo Subrata Pramanik |
| author_sort | Asri Rizki Yuliani |
| collection | DOAJ |
| description | Using lithium-ion (Li-ion) batteries exceeding their useful lifetime may be dangerous for users, and hence, developing an accurate prediction system for batteries that remain useful for life is necessary. Many deep learning models, such as gated recurrent units and long short-term memory (LSTM), have been proposed for that purpose and have shown good results. However, their performance when dealing with noisy data degrades significantly. This may hamper their implementations for the real world since battery data are prone to noise. In this paper, we develop a robust prediction model in a noisy environment for predicting the remaining useful life (RUL) of Li-ion batteries. We propose a denoising autoencoder (DAE) utilized to remove noise from the data. The DAE is built with convolutional layers instead of traditional feed-forward networks here. We combine DAE with LSTM as the predictor. The proposed framework is evaluated using artificially corrupted battery data provided by National Aeronautics and Space Administration (NASA). The results reveal that our proposed method improves robustness when data contain various types of noise. A comparative study using the traditional approach has also been conducted. Our evaluation shows that convolutional layers are more effective than the traditional approach and that the original composition of the DAE was built using traditional feed-forward networks. DAE with convolutional layers has the best average performance with MSE of 0.61 and is the most consistent model. |
| format | Article |
| id | doaj-art-045065a2412848b69e82bedb7c7174af |
| institution | DOAJ |
| issn | 2087-3379 2088-6985 |
| language | English |
| publishDate | 2024-07-01 |
| publisher | Indonesian Institute of Sciences |
| record_format | Article |
| series | Journal of Mechatronics, Electrical Power, and Vehicular Technology |
| spelling | doaj-art-045065a2412848b69e82bedb7c7174af2025-08-20T03:21:56ZengIndonesian Institute of SciencesJournal of Mechatronics, Electrical Power, and Vehicular Technology2087-33792088-69852024-07-011519310410.55981/j.mev.2024.905345Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoderAsri Rizki Yuliani0Hilman Ferdinandus Pardede1Ade Ramdan2Vicky Zilvan3Raden Sandra Yuwana4M Faizal Amri5R. Budiarianto Suryo Kusumo6Subrata Pramanik7National Research and Innovation Agency (BRIN)National Research and Innovation Agency (BRIN)National Research and Innovation Agency (BRIN)National Research and Innovation Agency (BRIN)National Research and Innovation Agency (BRIN)National Research and Innovation Agency (BRIN)National Research and Innovation Agency (BRIN)University of RajshahiUsing lithium-ion (Li-ion) batteries exceeding their useful lifetime may be dangerous for users, and hence, developing an accurate prediction system for batteries that remain useful for life is necessary. Many deep learning models, such as gated recurrent units and long short-term memory (LSTM), have been proposed for that purpose and have shown good results. However, their performance when dealing with noisy data degrades significantly. This may hamper their implementations for the real world since battery data are prone to noise. In this paper, we develop a robust prediction model in a noisy environment for predicting the remaining useful life (RUL) of Li-ion batteries. We propose a denoising autoencoder (DAE) utilized to remove noise from the data. The DAE is built with convolutional layers instead of traditional feed-forward networks here. We combine DAE with LSTM as the predictor. The proposed framework is evaluated using artificially corrupted battery data provided by National Aeronautics and Space Administration (NASA). The results reveal that our proposed method improves robustness when data contain various types of noise. A comparative study using the traditional approach has also been conducted. Our evaluation shows that convolutional layers are more effective than the traditional approach and that the original composition of the DAE was built using traditional feed-forward networks. DAE with convolutional layers has the best average performance with MSE of 0.61 and is the most consistent model.https://mev.brin.go.id/mev/article/view/905denoising autoencoder (dae)lithium-ion (li-ion) batteryneural networkremaining useful life (rul)system robustness. |
| spellingShingle | Asri Rizki Yuliani Hilman Ferdinandus Pardede Ade Ramdan Vicky Zilvan Raden Sandra Yuwana M Faizal Amri R. Budiarianto Suryo Kusumo Subrata Pramanik Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder Journal of Mechatronics, Electrical Power, and Vehicular Technology denoising autoencoder (dae) lithium-ion (li-ion) battery neural network remaining useful life (rul) system robustness. |
| title | Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder |
| title_full | Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder |
| title_fullStr | Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder |
| title_full_unstemmed | Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder |
| title_short | Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder |
| title_sort | robust remaining useful life prediction of lithium ion battery with convolutional denoising autoencoder |
| topic | denoising autoencoder (dae) lithium-ion (li-ion) battery neural network remaining useful life (rul) system robustness. |
| url | https://mev.brin.go.id/mev/article/view/905 |
| work_keys_str_mv | AT asririzkiyuliani robustremainingusefullifepredictionoflithiumionbatterywithconvolutionaldenoisingautoencoder AT hilmanferdinanduspardede robustremainingusefullifepredictionoflithiumionbatterywithconvolutionaldenoisingautoencoder AT aderamdan robustremainingusefullifepredictionoflithiumionbatterywithconvolutionaldenoisingautoencoder AT vickyzilvan robustremainingusefullifepredictionoflithiumionbatterywithconvolutionaldenoisingautoencoder AT radensandrayuwana robustremainingusefullifepredictionoflithiumionbatterywithconvolutionaldenoisingautoencoder AT mfaizalamri robustremainingusefullifepredictionoflithiumionbatterywithconvolutionaldenoisingautoencoder AT rbudiariantosuryokusumo robustremainingusefullifepredictionoflithiumionbatterywithconvolutionaldenoisingautoencoder AT subratapramanik robustremainingusefullifepredictionoflithiumionbatterywithconvolutionaldenoisingautoencoder |