LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles
Remaining useful life (RUL) prediction of lithium-ion batteries can reduce the risk of battery failure by predicting the end of life. In this paper, we propose novel RUL prediction techniques based on long short-term memory (LSTM). To estimate RUL even in the presence of capacity regeneration phenom...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8967059/ |
| _version_ | 1828908859600666624 |
|---|---|
| author | Kyungnam Park Yohwan Choi Won Jae Choi Hee-Yeon Ryu Hongseok Kim |
| author_facet | Kyungnam Park Yohwan Choi Won Jae Choi Hee-Yeon Ryu Hongseok Kim |
| author_sort | Kyungnam Park |
| collection | DOAJ |
| description | Remaining useful life (RUL) prediction of lithium-ion batteries can reduce the risk of battery failure by predicting the end of life. In this paper, we propose novel RUL prediction techniques based on long short-term memory (LSTM). To estimate RUL even in the presence of capacity regeneration phenomenon, we consider multiple measurable data from battery management system such as voltage, current and temperature charging profiles whose patterns vary as aging. Unlike the traditional LSTM prediction that matches input layer with output layer as one-to-one structure, we leverage many-to-one structure to be flexible for various input types and to substantially reduce the number of parameters for better generalization. Using the NASA lithium-ion battery datasets, we verify the accuracy of the proposed LSTM-based RUL prediction. The experimental results show that the proposed single-channel LSTM model improves the mean absolute percentage error (MAPE) by 39.2% compared to the baseline LSTM model. Furthermore, the proposed multi-channel LSTM model significantly improves the MAPE, e.g., by 63.7% compared to the baseline; the proposed model achieves 0.47-1.88% of MAPE while the state-of-the-art baseline LSTM shows 0.6-6.45% of MAPE. |
| first_indexed | 2024-12-13T18:17:21Z |
| format | Article |
| id | doaj.art-cd54db08e27a483eabcca10dd1ba39e1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T18:17:21Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-cd54db08e27a483eabcca10dd1ba39e12022-12-21T23:35:49ZengIEEEIEEE Access2169-35362020-01-018207862079810.1109/ACCESS.2020.29689398967059LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging ProfilesKyungnam Park0https://orcid.org/0000-0003-2817-2974Yohwan Choi1https://orcid.org/0000-0001-8830-6917Won Jae Choi2https://orcid.org/0000-0002-0552-4781Hee-Yeon Ryu3https://orcid.org/0000-0003-4620-3594Hongseok Kim4https://orcid.org/0000-0002-5744-2358Department of Electronic Engineering, Sogang University, Seoul, South KoreaDepartment of Electronic Engineering, Sogang University, Seoul, South KoreaHyundai Motors Inc., Seoul, South KoreaHyundai Motors Inc., Seoul, South KoreaDepartment of Electronic Engineering, Sogang University, Seoul, South KoreaRemaining useful life (RUL) prediction of lithium-ion batteries can reduce the risk of battery failure by predicting the end of life. In this paper, we propose novel RUL prediction techniques based on long short-term memory (LSTM). To estimate RUL even in the presence of capacity regeneration phenomenon, we consider multiple measurable data from battery management system such as voltage, current and temperature charging profiles whose patterns vary as aging. Unlike the traditional LSTM prediction that matches input layer with output layer as one-to-one structure, we leverage many-to-one structure to be flexible for various input types and to substantially reduce the number of parameters for better generalization. Using the NASA lithium-ion battery datasets, we verify the accuracy of the proposed LSTM-based RUL prediction. The experimental results show that the proposed single-channel LSTM model improves the mean absolute percentage error (MAPE) by 39.2% compared to the baseline LSTM model. Furthermore, the proposed multi-channel LSTM model significantly improves the MAPE, e.g., by 63.7% compared to the baseline; the proposed model achieves 0.47-1.88% of MAPE while the state-of-the-art baseline LSTM shows 0.6-6.45% of MAPE.https://ieeexplore.ieee.org/document/8967059/Lithium-ion batterylong short-term memoryremaining useful lifecapacity estimation |
| spellingShingle | Kyungnam Park Yohwan Choi Won Jae Choi Hee-Yeon Ryu Hongseok Kim LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles IEEE Access Lithium-ion battery long short-term memory remaining useful life capacity estimation |
| title | LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles |
| title_full | LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles |
| title_fullStr | LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles |
| title_full_unstemmed | LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles |
| title_short | LSTM-Based Battery Remaining Useful Life Prediction With Multi-Channel Charging Profiles |
| title_sort | lstm based battery remaining useful life prediction with multi channel charging profiles |
| topic | Lithium-ion battery long short-term memory remaining useful life capacity estimation |
| url | https://ieeexplore.ieee.org/document/8967059/ |
| work_keys_str_mv | AT kyungnampark lstmbasedbatteryremainingusefullifepredictionwithmultichannelchargingprofiles AT yohwanchoi lstmbasedbatteryremainingusefullifepredictionwithmultichannelchargingprofiles AT wonjaechoi lstmbasedbatteryremainingusefullifepredictionwithmultichannelchargingprofiles AT heeyeonryu lstmbasedbatteryremainingusefullifepredictionwithmultichannelchargingprofiles AT hongseokkim lstmbasedbatteryremainingusefullifepredictionwithmultichannelchargingprofiles |