Robust SOH Estimation for Batteries via Deep Learning Under Incomplete Measurements.
Saved in:
| Title: | Robust SOH Estimation for Batteries via Deep Learning Under Incomplete Measurements. |
|---|---|
| Authors: | Teng, Jenhao1 (AUTHOR) jhteng@ee.nsysu.edu.tw, Lin, Kuanyu1 (AUTHOR), Lee, Pingtse1 (AUTHOR) |
| Source: | Energies (19961073). May2026, Vol. 19 Issue 9, p2100. 20p. |
| Subject Terms: | *Long short-term memory, *Missing data (Statistics), *Interpolation algorithms, *Transformer models, *Deep learning, *Energy storage |
| Abstract: | Battery state-of-health (SOH) estimation is essential for the safety and reliability of energy storage systems. However, incomplete measurements due to sensor or communication failures pose significant challenges for accurate prediction. This paper proposes a robust SOH estimation framework using a minimal 5 min observation window to handle high data sparsity in both random and latter-half missing scenarios. Three Deep Learning (DL) architectures—Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Transformer—are evaluated for data imputation and SOH estimation against traditional polynomial fitting. Simulation results on the NASA benchmark dataset demonstrate that the proposed LSTM model achieves high accuracy, with an RMSE of 0.8522 on complete data. For imperfect data scenarios, BiLSTM-based imputation effectively suppresses extreme deviations, reducing the Maximum Error (MxE) by 44% (from 14.04 to 7.85) compared to traditional polynomial methods. Furthermore, in challenging terminal missing-data cases, a hybrid LSTM-Transformer strategy maintains physical consistency, achieving a superior RMSE of 1.0026. These findings confirm that the proposed DL-based framework significantly outperforms conventional techniques, providing a robust and reliable solution for real-time battery health monitoring under unpredictable data conditions. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: enr DbLabel: Energy & Power Source An: 193715996 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Robust SOH Estimation for Batteries via Deep Learning Under Incomplete Measurements. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Teng%2C+Jenhao%22">Teng, Jenhao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jhteng@ee.nsysu.edu.tw</i><br /><searchLink fieldCode="AR" term="%22Lin%2C+Kuanyu%22">Lin, Kuanyu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lee%2C+Pingtse%22">Lee, Pingtse</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. May2026, Vol. 19 Issue 9, p2100. 20p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Long+short-term+memory%22">Long short-term memory</searchLink><br />*<searchLink fieldCode="DE" term="%22Missing+data+%28Statistics%29%22">Missing data (Statistics)</searchLink><br />*<searchLink fieldCode="DE" term="%22Interpolation+algorithms%22">Interpolation algorithms</searchLink><br />*<searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink><br />*<searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Energy+storage%22">Energy storage</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Battery state-of-health (SOH) estimation is essential for the safety and reliability of energy storage systems. However, incomplete measurements due to sensor or communication failures pose significant challenges for accurate prediction. This paper proposes a robust SOH estimation framework using a minimal 5 min observation window to handle high data sparsity in both random and latter-half missing scenarios. Three Deep Learning (DL) architectures—Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Transformer—are evaluated for data imputation and SOH estimation against traditional polynomial fitting. Simulation results on the NASA benchmark dataset demonstrate that the proposed LSTM model achieves high accuracy, with an RMSE of 0.8522 on complete data. For imperfect data scenarios, BiLSTM-based imputation effectively suppresses extreme deviations, reducing the Maximum Error (MxE) by 44% (from 14.04 to 7.85) compared to traditional polynomial methods. Furthermore, in challenging terminal missing-data cases, a hybrid LSTM-Transformer strategy maintains physical consistency, achieving a superior RMSE of 1.0026. These findings confirm that the proposed DL-based framework significantly outperforms conventional techniques, providing a robust and reliable solution for real-time battery health monitoring under unpredictable data conditions. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=193715996 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/en19092100 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 20 StartPage: 2100 Subjects: – SubjectFull: Long short-term memory Type: general – SubjectFull: Missing data (Statistics) Type: general – SubjectFull: Interpolation algorithms Type: general – SubjectFull: Transformer models Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Energy storage Type: general Titles: – TitleFull: Robust SOH Estimation for Batteries via Deep Learning Under Incomplete Measurements. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Teng, Jenhao – PersonEntity: Name: NameFull: Lin, Kuanyu – PersonEntity: Name: NameFull: Lee, Pingtse IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 05 Text: May2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 19961073 Numbering: – Type: volume Value: 19 – Type: issue Value: 9 Titles: – TitleFull: Energies (19961073) Type: main |
| ResultId | 1 |
