Details
Original language | English |
---|---|
Article number | 121355 |
Journal | Applied energy |
Volume | 349 |
Early online date | 28 Jul 2023 |
Publication status | Published - 1 Nov 2023 |
Abstract
This paper introduces and formalizes the concept of T-shape data, which arises in several engineering and natural contexts, where the initial data are richer and cover a wider range of operations than the data acquired in the following time. The specific context considered is the Li-ion battery experimental testing before the actual operation, where the T-shape data is cast as right-censored data in the application of battery remaining useful life (RUL) prediction. Existing RUL prediction techniques focused on RUL point estimation and provided rough calculations concerning the RUL distribution, thus are insufficient for battery degradation information. Based on the T-shape structure, this paper investigates a time-varying construction of the RUL probability density function. The proposed computationally efficient method, the multiple non-crossing quantiles Long Short-Term Memory (MNQ-LSTM), learns long-term dependencies among battery RUL and operation process quantities, including operating conditions. With several predicted quantile levels, the construction of the RUL conditional probability density function can capture the underlying survival distribution and statistical inferences of battery RUL with richer and more accurate information. Numerical results verify the performance of the proposed MNQ-LSTM with T-shape data. Compared to the conventional LSTM, Gaussian process regression, and a hybrid deep learning model of convolutional neural network and the bi-directional gated recurrent unit, the proposed model outperforms and can achieve the coefficient of determination up to 95.74% regarding point predictions. 100% testing results of battery RUL are not outside the range of 90% prediction intervals even in the worst case of 80% T-shape data.
Keywords
- Li-ion battery, LSTM, Monte Carlo simulation, Non-crossing quantile, Remaining useful life, Right-censored data, T-shape data
ASJC Scopus subject areas
- Engineering(all)
- Building and Construction
- Energy(all)
- Renewable Energy, Sustainability and the Environment
- Engineering(all)
- Mechanical Engineering
- Energy(all)
- General Energy
- Environmental Science(all)
- Management, Monitoring, Policy and Law
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Applied energy, Vol. 349, 121355, 01.11.2023.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - T-shape data and probabilistic remaining useful life prediction for Li-ion batteries using multiple non-crossing quantile long short-term memory
AU - Ly, Sel
AU - Xie, Jiahang
AU - Wolter, Franz Erich
AU - Nguyen, Hung D.
AU - Weng, Yu
N1 - Funding Information: This research is supported by the National Research Foundation Singapore , and the Energy Market Authority , under its Energy Programme (EP Award EMA-EP004-EKJGC-0003), Ministry of Education Singapore under its Award AcRF TIER 1 RG60/22, NRF DERMS for Energy Grid 2.0, and Intra-CREATE Seed Fund Award NRF2022-ITS010- 0005.
PY - 2023/11/1
Y1 - 2023/11/1
N2 - This paper introduces and formalizes the concept of T-shape data, which arises in several engineering and natural contexts, where the initial data are richer and cover a wider range of operations than the data acquired in the following time. The specific context considered is the Li-ion battery experimental testing before the actual operation, where the T-shape data is cast as right-censored data in the application of battery remaining useful life (RUL) prediction. Existing RUL prediction techniques focused on RUL point estimation and provided rough calculations concerning the RUL distribution, thus are insufficient for battery degradation information. Based on the T-shape structure, this paper investigates a time-varying construction of the RUL probability density function. The proposed computationally efficient method, the multiple non-crossing quantiles Long Short-Term Memory (MNQ-LSTM), learns long-term dependencies among battery RUL and operation process quantities, including operating conditions. With several predicted quantile levels, the construction of the RUL conditional probability density function can capture the underlying survival distribution and statistical inferences of battery RUL with richer and more accurate information. Numerical results verify the performance of the proposed MNQ-LSTM with T-shape data. Compared to the conventional LSTM, Gaussian process regression, and a hybrid deep learning model of convolutional neural network and the bi-directional gated recurrent unit, the proposed model outperforms and can achieve the coefficient of determination up to 95.74% regarding point predictions. 100% testing results of battery RUL are not outside the range of 90% prediction intervals even in the worst case of 80% T-shape data.
AB - This paper introduces and formalizes the concept of T-shape data, which arises in several engineering and natural contexts, where the initial data are richer and cover a wider range of operations than the data acquired in the following time. The specific context considered is the Li-ion battery experimental testing before the actual operation, where the T-shape data is cast as right-censored data in the application of battery remaining useful life (RUL) prediction. Existing RUL prediction techniques focused on RUL point estimation and provided rough calculations concerning the RUL distribution, thus are insufficient for battery degradation information. Based on the T-shape structure, this paper investigates a time-varying construction of the RUL probability density function. The proposed computationally efficient method, the multiple non-crossing quantiles Long Short-Term Memory (MNQ-LSTM), learns long-term dependencies among battery RUL and operation process quantities, including operating conditions. With several predicted quantile levels, the construction of the RUL conditional probability density function can capture the underlying survival distribution and statistical inferences of battery RUL with richer and more accurate information. Numerical results verify the performance of the proposed MNQ-LSTM with T-shape data. Compared to the conventional LSTM, Gaussian process regression, and a hybrid deep learning model of convolutional neural network and the bi-directional gated recurrent unit, the proposed model outperforms and can achieve the coefficient of determination up to 95.74% regarding point predictions. 100% testing results of battery RUL are not outside the range of 90% prediction intervals even in the worst case of 80% T-shape data.
KW - Li-ion battery
KW - LSTM
KW - Monte Carlo simulation
KW - Non-crossing quantile
KW - Remaining useful life
KW - Right-censored data
KW - T-shape data
UR - http://www.scopus.com/inward/record.url?scp=85166548118&partnerID=8YFLogxK
U2 - 10.1016/j.apenergy.2023.121355
DO - 10.1016/j.apenergy.2023.121355
M3 - Article
AN - SCOPUS:85166548118
VL - 349
JO - Applied energy
JF - Applied energy
SN - 0306-2619
M1 - 121355
ER -