T-shape data and probabilistic remaining useful life prediction for Li-ion batteries using multiple non-crossing quantile long short-term memory

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Sel Ly
  • Jiahang Xie
  • Franz Erich Wolter
  • Hung D. Nguyen
  • Yu Weng

External Research Organisations

  • Nanyang Technological University (NTU)
View graph of relations

Details

Original languageEnglish
Article number121355
JournalApplied energy
Volume349
Early online date28 Jul 2023
Publication statusPublished - 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

Sustainable Development Goals

Cite this

T-shape data and probabilistic remaining useful life prediction for Li-ion batteries using multiple non-crossing quantile long short-term memory. / Ly, Sel; Xie, Jiahang; Wolter, Franz Erich et al.
In: Applied energy, Vol. 349, 121355, 01.11.2023.

Research output: Contribution to journalArticleResearchpeer review

Ly S, Xie J, Wolter FE, Nguyen HD, Weng Y. T-shape data and probabilistic remaining useful life prediction for Li-ion batteries using multiple non-crossing quantile long short-term memory. Applied energy. 2023 Nov 1;349:121355. Epub 2023 Jul 28. doi: 10.1016/j.apenergy.2023.121355
Download
@article{877003089d944df1822bb05b1ea93781,
title = "T-shape data and probabilistic remaining useful life prediction for Li-ion batteries using multiple non-crossing quantile long short-term memory",
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",
author = "Sel Ly and Jiahang Xie and Wolter, {Franz Erich} and Nguyen, {Hung D.} and Yu Weng",
note = "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. ",
year = "2023",
month = nov,
day = "1",
doi = "10.1016/j.apenergy.2023.121355",
language = "English",
volume = "349",
journal = "Applied energy",
issn = "0306-2619",
publisher = "Elsevier BV",

}

Download

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 -