A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting

An effective forecast method to trigger Thermal Runaway (TR) warning in an early stage is essential for monitoring battery safety. In this article, we propose a novel data-driven approach to perform multistep ahead forecast accurately for battery TR state at cell-level. We formulate this forecasting...

Full description

Saved in:
Bibliographic Details
Main Authors: Ding, Shuya, Dong, Chaoyu, Zhao, Tianyang, Koh, Liang Mong, Bai, Xiaoyin, Luo, Jun
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/160292
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-160292
record_format dspace
spelling sg-ntu-dr.10356-1602922022-07-19T01:40:44Z A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting Ding, Shuya Dong, Chaoyu Zhao, Tianyang Koh, Liang Mong Bai, Xiaoyin Luo, Jun School of Computer Science and Engineering Energy Research Institute @ NTU (ERI@N) Engineering::Computer science and engineering Feature Extraction Batteries An effective forecast method to trigger Thermal Runaway (TR) warning in an early stage is essential for monitoring battery safety. In this article, we propose a novel data-driven approach to perform multistep ahead forecast accurately for battery TR state at cell-level. We formulate this forecasting task as an imbalance data classification task and propose meta thermal runaway forecasting neural network (Meta-TRFNN) to solve it. Essentially, we exploit high-dimensional thermal images along with low-dimensional temperature and voltage data to capture a more representative thermal profile. Moreover, we adapt a meta-learning framework to handle the data deficiency problem. We evaluate Meta-TRFNN on simulated samples and also explore its applicability in the real world with real samples. Although this classification task is highly imbalanced, Meta-TRFNN is still proven effective with limited historical information. Our further comparison experiments not only demonstrate the forecasting ability of Meta-TRFNN, but also validate the benefit of involving high-dimensional thermal images and the efficacy of meta-learning framework. Nanyang Technological University National Research Foundation (NRF) This work was supported in part by the Energy Program Energy Storage System Test Bed Project under Grant NRF2016ENC-ESS001-022, and in part by the Energy Research Institute at Nanyang Technological University (Singapore). 2022-07-19T01:40:43Z 2022-07-19T01:40:43Z 2020 Journal Article Ding, S., Dong, C., Zhao, T., Koh, L. M., Bai, X. & Luo, J. (2020). A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting. IEEE Transactions On Industrial Informatics, 17(7), 4503-4511. https://dx.doi.org/10.1109/TII.2020.3015555 1551-3203 https://hdl.handle.net/10356/160292 10.1109/TII.2020.3015555 2-s2.0-85104196858 7 17 4503 4511 en NRF2016ENC-ESS001-022 IEEE Transactions on Industrial Informatics © 2020 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Feature Extraction
Batteries
spellingShingle Engineering::Computer science and engineering
Feature Extraction
Batteries
Ding, Shuya
Dong, Chaoyu
Zhao, Tianyang
Koh, Liang Mong
Bai, Xiaoyin
Luo, Jun
A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting
description An effective forecast method to trigger Thermal Runaway (TR) warning in an early stage is essential for monitoring battery safety. In this article, we propose a novel data-driven approach to perform multistep ahead forecast accurately for battery TR state at cell-level. We formulate this forecasting task as an imbalance data classification task and propose meta thermal runaway forecasting neural network (Meta-TRFNN) to solve it. Essentially, we exploit high-dimensional thermal images along with low-dimensional temperature and voltage data to capture a more representative thermal profile. Moreover, we adapt a meta-learning framework to handle the data deficiency problem. We evaluate Meta-TRFNN on simulated samples and also explore its applicability in the real world with real samples. Although this classification task is highly imbalanced, Meta-TRFNN is still proven effective with limited historical information. Our further comparison experiments not only demonstrate the forecasting ability of Meta-TRFNN, but also validate the benefit of involving high-dimensional thermal images and the efficacy of meta-learning framework.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Ding, Shuya
Dong, Chaoyu
Zhao, Tianyang
Koh, Liang Mong
Bai, Xiaoyin
Luo, Jun
format Article
author Ding, Shuya
Dong, Chaoyu
Zhao, Tianyang
Koh, Liang Mong
Bai, Xiaoyin
Luo, Jun
author_sort Ding, Shuya
title A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting
title_short A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting
title_full A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting
title_fullStr A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting
title_full_unstemmed A meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting
title_sort meta-learning based multimodal neural network for multistep ahead battery thermal runaway forecasting
publishDate 2022
url https://hdl.handle.net/10356/160292
_version_ 1739837459661848576