Battery Health Prognosis: Discharging Capacity Prediction at All Operating Voltage Levels

Chunyang Zhao; Peter Bach Andersen; Chresten Træholt; Seyedmostafa Hashemi

doi:10.1109/PESGM52003.2023.10252691

Battery Health Prognosis: Discharging Capacity Prediction at All Operating Voltage Levels

Chunyang Zhao, Peter Bach Andersen, Chresten Træholt, Seyedmostafa Hashemi

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

128 Downloads (Pure)

Abstract

The battery energy storage system is an essential component in the modern energy system with the development of renewable energy, transportation electrification, and carbon-neutral goals. Battery degradation has been the most challenging issue of energy storage. This work presents a data-driven battery degradation model powered by long short-term memory (LSTM) recurrent neural network (RNN). Utilizing the battery dataset with more than 100 batteries exposed to different operations, the proposed model gives a precise prediction of full-discharge capacity and internal resistance (IR) with the root-mean-square error (RMSE) of 0.008 Ah and 0.00017 Ohm in 100 cycles, respectively. Instead of a single capacity or state of health (SOH) value projection, our model predicts the full-discharge capacity-voltage trajectory of the following cycles, addresses the capacity and energy content in different voltage ranges, and improves the accuracy and applicability of the SOH prognosis in industrial applications.

Original language	English
Title of host publication	Proceedings of 2023 IEEE Power & Energy Society General Meeting (PESGM)
Number of pages	5
Publisher	IEEE
Publication date	2023
ISBN (Electronic)	978-1-6654-6441-3
DOIs	https://doi.org/10.1109/PESGM52003.2023.10252691
Publication status	Published - 2023
Event	2023 IEEE Power & Energy Society General Meeting - Orlando, United States Duration: 16 Jul 2023 → 20 Jul 2023

Conference

Conference	2023 IEEE Power & Energy Society General Meeting
Country/Territory	United States
City	Orlando
Period	16/07/2023 → 20/07/2023

Series	Ieee Power and Energy Society General Meeting
ISSN	1944-9933

Keywords

State of health
Data-driven prognosis
Battery degradation modeling
Battery health indicator

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/PESGM52003.2023.10252691

FulltextFinal published version, 1.16 MB

OpenUrl availability

Full text

Cite this

@inproceedings{adb4eaae19d34281a8168485a4a5e25b,

title = "Battery Health Prognosis: Discharging Capacity Prediction at All Operating Voltage Levels",

abstract = "The battery energy storage system is an essential component in the modern energy system with the development of renewable energy, transportation electrification, and carbon-neutral goals. Battery degradation has been the most challenging issue of energy storage. This work presents a data-driven battery degradation model powered by long short-term memory (LSTM) recurrent neural network (RNN). Utilizing the battery dataset with more than 100 batteries exposed to different operations, the proposed model gives a precise prediction of full-discharge capacity and internal resistance (IR) with the root-mean-square error (RMSE) of 0.008 Ah and 0.00017 Ohm in 100 cycles, respectively. Instead of a single capacity or state of health (SOH) value projection, our model predicts the full-discharge capacity-voltage trajectory of the following cycles, addresses the capacity and energy content in different voltage ranges, and improves the accuracy and applicability of the SOH prognosis in industrial applications.",

keywords = "State of health, Data-driven prognosis, Battery degradation modeling, Battery health indicator",

author = "Chunyang Zhao and Andersen, {Peter Bach} and Chresten Tr{\ae}holt and Seyedmostafa Hashemi",

year = "2023",

doi = "10.1109/PESGM52003.2023.10252691",

language = "English",

series = "Ieee Power and Energy Society General Meeting",

booktitle = "Proceedings of 2023 IEEE Power & Energy Society General Meeting (PESGM)",

publisher = "IEEE",

address = "United States",

note = "2023 IEEE Power & Energy Society General Meeting<br/>, PESGM 2023 ; Conference date: 16-07-2023 Through 20-07-2023",

}

Zhao, C , Andersen, PB , Træholt, C & Hashemi, S 2023, Battery Health Prognosis: Discharging Capacity Prediction at All Operating Voltage Levels. in Proceedings of 2023 IEEE Power & Energy Society General Meeting (PESGM). IEEE, Ieee Power and Energy Society General Meeting, 2023 IEEE Power & Energy Society General Meeting
, Orlando, Florida, United States, 16/07/2023. https://doi.org/10.1109/PESGM52003.2023.10252691

Battery Health Prognosis: Discharging Capacity Prediction at All Operating Voltage Levels. / Zhao, Chunyang ; Andersen, Peter Bach ; Træholt, Chresten et al.
Proceedings of 2023 IEEE Power & Energy Society General Meeting (PESGM). IEEE, 2023. (Ieee Power and Energy Society General Meeting).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Battery Health Prognosis: Discharging Capacity Prediction at All Operating Voltage Levels

AU - Zhao, Chunyang

AU - Andersen, Peter Bach

AU - Træholt, Chresten

AU - Hashemi, Seyedmostafa

PY - 2023

Y1 - 2023

N2 - The battery energy storage system is an essential component in the modern energy system with the development of renewable energy, transportation electrification, and carbon-neutral goals. Battery degradation has been the most challenging issue of energy storage. This work presents a data-driven battery degradation model powered by long short-term memory (LSTM) recurrent neural network (RNN). Utilizing the battery dataset with more than 100 batteries exposed to different operations, the proposed model gives a precise prediction of full-discharge capacity and internal resistance (IR) with the root-mean-square error (RMSE) of 0.008 Ah and 0.00017 Ohm in 100 cycles, respectively. Instead of a single capacity or state of health (SOH) value projection, our model predicts the full-discharge capacity-voltage trajectory of the following cycles, addresses the capacity and energy content in different voltage ranges, and improves the accuracy and applicability of the SOH prognosis in industrial applications.

AB - The battery energy storage system is an essential component in the modern energy system with the development of renewable energy, transportation electrification, and carbon-neutral goals. Battery degradation has been the most challenging issue of energy storage. This work presents a data-driven battery degradation model powered by long short-term memory (LSTM) recurrent neural network (RNN). Utilizing the battery dataset with more than 100 batteries exposed to different operations, the proposed model gives a precise prediction of full-discharge capacity and internal resistance (IR) with the root-mean-square error (RMSE) of 0.008 Ah and 0.00017 Ohm in 100 cycles, respectively. Instead of a single capacity or state of health (SOH) value projection, our model predicts the full-discharge capacity-voltage trajectory of the following cycles, addresses the capacity and energy content in different voltage ranges, and improves the accuracy and applicability of the SOH prognosis in industrial applications.

KW - State of health

KW - Data-driven prognosis

KW - Battery degradation modeling

KW - Battery health indicator

U2 - 10.1109/PESGM52003.2023.10252691

DO - 10.1109/PESGM52003.2023.10252691

M3 - Article in proceedings

T3 - Ieee Power and Energy Society General Meeting

BT - Proceedings of 2023 IEEE Power & Energy Society General Meeting (PESGM)

PB - IEEE

T2 - 2023 IEEE Power & Energy Society General Meeting<br/>

Y2 - 16 July 2023 through 20 July 2023

ER -

Battery Health Prognosis: Discharging Capacity Prediction at All Operating Voltage Levels

Abstract

Conference

Keywords

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this