A NARROWBAND INTERNET OF THING CONNECTED TEMPERATURE PREDICTION FOR VALVE-REGULATED LEAD-ACID BATTERY

Hao Wang; Tsz Chun Lai; Yang Wei; Yucheng Liu; Kim Fung Tsang; Chun Sing Lai; Loi Lei Lai

doi:10.46855/energy-proceedings-6675

A NARROWBAND INTERNET OF THING CONNECTED TEMPERATURE PREDICTION FOR VALVE-REGULATED LEAD-ACID BATTERY

Hao Wang
, Tsz Chun Lai
, Yang Wei
, Yucheng Liu
, Kim Fung Tsang^*
, Chun Sing Lai^*
, Loi Lei Lai

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Valve-regulated lead-acid (VRLA) battery, owning the huge market, plays an important role in all aspects of industries. A VRLA battery sometimes called sealed lead-acid (SLA) or maintenance-free battery, however, the safety of VRLA has been a wide concern since it is prone to self-heating problems which generate extra cost or even cause accidents when the internal temperature (IT) of VRLA is out of range. To prevent potential hazards, effective internal VRLA temperature monitoring methods are in need of further management. In this paper, a narrowband (NB) Internet of thing (IoT) connected VRLA battery internal temperature prediction (VBITP) algorithm is developed to provide early warning of battery temperature. In VBITP, the internal temperature is estimated by ambient temperature (AT) and input current (IC) through a pre-trained prediction model. The measured temperature data will be sent to the backend server using NB-IoT. A kind of recurrent neural network, nonlinear autoregressive exogenous (NARX) is applied to find the potential relationship between the input AT, IC and the output IT and train this model. The experimental results show that VBITP could estimate the IT of VRLA battery with an error rate of 0.04. © 2019 ICAE.

Original language	English
Title of host publication	Innovative Solutions for Energy Transitions: Part V
Place of Publication	Stockholm, Sweden
Publisher	Scanditale AB
DOIs	https://doi.org/10.46855/energy-proceedings-6675
Publication status	Published - Aug 2019
Event	11th International Conference on Applied Energy (ICAE 2019): Innovative Solutions for Energy Transitions - Västerås, Sweden Duration: 12 Aug 2019 → 15 Aug 2019 https://www.energy-proceedings.org/volumes/ https://applied-energy.org/icae2019/wp-content/uploads/2019/08/18.pdf

Publication series

Name	Energy Proceedings
Volume	6
ISSN (Print)	2004-2965

Conference

Conference	11th International Conference on Applied Energy (ICAE 2019)
Abbreviated title	ICAE2019
Place	Sweden
City	Västerås
Period	12/08/19 → 15/08/19
Internet address	https://www.energy-proceedings.org/volumes/ https://applied-energy.org/icae2019/wp-content/uploads/2019/08/18.pdf

Funding

The project is sponsored by the project titled “The design of self-sustainable wireless sensor network mod-ule for telemedicine”, the City University of Hong Kong with project number 9678057.

UN SDGs

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

SDG 9 Industry, Innovation, and Infrastructure

Research Keywords

internal temperature prediction
narrowband internet of thing
NARX neural network
VRLA battery

Access Output

10.46855/energy-proceedings-6675

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{4775491be7474267bd830fdce26563e6,

title = "A NARROWBAND INTERNET OF THING CONNECTED TEMPERATURE PREDICTION FOR VALVE-REGULATED LEAD-ACID BATTERY",

abstract = "Valve-regulated lead-acid (VRLA) battery, owning the huge market, plays an important role in all aspects of industries. A VRLA battery sometimes called sealed lead-acid (SLA) or maintenance-free battery, however, the safety of VRLA has been a wide concern since it is prone to self-heating problems which generate extra cost or even cause accidents when the internal temperature (IT) of VRLA is out of range. To prevent potential hazards, effective internal VRLA temperature monitoring methods are in need of further management. In this paper, a narrowband (NB) Internet of thing (IoT) connected VRLA battery internal temperature prediction (VBITP) algorithm is developed to provide early warning of battery temperature. In VBITP, the internal temperature is estimated by ambient temperature (AT) and input current (IC) through a pre-trained prediction model. The measured temperature data will be sent to the backend server using NB-IoT. A kind of recurrent neural network, nonlinear autoregressive exogenous (NARX) is applied to find the potential relationship between the input AT, IC and the output IT and train this model. The experimental results show that VBITP could estimate the IT of VRLA battery with an error rate of 0.04. {\textcopyright} 2019 ICAE.",

keywords = "internal temperature prediction, narrowband internet of thing, NARX neural network, VRLA battery",

author = "Hao Wang and Lai, \{Tsz Chun\} and Yang Wei and Yucheng Liu and Tsang, \{Kim Fung\} and Lai, \{Chun Sing\} and Lai, \{Loi Lei\}",

year = "2019",

month = aug,

doi = "10.46855/energy-proceedings-6675",

language = "English",

series = "Energy Proceedings",

publisher = "Scanditale AB",

booktitle = "Innovative Solutions for Energy Transitions: Part V",

note = "11th International Conference on Applied Energy (ICAE 2019) : Innovative Solutions for Energy Transitions, ICAE2019 ; Conference date: 12-08-2019 Through 15-08-2019",

url = "https://www.energy-proceedings.org/volumes/, https://applied-energy.org/icae2019/wp-content/uploads/2019/08/18.pdf",

}

Wang, H, Lai, TC , Wei, Y , Liu, Y , Tsang, KF, Lai, CS & Lai, LL 2019, A NARROWBAND INTERNET OF THING CONNECTED TEMPERATURE PREDICTION FOR VALVE-REGULATED LEAD-ACID BATTERY. in Innovative Solutions for Energy Transitions: Part V., 0204, Energy Proceedings, vol. 6, Scanditale AB, Stockholm, Sweden, 11th International Conference on Applied Energy (ICAE 2019), Västerås, Sweden, 12/08/19. https://doi.org/10.46855/energy-proceedings-6675

A NARROWBAND INTERNET OF THING CONNECTED TEMPERATURE PREDICTION FOR VALVE-REGULATED LEAD-ACID BATTERY. / Wang, Hao; Lai, Tsz Chun ; Wei, Yang et al.
Innovative Solutions for Energy Transitions: Part V. Stockholm, Sweden: Scanditale AB, 2019. 0204 (Energy Proceedings; Vol. 6).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A NARROWBAND INTERNET OF THING CONNECTED TEMPERATURE PREDICTION FOR VALVE-REGULATED LEAD-ACID BATTERY

AU - Wang, Hao

AU - Lai, Tsz Chun

AU - Wei, Yang

AU - Liu, Yucheng

AU - Tsang, Kim Fung

AU - Lai, Chun Sing

AU - Lai, Loi Lei

PY - 2019/8

Y1 - 2019/8

N2 - Valve-regulated lead-acid (VRLA) battery, owning the huge market, plays an important role in all aspects of industries. A VRLA battery sometimes called sealed lead-acid (SLA) or maintenance-free battery, however, the safety of VRLA has been a wide concern since it is prone to self-heating problems which generate extra cost or even cause accidents when the internal temperature (IT) of VRLA is out of range. To prevent potential hazards, effective internal VRLA temperature monitoring methods are in need of further management. In this paper, a narrowband (NB) Internet of thing (IoT) connected VRLA battery internal temperature prediction (VBITP) algorithm is developed to provide early warning of battery temperature. In VBITP, the internal temperature is estimated by ambient temperature (AT) and input current (IC) through a pre-trained prediction model. The measured temperature data will be sent to the backend server using NB-IoT. A kind of recurrent neural network, nonlinear autoregressive exogenous (NARX) is applied to find the potential relationship between the input AT, IC and the output IT and train this model. The experimental results show that VBITP could estimate the IT of VRLA battery with an error rate of 0.04. © 2019 ICAE.

AB - Valve-regulated lead-acid (VRLA) battery, owning the huge market, plays an important role in all aspects of industries. A VRLA battery sometimes called sealed lead-acid (SLA) or maintenance-free battery, however, the safety of VRLA has been a wide concern since it is prone to self-heating problems which generate extra cost or even cause accidents when the internal temperature (IT) of VRLA is out of range. To prevent potential hazards, effective internal VRLA temperature monitoring methods are in need of further management. In this paper, a narrowband (NB) Internet of thing (IoT) connected VRLA battery internal temperature prediction (VBITP) algorithm is developed to provide early warning of battery temperature. In VBITP, the internal temperature is estimated by ambient temperature (AT) and input current (IC) through a pre-trained prediction model. The measured temperature data will be sent to the backend server using NB-IoT. A kind of recurrent neural network, nonlinear autoregressive exogenous (NARX) is applied to find the potential relationship between the input AT, IC and the output IT and train this model. The experimental results show that VBITP could estimate the IT of VRLA battery with an error rate of 0.04. © 2019 ICAE.

KW - internal temperature prediction

KW - narrowband internet of thing

KW - NARX neural network

KW - VRLA battery

UR - https://www.scopus.com/pages/publications/85202484999

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85202484999&origin=recordpage

U2 - 10.46855/energy-proceedings-6675

DO - 10.46855/energy-proceedings-6675

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - Energy Proceedings

BT - Innovative Solutions for Energy Transitions: Part V

PB - Scanditale AB

CY - Stockholm, Sweden

T2 - 11th International Conference on Applied Energy (ICAE 2019)

Y2 - 12 August 2019 through 15 August 2019

ER -

A NARROWBAND INTERNET OF THING CONNECTED TEMPERATURE PREDICTION FOR VALVE-REGULATED LEAD-ACID BATTERY

Abstract

Publication series

Conference

Funding

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this