An End-to-End Early Warning System Based on Wireless Sensor Network for Gas Leakage Detection in Industrial Facilities

Bany Salameh, Haythem Ahmad, Dhainat, Mohammad Fozi and BENKHELIFA, Elhadj (2020) An End-to-End Early Warning System Based on Wireless Sensor Network for Gas Leakage Detection in Industrial Facilities. IEEE Systems Journal. pp. 1-9. ISSN 1932-8184

Preview

Text Technical_Progress_report__1_ (7).pdf - AUTHOR'S ACCEPTED Version (default) Available under License All Rights Reserved. Download (2MB) | Preview

Abstract or description

Existing Liquefied Petroleum Gas (LPG)-detectionsystems are ad-hoc and designed as stand-alone nodes. Thispaper, however, presents an integrated end-to-end Wireless SensorNetwork (WSN) system that integrates hardware and software forearly-warning gas-leakage detection and monitoring applications;fully utilizing the Internet-of-thing (IoT) functionalities andcapabilities in WSNs at the network level such that networkperformance is improved. The proposed system can operate insingle-hop and multi-hop modes depending on the surround-ing radio frequency (RF) environment and network topology.Specifically, we design a per-deployed WSN system for LPG-gas detection/monitoring in residential areas and factories thatcollects, analyzes and forwards the collected information over awireless channel to the monitoring center to take the appropriateaction. To achieve a reliable communication and data delivery, weimplement an efficient communication protocol that organizes thedata exchanges between the different nodes in the network. Theproposed WSN system is deployed and experimentally tested.The data acquired from the various experiments is used toexamine the reliable operation of the implemented system interms of robustness and data-delivery reliability. Robust andreliable performance is demonstrated with packet loss rate as lowas5%. The experimental results also indicate that the proposedsystem can promptly detect gas-leakage within50ms and provideaccurate gas concentration measurements with97%accuracy.

Item Type:	Article
Additional Information:	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Faculty:	School of Computing and Digital Technologies > Computing
Depositing User:	Elhadj BENKHELIFA
Date Deposited:	10 Sep 2020 13:38
Last Modified:	24 Feb 2023 14:00
URI:	https://eprints.staffs.ac.uk/id/eprint/6533

Actions (login required)

View Item