Leakage detection in a gas pipeline using artificial neural networks based on wireless sensor network and Internet of Things

In this paper, a neural network-based method for leakage detection of a gas pipeline by using gas flow pattern is proposed. The pipe is divided in several segments and each segment is modeled by considering input/output pressure of the gas flow. The idea is to use a computer network based on Internet of Things (IOT) phenomena to gather all the required information for detection of the leakage point. In order to process the acquired data from the pipeline, a neural network is used and trained. As usual some of the data are used as training set to adjust the neural network weights and some other are used to evaluate the performance of the neural network based fault detection system. Practical data gathered from a real life pipeline is used to train the network to make sure that the proposed method is applicable real life projects.

[1]  Rubén Morales-Menéndez,et al.  Leaks Detection in a Pipeline Using Artificial Neural Networks , 2009, CIARP.

[2]  Fei Tao,et al.  IoT-Based Intelligent Perception and Access of Manufacturing Resource Toward Cloud Manufacturing , 2014, IEEE Transactions on Industrial Informatics.

[3]  M. F. Ghazali,et al.  Leak detection in gas pipeline by acoustic and signal processing - A review , 2015 .

[4]  Özgür Ulusoy,et al.  A framework for use of wireless sensor networks in forest fire detection and monitoring , 2012, Comput. Environ. Urban Syst..

[5]  Xue Liu,et al.  Data Loss and Reconstruction in Wireless Sensor Networks , 2014, IEEE Transactions on Parallel and Distributed Systems.

[6]  Ana Maria Frattini Fileti,et al.  Detection and on-line prediction of leak magnitude in a gas pipeline using an acoustic method and neural network data processing , 2014 .

[7]  Jiang Zhe,et al.  A microsensor array for quantification of lubricant contaminants using a back propagation artificial neural network , 2016 .

[8]  Meng-Shiuan Pan,et al.  Event data collection in ZigBee tree-based wireless sensor networks , 2014, Comput. Networks.

[9]  Xianbin Wang,et al.  Wireless Sensor Network Reliability and Security in Factory Automation: A Survey , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[10]  L. Molina-Espinosa,et al.  Numerical modeling of pseudo-homogeneous fluid flow in a pipe with leaks , 2017, Comput. Math. Appl..

[11]  Weiming Shen,et al.  An IoT-Based Online Monitoring System for Continuous Steel Casting , 2016, IEEE Internet of Things Journal.

[12]  Bo Hu,et al.  A Vision of IoT: Applications, Challenges, and Opportunities With China Perspective , 2014, IEEE Internet of Things Journal.

[13]  Jukka Riekki,et al.  Enabling user-centered interactions in the Internet of Things , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[14]  Wing Kong Chiu,et al.  Distributed Optical Fibre Sensors and their Applications in Pipeline Monitoring , 2013 .

[15]  Simin Nadjm-Tehrani,et al.  Attitudes and Perceptions of IoT Security in Critical Societal Services , 2016, IEEE Access.

[16]  Hiranmay Saha,et al.  An IoT based smart solar photovoltaic remote monitoring and control unit , 2016, 2016 2nd International Conference on Control, Instrumentation, Energy & Communication (CIEC).

[17]  Lida Xu,et al.  IoT and Cloud Computing in Automation of Assembly Modeling Systems , 2014, IEEE Transactions on Industrial Informatics.

[18]  Sanghamitra Panda,et al.  Secure and Efficient Data Transmission for Cluster-Based Wireless Sensor Networks , 2015 .

[19]  Andrey Somov,et al.  wireless sensor – actuator system for hazardous gases detection nd control , 2014 .

[20]  John A. Stankovic,et al.  Research Directions for the Internet of Things , 2014, IEEE Internet of Things Journal.

[21]  Morteza Mohammadzaheri,et al.  Fault Detection of Gas Pipelines Using Mechanical Waves and Intelligent Techniques , 2015 .