Gas pipeline safety management system based on neural network

Abstract

The risk of leakage poses a grave threat to natural gas pipeline safety. The high compressibility of gases combined with unsteady boundary conditions makes detecting leaks in pipelines a challenging endeavor. To date, in the literature, only a limited number of studies have focused on leak detection and diagnostics in gas mixture pipelines. The present study provides a system for detecting, locating, and estimating the size of small gas leaks from a compressible and dynamic natural gas flow in pipelines with improved accuracy. As a case study, a long natural gas pipeline of 80 km is simulated with leak sizes of 0%, 2%, and 5%. The safety system is developed using mass flow rate, temperature, and pressure measurements. Six classes for faulty cases and one class for no fault case were considered for the study. A shallow neural network classifier (SNNC) is trained to identify a specific fault class. The SNNC is based on a two-layered network with 20 and 7 neurons. An input vector of 15 variables is provided to the system, and the output is one of the seven possible classes. Leakage as low as 2% at various locations are correctly diagnosed with more than 99% correct classification rate.

Research on Intelligent Management System of Gas Pipeline with Multi-source Data Fusion

“…The fusion of data from multiple sources can provide a more comprehensive view of the system and help assess the operational status and potential risks of pipelines more accurately [7]. An efficient, intelligent gas pipeline management system usually includes several key components, including data collection, data storage, data analysis, and decision support [8][9][10]. The system should be able to collect and process data from various sensors and databases in real-time, utilize advanced data analysis techniques (e.g., machine learning and artificial intelligence) to perform risk assessment and prediction, and provide effective decision support [11].…”

Research on Predicting Leakage Aperture of Water Pipelines Based on IGWO-BP Model

“…Preference [1][2] detects pressure changes in the pipe network using high-frequency pressure sensors, and identifies leakage conditions in the pipe network using negative pressure waves; Ahmad et al [3] used continuous wavelet transform to obtain acoustic image features from time series acoustic emission signals, and then identified the pipeline leakage state through neural network; Mujtaba et al [4] identified the fault category of specific gas pipeline through shallow neural network classifier (SNNC); Zhang Yong et al [5] optimized Elman neural network by genetic algorithm (GA) and applied it to pipeline leakage identification.…”

Application of rough set theory and machine learning algorithms in predicting accident outcomes in the Indian petroleum industry

“…A safety management system (SMS) is an important part of every organization as its ignorance can lead to loss of lives, property, and productivity 1 . The efficient analysis of incident data helps companies pinpoint the weakness in the safety management system and it helps to plan future training and operations planning decisions 2 .…”