Design and Application of Mixed Natural Gas Monitoring System Using Artificial Neural Networks

Abstract

Natural gas component analysis is one of the significant technologies in the exploitation and utilization of natural gas. A stable and accurate online natural gas monitoring system is necessary for the gas extracting industry. We have developed an online monitoring system of natural gas with a novel hardware architecture. It improves the dependability and maintainability of the system. A specific instruction set is designed to facilitate the coordination of software and hardware. To reduce the sample noise, the exponentially weighted moving average (EWMA) method is used to preprocess the real-time raw data of the sensor array. A tailored neural network is designed for calibration. And the relationship between the performance and the structure of the gas neural network is demonstrated to find the optimal solution for accuracy and hardware scale. The design not only focuses on the optimization of individual components but also focuses on system-level improvement. The system has been running stably for several months in the gas fields. It meets the requirements of stability, ease of use, maintainability, and online monitoring in industrial applications.

Multi-feature Optimization of a Gas Sensor Array to Improve Component and Concentration Detection Performance of VOC Mixtures

“…Data analysis and statistics.-Feature extraction.-Feature extraction is aimed to extract relevant information from sensor responses to fully characterize the responses and has significant influences on the performance of feature selection and pattern recognition. 20,47 Compared with other feature extraction methods, such as coefficients of transform domain, 51 and exponentially moving average method, 52 features directly extracted from the original responses have special physiochemical meanings and reflect the reaction kinetics information. Besides, some papers have proved that the introduction of dynamic features, such as derivatives and integrals of the response curves, can improve the performance of pattern recognition.…”

Design and research of Sense, Know, Anticipate and Protect Integrated Intelligent Gas Pipeline Network Security System

“…Hou et al proposed a method to optimize pipeline leakage monitoring points, which monitored the leakage diffusion radius and effective length, and achieved a reduced monitoring point in monitoring of gas pipeline leaks [16]. Wang et al designed a natural gas online monitoring system that enables online monitoring of natural gas leaks and online calibration of raw data through neural networks [17]. Karumanchi Meeravali et al in 2022 required the inclusion of flame out in twelve safety protection measures for German wall-hung protection function and ionizing flame control device, which cuts off the gas supply and lights up to indicate when the flame is extinguished, prevents residual and incomplete combustion, and accesses a manual recovery function for gas safety [18].…”

Harmful gases detection using artificial neural networks of the environment

“…Soomro and Jilani [20] developed a gas safe registered monitoring system for coal mining that uses sensors to detect gas concentrations (CO, methane temperature, as well as humidity), a ZigBee wireless network to communicate, as well as an artificial neural network to estimate gas concentration levels and alarm hazards. Natural gas fields are extensively scattered around the world, and organic gas monitoring application circumstances vary greatly, ranging from frigid and dry inland regions to warm and humid offshore gas fields [21].…”

“…The mentioned smelling system steps were used to collect scent information for each of the illustrations and trials; [0-20] sec: for first 20 seconds, the smell container was kept closed and separated from longing (pattern esteem); [20][21][22][23][24][25][26][27][28][29][30] sec: Jug was open for such 10 seconds (stabilization); [30-90] sec: electronics nose goal was placed closer to container after 30 seconds, at a distance of 10 cm, as well as recorded for 60 seconds. [90-X] sec: lastly, the source was removed, as well as the electronic nose was left to return to layout state for 10 minutes before the next chronicle.…”