Intelligent fault diagnosis for instrument in gas transportation system

The reliability and availability of the metering system plays a crucial part in the gas transportation system because it affects the billing integrity between the gas supplier and their customers. A slight error in measurement will lead to significant monetary impact. Therefore, the challenge lies in building an online verification system that is able to check the accuracy of instruments in the metering system as well as to enable the verification system to reconstruct data in the case of faults on the instruments during operation time. This paper proposes hypotheses as well as a research plan to deal with these problems. The proposed idea invests in the behavior and relation among instruments based on empirical models, particularly Neural Network. Based on this model, the faults of instrument will be detected and unreliable data will be corrected. © 2014 IEEE.