A Neural Model To Detect And Determine The Magnitude Of Leaks In Gas Pipelines

Considering the importance of monitoring piping systems, the aim of this work is to develop a technique to detect gas leaks in pipes, based on acoustic method, in order to determining the magnitude of leaks through the use of neural artificial networks. Audible noise, generated by leaks, was detected in a pipe 100 m long. The experimental data, obtained through a microphone installed inside the pressure vessel and connected to a data acquisition system, are decomposed into sounds of different frequencies. The dynamics of these noises in time is used as input to the neural model to determine the occurrence and magnitude of the leaks. From the results, it was observed that the leaks were properly detected by the acoustic method in all situations. The developed neural models determined successfully the magnitude of new leaks caused in the same pipe.8994Verde, C., Visairo, N., Gentil, S., Two leaks isolation in a pipeline by transient response (2007) Advances in Water Resources, 30 (8), pp. 1711-1721. , DOI 10.1016/j.advwatres.2007.01.001, PII S0309170807000103Taghvaei, M., Beck, S.B.M., Staszewski, W.J., Leak detection in pipeline networks using low-profile piezoceramic transducers (2007) Structural Control and Health Monitoring, 14 (8), pp. 1063-1082. , DOI 10.1002/stc.187Sousa, E.O., Cruz, S.L., Pereira, J.A.F.R., Monitoring pipelines through acoustic method (2009) Computer Aided Chemical Engineering, 27, pp. 1509-1514Zhong, T., Alouani, A.T., Smoak, R.A., ANN based tube detection system. A tutorial review (1997) Proc. 29th IEEE Southeastern Symposium on System Theory, pp. 211-115Belsito, S., Lombardi, P., Andreussi, P., Banerjee, S., Leak detection in liquefied gas pipelines by artificial neural networks (1998) AIChE Journal, 44 (12), pp. 2675-2688Tolstoy, A., Horoshenkov, K.V., Bin All, M.T., Detection pipe changes via acoustic matched field processing (2008) J. Appl. Acoustics, 70, pp. 695-702Selli, M.F., Seleghim, P., Online identification of horizontal two-phase flow regimes through gabor transform and neural network processing (2007) Heat Transfer Engineering, 28 (6), pp. 541-548. , DOI 10.1080/01457630701193955, PII 777785228Avelino, A.M., De Paiva, J.A., Da Silva, R.E.F., Araujo, G.J.M., Real time leak detection system applied to oil pipelines using sonic technology and neural networks (2009) 35th Annual Conference of IEEE, pp. 2109-2114Yang, J., Wen, Y., Li, P., Leak acoustic detection in water distribution pipelines (2008) Proceedings of the 7th World Congress on Intelligent Control and Automation, pp. 3057-3061Caputo, A.C., Pelagagge, P.M., Using neural networks to monitor piping systems (2003) Process Safety Progress, 22 (2), pp. 119-127Verde, C., Menendez, R.M., Garza, L.E., Vargas, A., Roug, P.V., Rea, C., Aparicio, C.T., De La Fuente, J.O., Monitoring pipelines through acoustic method. Multileak diagnosis in pipelines - A comparison of approaches (2008) Seventh Mexican International Conference on Artificial Intelligence, pp. 352-35