Title :
Leak monitoring system for gas pipelines
Author :
Brodetsky, Igal ; Savic, Michael
Author_Institution :
Electr. Comput. & Syst. Eng. Dept., Rensselaer Polytech. Inst., Troy, NY, USA
Abstract :
An approach and a solution to the continuous leak monitoring problem in underground gas pipelines are presented. This approach places permanent monitoring units along the pipeline. These units detect acoustic signals in the pipeline and discriminate leak sounds from other man-made or natural nonleak sounds that can occur. The system uses the kNN classifier as the detector with LPC (linear predictive coding) cepstrums as signal features. To increase system performance, pipeline effects on acoustic signals were taken into account during the classifier training phase. Each unit can detect 1/4-in-diameter leaks from a distance of 300 m, yielding 600 m as the maximum distance between units.<>
Keywords :
acoustic signal processing; computerised monitoring; leak detection; learning (artificial intelligence); linear predictive coding; natural gas technology; acoustic signals; classifier training; continuous leak monitoring; k-nearest neighbour classifier; linear predictive coding; monitoring units; system performance; underground gas pipelines;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference on
Conference_Location :
Minneapolis, MN, USA
Print_ISBN :
0-7803-7402-9
DOI :
10.1109/ICASSP.1993.319424