Fully automatic AI-based leak detection system》.pdfVIP

Energy 35 (2010) 3838e3848 Contents lists available at ScienceDirect Energy journal homepage: /locate/energy Fully automatic AI-based leak detection system a a b, * Wojciech Tylman , Jakub Kolczynski , George J. Anders a Dept. of Microelectronics and Computer Science, Technical University of Lodz in Poland, ul. Wólczanska 221/223, Łódz, Poland b Kinectrics Inc., 800 Kipling Ave., Toronto, Ontario M8Z 6C4, Canada a r t i c l e i n f o a b s t r a c t Article history: This paper presents a fully automatic system intended to detect leaks of dielectric fluid in underground Received 17 August 2009 high-pressure, fluid-filled (HPFF) cables. The system combines a number of artificial intelligence (AI) and Received in revised form data processing techniques to achieve high detection capabilities for various rates of leaks, including 20 May 2010 leaks as small as 15 l per hour. The system achieves this level of precision mainly thanks to a novel auto- Accepted 25 May 2010 tuning procedure, enabling learning of the Bayesian network e the decision-making component of the system e using simulated leaks of various rates. Significant new developments extending the capabilities of the original leak detection system d