Leak detection in petroleum pipelines using a fuzzy system Henrique V. da Silva a , Celso K. Morooka b, * , Ivan R. Guilherme c , Tiago C. da Fonseca b , Jose ´ R.P. Mendes b a Petrobras, Paulinia-SP, Brazil b State University of Campinas, UNICAMP/FEM/DEP, C.P. - 6052, 13083-970, Campinas-SP, Brazil c Paulista State University, DEMAC/IGCE. Rio Claro-SP, Brazil Accepted 20 May 2005 Abstract A methodology for pipeline leakage detection using a combination of clustering and classification tools for fault detection is presented here. A fuzzy system is used to classify the running mode and identify the operational and process transients. The relationship between these transients and the mass balance deviation are discussed. This strategy allows for better identification of the leakage because the thresholds are adjusted by the fuzzy system as a function of the running mode and the classified transient level. The fuzzy system is initially off-line trained with a modified data set including simulated leakages. The methodology is applied to a small-scale LPG pipeline monitoring case where portability, robustness and reliability are amongst the most important criteria for the detection system. The results are very encouraging with relatively low levels of false alarms, obtaining increased leakage detection with low computational costs. D 2005 Elsevier B.V. All rights reserved. Keywords: Pipeline leakage detection; Pattern recognition; Fuzzy systems 1. Introduction Pipeline is an efficient and economic transportation means for petroleum products. However, risks associ- ated with accidental releases of transported product are still high (Costa, 2001). This issue has motivated the development of many methods for leak detection, main- ly based on process variables, i.e., pressure, flow rate and temperature, such as the volume balance method (Ellul, 1989), or (Stouffs and Giot, 1993), where the importance of packing term in the transient flow is highlighted. In these approaches, data for the estimate of the mass balance are obtained from flow calculators installed in the pipelines. Usually, two equations are used for the mass balance: a more simplified one for the purpose of obtaining a rapid response to large leakages and another more detailed one to obtain slower responses (around 3 to 6 h) in the identification of small leakages (0.5% of the nominal flow). The method proposes the installation of devices at the extremities of the pipelines and occasionally at an intermediary point. This technique does not permit localization of the leak- age point. In the reviewed work, Ellul (1989) describes another technique also referred to as the deviation method. This method is based on the mathematical model of pipeline systems capable of deducing flows and pressures, which can in turn be compared with the measured values. Differences can indicate leakages. The system was ca- pable of detecting leakages of 1.6% of the nominal flow 0920-4105/$ - see front matter D 2005 Elsevier B.V. All rights reserved. doi:10.1016/j.petrol.2005.05.004 * Corresponding author. Tel.: +55 19 3788 3339; fax: +55 19 3289 4916. E-mail address: morooka@dep.fem.unicamp.br (C.K. Morooka). Journal of Petroleum Science and Engineering 49 (2005) 223 – 238 www.elsevier.com/locate/petrol