RT info:eu-repo/semantics/article
T1 Time windows: the key to improving the early detection of fuel leaks in petrol stations
A1 Sigut Saavedra, Marta
A1 Alayón Miranda, Silvia
A1 Arnay del Arco, Rafael
A1 Toledo Delgado, Pedro Antonio
A2 Ingeniería Informática y de Sistemas
K1 Machine learning; Two-classclassifiers; Time windows; Fuel leaks; Inventory reconciliation
AB In this paper, the authors propose the use of time windows to improve the detection of fuel leaks in petrolstations. They employ two-class supervised classifiers that work with feature sets containing representativevariables taken from station inventory books that indicate the presence of leaks. Fuel leaks in petrol stations withunderground tanks pose a serious problem from an environmental standpoint. Large leaks are very evident, andare therefore detected quickly without the need to use a specific procedure. Small leaks, however, tend to gounnoticed, and if no detection techniques are employed, they are only identified once environmental damage hasbeen done. This makes detecting the leak in the shortest time possible as important as ascertaining when the leakstarted. The authors show how the use of time windows, which entails having the classifier work with information accumulated over several days, can be used to efficiently resolve the proposed problem, fully complying with the applicable regulation.
SN 0925-7535
YR 2020
FD 2020
LK http://riull.ull.es/xmlui/handle/915/34798
UL http://riull.ull.es/xmlui/handle/915/34798
LA en
DS Repositorio institucional de la Universidad de La Laguna
RD 11-may-2024