Detection and mitigation of risks associated with pipeline releases

Informations projet

N° de convention de subvention: EV5V0419

Projet clôturé

Date de début 1 Septembre 1994

Date de fin 31 Decembre 1997

Financé au titre de

• Specific research and technological development programme (EEC) in the field of the environment, 1990-1994

Coût total

Aucune donnée

Contribution de l’UE

Aucune donnée

Coordonné par

SNAMPROGETTI SPA
Italy

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Résultats exploitables

DEPIRE: Neural network technique for leak detection in pipelines

Leak detection in pipelines carrying hazardous substances should ensure a fast identification of even small leaks and a low rate of spurious alarms. The research has developed a system, based on the artificial neural network technology, that receives the measured data on the line, which is able to detect leaks as small as 1% of the line operating flowrate, with a negligible rate of spurious alarms, even in the case of sensor failure or drift. The system has been developed for a line carrying ammonia and for one carrying liquefied petroleum gas, and has been tested on a small scale experimental rig. The system can be fitted to any existing pipeline, and its performances will depend on the process measurement system already installed.