Among industrial assets, pipelines are critical for their role as carriers of fluid and gas resources. Defects such as fatigue cracks, stress cracks, corrosion cracks, and structural discontinuities can create leaks in the pipeline leading to severe repercussions such as waste of resources, a threat to public safety, and economic losses. Hence, early leak detection and localisation are of primary importance.
A new collaborative study by Akhand Rai, Assistant Professor, School of Engineering and Applied Science, with researchers from Ulsan University and PD Technology, South Korea, proposed the acoustic emissions (AE) technique to detect and localise leaks. AE testing is a non-destructive testing technique that detects and monitors the release of ultrasonic stress waves from localised sources when a material deforms under stress. He says, “Supervised techniques need prior knowledge about pipeline failure for training purposes. To address this challenge, our study proposes a new pipeline leak detection method independent of prior knowledge. Artificial intelligence-based supervised methods are a popular adoption for pipeline leak identification.” In the past, efforts have been made to detect and locate leaks in pipelines using nondestructive testing methods such as pressure monitoring, ultrasonic monitoring, reflectometry in the time domain, accelerometer-based monitoring, and AE-based monitoring. Professor Rai adds, “AE technology is the most preferred among the nondestructive testing techniques because of its response in real-time, high sensitivity, rapid recognition of leaks, and easy installation.” The work was recently published in the journal, Mechanical Systems and Signal Processing.
Siddharth Agrawal Wins Best Conference Paper Award for his Study on Identification of Truck Licence Plates for Weighbridge Automation
Ahmedabad Professors Receive Grant from the Department of Atomic Energy for Research on Person Identification in Unconstrained Surveillance