Major accidents at production facilities can be detected from a distance in real time through “sounds”

Production facilities:- A significant national advancement has been made with the development of a new technology that can pinpoint the location of pipeline leakages in real time by detecting the sounds that they emit. This technology is crucial for averting major accidents at production facilities.

The research team lead by Senior Researcher Jung-Han Woo of the Korea Institute of Machinery and Materials (President Seog-Hyeon Ryu, hereinafter referred to as KIMM), an institute under the jurisdiction of the Ministry of Science and ICT, has developed, for the first time in the country, a noble technology that can detect the location of pipeline leaks from afar on a real-time basis by using acoustic sensors.

The KIMM’s research team has developed a system that can promptly determine the location of a pipeline leak by strategically placing four-channel acoustic sensor modules capable of detecting the direction of the sound. By correlating the location data from a three-dimensional virtual space and surveillance cameras within the system, facility workers can swiftly identify leak locations and respond effectively within the crucial first hour of the incident.

Previously, leakage detection relied on acoustic pressure, which measures sound magnitude. Typically, identifying the exact location of a leak required proximity, potentially compromising worker safety. Moreover, this method necessitated the use of expensive equipment featuring more than 100 channels of acoustic sensors per module.

The core of the new technology developed by the KIMM lies in its signal processing technique that utilizes acoustic intensity*. This technique significantly reduces detection errors in environments with substantial reflections or reverberations by employing a statistical algorithm for removal of abnormal data. It allows for leak detection with an error margin of less than one (1) meter (estimated error within three (3) degrees), and the location can be verified in a three-dimensional virtual space within the system, facilitating prompt response to accidents caused by leakage.

This innovative technology reduces the scale of the required equipment, decreasing the number of acoustic sensors per module from over 100 channels to just four (4). This adjustment results in equipment cost reductions of more than 30 percent compared to conventional systems. Additionally, with the capability to monitor leak detection outcomes in real-time from a distance, leaks can be identified at the early stage of an accident, allowing for immediate intervention.

Senior Researcher Jung-Han Woo of the KIMM commented, “This three-dimensional acoustic intensity-based leak detection technology is incredibly valuable for pinpointing the origins of noises at various sites and analyzing their characteristics, thus aiding in determining the causes of accidents.” He further noted, “The technology can expanded to include preemptive response to incidents and accidents, and can also be applied to a broad spectrum of industrial sectors, including alarm and surveillance systems for crime prevention.”

This research was facilitated by the project for the “dArtificial intelligence based predictive diagnosis and damage management technology” one of the basic projects of the KIMM. Newswise/SP