Intelligent Engineering Systems through Artificial Neural Networks, Volume 16
106 High-Pressure Gas Leak Detection Proof Experiment Using Chaos Information Criteria
Download citation file:
- Ris (Zotero)
- Reference Manager
In a petroleum refining plant with a large number of high-pressure facilities, high-pressure gas leaks resulting from equipment failures can engender disasters. To prevent such accidents, technologies for early detection of leak sounds and appropriate countermeasures are indispensable. A previous work proposed chaos information criteria based on a trajectory parallel measure to analyze dynamics of acoustic time series data. That paper reported the effectiveness of chaos information criteria on high-pressure gas leak detection. This paper reports an experiment for confirmation that was carried out at the platformate distillation unit of Idemitsu Kosan Chiba refinery. Nitrogen gas was leaked artificially at nine different locations. We analyzed acoustic time series data observed using eight microphones installed in different places. Results demonstrate that gas leak detection is possible regardless of the microphone position.