CLUSTERING OF LOCALIZED ACOUSTIC EMISSION SOURCES BY THE DBSCAN ALGORITHM IN SEPARATORS

Abstract

In this paper, the method for locating sources of acoustic emission by approximate calculation of potential coordinates using a grid superimposed on the area around the sensors that detected the wave was proposed. Various noises such as electromagnetic pulses and other external noises were removed from input data. The DBSCAN clustering algorithm was applied. The results were compared with the real state of the object under study after additional control. Analytical and practical research points to the possibility of using the presented method as a tool for determining the coordinates of defect development points and wave velocity.

Keywords

• acoustic emission
• location
• defects
• approximate calculation
• clusterization
• pressure vessel