Abstract：n the acoustic emission (AE) testing for tank bottom, it needs to process the signals acquiring from multi sensors mounting on the out surface of tank wall. During the signal processing procedure, the signals coming from the same AE source should be grouped as an AE event. However, because of the influence of noise signals, the traditional AE sources determine method often gets wrong AE events. In order to avoid getting wrong AE events which is combined by the signals coming from different AE sources, a signal fusion method based on cluster analysis is proposed. The method is based on the classification of AE signals recorded in each event definition time. Each class that contains three or more signals would be determined as a target event. An experiment showed that the method has strong ability to resist noise interference and has low probability of determining error AE events. Therefore, it can raise the accuracy of tank bottom corrosion evaluation.
王伟魁 李一博 杜刚 张涛 靳世久. 基于聚类分析的罐底声发射检测信号融合方法[J]. , 2012, 31(17): 181-185.
WANG Wei-kui;Li Yi-bo;DU Gang;ZHANG Tao;Jin Shi-jiu. Signal fusion method for acoustic emission testing of tank bottom based on cluster analysis. , 2012, 31(17): 181-185.
2012, Vol. 31 
