A two-level adaptive chirp mode decomposition and tangent entropy in estimation of single-valued neutrosophic cross-entropy for detecting impeller defects in centrifugal pump

Abstract

A novel approach for identifying the impeller defects in the centrifugal pump has been demonstrated by extracting the single-valued neutrosophic cross-entropy (SVNCE) of adaptive chirp mode decomposition (ACMD). ACMD decomposes the acoustic signals into different modes by estimating the instantaneous frequencies. The ACMD is incorporated with novel tangent entropy which helps in selecting the prominent modes and enhances the performance of ACMD. The energy of each prominent mode is computed under different health conditions of the impeller. The energy eigen values set the energy interval ranges for unknown impeller defect conditions which are further converted into single-valued neutrosophic sets (SVNSs). The minimum argument principle utilizes the least SVNCE values between SVNSs of testing samples (obtained from unknown impeller conditions) and SVNSs of training samples (obtained from known impeller conditions) to recognize the different impeller defects of the pump. The proposed scheme has been compared with other techniques such as EEMD, VMD, permutation entropy and corrected conditional entropy. The results of the comparison suggested the superiority of the proposed method.