Loudspeaker rub&buzz automatic classification with combined variational mode decomposition and energy entropy  

作　　者：ZHOU Jinglei YAN Ting DING Fang 

机构地区：[1]School of Electronics and Information,Xi'an Polytechnic University,Xi'an 710600

出　　处：《Chinese Journal of Acoustics》2021年第4期539-552,共14页声学学报（英文版）

基　　金：the Youth Project of National Natural Science Foundation of China(61901347);the Science and Technology Planning Project of Shaanxi Provincial Department of Educa-tion(18JK0342).

摘　　要：An automatic classification method of loudspeaker rub&buzz based on variational mode decomposition(VMD),energy entropy,and genetic algorithm-support vector machine(GA-SVM)is proposed to classify the loudspeaker rub&buzz more accurately and automatically.Firstly,the radiated acoustical signals of loudspeaker units were decomposed by VMD.Then,the energy entropy of each variational mode function(VMF)was extracted and statistically analyzed.Finally,the loudspeaker rub&buzz was judged by GA-SVM.The experimental results showed that VAID energy entropy could characterize features of loudspeaker rub&buzz more accurately compared with VMD time-frequency entropy,empirical mode decomposition(EMD)energy entropy,and EMD time-frequency entropy.The average recognition rate of VMD energy entropy of 96.3%was higher than those of the three other methods,which were 18.3%,24.0%,and 54.3%,respectively.

关 键 词：ENTROPY ENTROPY VARIATIONAL 

分 类 号：TN643[电子电信—电路与系统] TP18[自动化与计算机技术—控制理论与控制工程]