Combining Spatial Filtering and Sparse Filtering for Coaxial-Moving Sound Source Separation, Enhancement and Fault Diagnosis

IEEE Access

Kesai Ouyang¹  Wei Xiong¹  Qingbo He²  Zhike Peng² 

[1] Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, China;State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai, China;

关键词: Moving sound source;    spatial filtering;    sparse filtering;    source separation;    signal enhancement;    fault diagnosis;   

DOI  :  10.1109/ACCESS.2019.2900229

来源: DOAJ

【 摘 要 】

The wayside acoustic detector system is a potential technique in ensuring the safety of traveling vehicles. However, multisource aliasing and Doppler distortion in acquired acoustic signals decrease the accuracy of machine diagnosis. The conventional multisource separation schemes fail to solve the coaxial-moving sound source (CMSS) problem by constructing time-frequency filters and designing one-dimensional time-varying spatial filters. To address this issue, this paper combines spatial filtering with sparse filtering to solve this problem. Spatial filtering could suppress but not eliminate undesired sources. Sparse filtering has no capability of coping with non-stationary signals with Doppler distortion. The combination of spatial filtering and sparse filtering could make up their shortcomings and effectively solve the CMSS problem. The proposed scheme has two main advantages of eliminating residual interferences completely and suppressing background noise effectively. The simulation and experimental cases verify the effectiveness of the proposed method. The results indicate the potential of the proposed method to improve the performance of wayside acoustic detector systems.

【 授权许可】

Unknown