一种基于模糊融合的分布式传声器阵列瞬态声识别方法
By employing a fuzzy fusion-based distributed microphone array method and utilizing time-domain beamforming and signal energy weighting techniques, the problem of identifying and locating transient sounds in large-scale industrial environments was solved, achieving high-precision sound source localization.
CN121385800BActive Publication Date: 2026-07-17KUNMING UNIV OF SCI & TECH
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- KUNMING UNIV OF SCI & TECH
- Filing Date
- 2025-10-24
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
In large-scale industrial environments, a single microphone array struggles to effectively identify and locate transient sounds, resulting in insufficient fault detection accuracy.
Method used
A distributed microphone array method based on fuzzy fusion is adopted. The direction of the sound source is estimated by time-domain beamforming technology, the sound source membership function and performance membership function are constructed, and the sound source is located by combining fuzzy set operation and signal energy weighting.
Benefits of technology
It improves the positioning accuracy of transient sound, enhances the fault detection capability in a wide range of industrial environments, and reduces the impact of noise interference.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121385800B_ABST
Abstract
本发明公开了一种基于模糊融合的分布式传声器阵列瞬态声识别方法，属机械设备状态监测及故障诊断领域。本发明基于子阵列特征和定位结果建立隶属函数。首先，传声器子阵列通过时域波束形成估计声源方向，结合波束能量分布，建立声源隶属函数；仿真分析子阵列定位特性，结合主瓣宽度分布，建立性能隶属函数。将两个隶属函数聚合输出为一个模糊集。再根据子阵列接收到信号能量的强弱对模糊集进行加权，并融合所有子阵列模糊集，最后将融合结果去模糊处理得到精确的声源位置，与单阵列定位结果相比，本发明提高了瞬态声定位精度，同时，实现大范围空间下瞬态声定位。
Need to check novelty before this filing date? Find Prior Art