The invention discloses a CS-MUSIC-based mine hoist fault source positioning analysis method. The method comprises the following steps: preprocessing a multi-channel mine hoist audio signal; mFCC characteristic parameters of audio signals are extracted, secondary framing is carried out on the fault audio signals, characteristic decomposition is carried out on a covariance matrix, and fault identification and the orientation of the fault audio signals are finally realized in combination with a frequency estimation function of MUSIC. And the CS algorithm is used for optimizing the MUSIC positioning result, so that the positioning accuracy is remarkably improved. The method has many advantages, the recognition algorithm and the positioning algorithm are combined, the positioning result is optimized through the CS, and compared with a traditional positioning method, the method has the advantages of being high in real-time performance, easy and convenient to operate and high in positioning algorithm result accuracy.
本发明公开了一种基于CS‑MUSIC矿井提升机故障源定位分析方法,包括对多通道的矿井提升机音频信号进行预处理;通过提取音频信号的MFCC特征参数并对故障的音频信号进行二次分帧、对协方差矩阵进行特征分解,结合MUSIC的频估计函数,最终实现故障识别和故障音频信号的方位。使用CS算法对MUSIC定位结果进行寻优,显著提高了定位的精准率。本发明具有诸多优势,采用了识别和定位算法相结合并通过CS对定位结果进行寻优,与传统的定位方法相比,具有实时性高、操作简便、定位算法结果准确率高的优势。
CS-MUSIC-based mine hoist fault source positioning analysis method
一种基于CS-MUSIC矿井提升机故障源定位分析方法
2022-07-22
Patent
Electronic Resource
Chinese
MFCC-CNN-based mine hoist fault acoustic analysis method
European Patent Office | 2021
|Engineering Index Backfile | 1949
|