基于小波和独立分量分析的煤矸界面识别

Coal and Rock Recognition Based on Wavelet Denosing and Independent Component Analysis

为了解决综采工作面放顶煤开采过程中煤矸界面识别问题,给出了一种基于小波去噪和独立分量分析相结合的煤矸放落声信号特征提取算法。利用小波分析对传声器实时采集的声信号进行降噪处理,提高信噪比。利用独立分量分析方法对煤矸混合声信号进行盲源分离,分别提取出煤和矸石的独立声谱特征信号。选取该信号的统计特征值作为神经网络分类器的输入向量,对顶煤放落过程中的混矸状态进行识别。实验表明,给出的方法提高了声信号的信噪比,有利于矸石声信号的成功分离;采用BP神经网络准确地识别出了放煤过程中的矸石下落状态。

To the problem of coal and rock recognition on fully mechanized mining face in top-coal caving, proposed an acoustic signal feature extraction algorithm of coal and rock is proposes based on the combination of wavelet analysis and independent component analysis （ICA） . The wavelet analysis is utilized to de-noise the acoustic signal of sensor and increase to the ratio of signal to noise. ICA method is used to separate the preprocessed acoustic signal and extract independent component of coal and rock. The feature signals are served as the input parameter of BP neural network to identify the content of rock in top-coal caving. Experimental result shows that the approach is effective and gives the high recognition rate.