基于主成分分析和BP神经网络的煤岩界面识别

Identification of coal-rock interface based on principal component analysis and BP neural network

  • 摘要: 针对现有煤岩识别方法由于提取的时域参数过多,存在识别速度慢、实时性差等问题,提出了一种基于主成分分析和BP神经网络的煤岩界面识别方法。该方法首先提取采煤机滚筒扭矩的时域信号,然后利用主成分分析方法对该时域信号进行压缩,最后将得到的最终信号输入到BP神经网络进行煤岩识别。仿真结果表明,该煤岩识别方法不仅满足了识别率,还提高了识别速度,为提高滚筒调高响应速度奠定了基础。

     

    Abstract: In view of problem of slow identification speed and bad real-time performance of current identification method of coal-rock interface because of extracting much time domain signals, an identification method based on principal component analysis and BP neural network was proposed. According to the method, time-domain signals of cutting torque of shear drum were selected at first, and then PCA method was used to compress the signals. At last, these final signals were input into BP network to identify coal-rock interface. The simulation result shows that the method can not only meet with recognition rate, but also increase identification speed, which establishes foundation for improving response of drum lifting.

     

/

返回文章
返回