为实现采煤机截割过程中截齿磨损状态的实时在线监测,采用声发射传感器对不同磨损程度截齿截割时的声发射信号进行采集,采用小波包分析方法分析声发射信号不同频带能量的变化规律,建立能量值的样本空间,构建基于SOM神经网络的截齿磨损识别模型,实现对截齿不同磨损状态的在线监测。通过随机测试实验对截齿磨损状态识别模型进行验证,结果表明,基于小波包分析与SOM神经网络的截齿预测磨损状态识别模型识别精度较高,测试样本识别精度约95%。研究结果为准确识别截齿的磨损状态、提高采煤机的工作效率提供一种重要的技术手段。

In order to realize the real-time monitoring on the wear degree of coal shearer picks in the cutting process, the acoustic emission signals under individual wear degrees are collected via acoustic emission sensors. The wavelet packet analysis is used to analyze the trend of the signal under individual wave band,the sample space of the energy is established,and the pick wear identification model based on SOM ( Self Organizing Maps) neural network is built to realize the real-time monitoring of the pick wear degree. The model is proved via random testing experiments. The re- sults show that the accuracy of the model,which is based on wavelet packet analysis and SOM neural network,is high, and the accuracy is about 95% . The results provide an important technical mean for identifying the wear degree of picks precisely and improving the work efficiency.