摘要
为了准确识别采煤机截割状态,提出了一种基于小波包分解和学习向量量化(LVQ)神经网络的模式识别方法。将振动信号进行小波包分解,实现振动信号的预处理,得到若干个子频带。在此基础上,计算各个频带的方差,并将其作为特征向量。然后将计算得到的频带方差作为特征向量,输入到LVQ神经网络进行采煤机煤岩截割状态识别。通过实验验证了该方法的有效性,实验结果表明:该方法能够实现采煤机典型煤岩截割状态的识别,平均识别准确率较高,对实现综采工作面的"无人化"具有重要意义。
In order to accurately recognize the cutting state of shearer,a state recognition method based on wavelet packet decomposition and learning vector quantization(LVQ)neural network is proposed.The vibration signal is decomposed by wavelet packet to pre-process the vibration signal and obtain several sub-bands.On this basis,the variance of each frequency band is calculated and used as the eigenvector.Then,the calculated frequency band variance is taken as the eigenvector and input to LVQ neural network to recognize the coal cutting state of shearer.The experimental results show that the method can realize the recognition of typical coal rock cutting state of shearer,and the average recognition accuracy is high,which is of great significance to realize the unmanned fully mechanized working face.
作者
李福涛
王忠宾
司垒
谭超
梁斌
LI Fu-tao;WANG Zhong-bin;SI Lei;TAN Chao;LIANG Bin(School of Mechatronic Engineering,China University of Mining and Technology,Xuzhou 221116,China;Xuhai College,China University of Mining and Technology,Xuzhou 221116,China)
出处
《煤炭工程》
北大核心
2022年第1期123-127,共5页
Coal Engineering
基金
江苏省高等学校自然科学研究面上项目(19KJB510014)。
关键词
综采工作面
煤岩截割状态
小波包
频带方差
LVQ神经网络
fully mechanized working face
coal and rock cutting state
wavelet packet
frequency band variance
LVQ neural network
