摘要
针对煤层底板突水系统为一非线性动力学系统的特性,并在考察目前煤层底板突水预测方法的基础上,给出利用小波神经网络对煤层底板突水进行预测的可行性和优越性;阐述了小波神经网络的基本原理;提出和分析了基于小波神经网络的煤层底板突水预测模型及算法;并通过实例证明,应用小波神经网络解决煤层底板突水预测的可行性和优越性。研究及实践表明:小波神经网络的预测精度更高、更准确。
Directing at the non-linear dynamic characteristic of water inrush from coal floor and the weakness analysis of current forecast methods for water inrush from coal floor, a new forecast method is raised based on wavelet neural network. Firstly basic principles of wavelet neural network are described in this paper, then a forecast model for water inrush from coal floor based on wavelet neural network is raised and analyzed, finally an example is illustrated to verify the feasibility and superiority of this method. Conclusion shows that the forecast result based on wavelet neural network is more precise, which is more beneficial to the prevention and control of water inrush from coal floor in coal layer.
出处
《中国安全科学学报》
CAS
CSCD
2006年第11期24-28,共5页
China Safety Science Journal
关键词
小波
神经网络
底板突水
非线性
预测
BP神经网络
wavelet
neural network
water inrush from seam floor
non-linear
forecast back-propagation neural network
