摘要
将小波理论与神经网络理论相结合,建立了小波网络模型,并应用于工程实例。它避免了BP神经网络结构设计的盲目性和局部最优等非线性优化问题,大大简化了训练,具有较强的函数学习能力和推广能力。实例计算结果表明,小波网络模型具有比BP神经网络收敛速度快、预测精度高等特点,因而具有广阔的应用前景。
Wavelet neural network is a kind of neural network, which combines wavelet theory closely with neural network theory, and avoids both the blindness of framework designs for BP neural networks and the problem of nonlinear optimizations, such as local optimization. So it can greatly simplify the training of neural networks. It has better abilities in function learning and generalization. The results show that the wavelet neural network established is faster in convergence speed and more accurate in prediction than BP neural network. Therefore it has wide application prospect.
出处
《勘察科学技术》
2008年第1期40-43,共4页
Site Investigation Science and Technology
基金
华东电网有限公司科技项目No.T0501
关键词
小波网络
渗流
监控模型
wavelet network
seepage
monitoring model