用神经网络滚动模型预测天然气的生产能力

THE PREDICTION OF PRODU CTIVE CAPACITY OP NATURAL GAS USING THE ROLLING MODEL OF NEURAL NETWORK

本文介绍了滚动神经网络模型，引入了有序导数的概念，讨论了此网络的实现过程。提出了迭代滚动递推ＢＰ神经网络的天然气产量预测模型，建立了气藏稳产期和递减期天然气生产能力预测的迭代递推滚动ＢＰ网络的数学模型通过验证表明，该模型计算结果达到了数值模拟的精度，对新区的天然气生产能力可做到较为精确的预测。

This paper introduces the rolling model of neural network and the concept of ordered derivatives' Theimplementation of this network is discussed in this paper' We put forward the prediction of productive capacity of natural sas using iterative rolling BP network and build up the mathematic model of productive Capacityin stead period and decreasing period 'sinS the iterratiye rolling BP network.Through verified,the model canget the result as exsactly as numerical simulation.This model overcomes the rudeness of traditional prediction' the productive capacity of natural sas and can predict more exactly the productive capacity of natural gas'traditional prediction