摘要
基于时间序列预测思想构建了适合于煤层气井产能预测的BP神经网络模型。以潘庄CM1井为预测实例,结果表明:该模型能够较为准确地预测出煤层气井未来30天的产能变化,其产气量和产水量预测平均相对误差分别为1.35%和3.88%,从而可为煤层气井排采制度的调整提供依据。
In order to achieve the purpose of real-time dynamic monitoring and forecasting the coalbed methane well productivity, so build the BP neural network model that based on time series prediction idea suitable for coalbed methane well productivity prediction. Use Panzhuang CMlwell for forecast instance, the results show that. this model can accurately predict the pro- ductivity change of the CBM wells in the next 30 days , the average relative error of gas produc- tion and water production forecast respectively 1.35% and 3.88%, thus provide the basis for the adjustment of the coalbed methane wells drainage system.
出处
《中国煤炭》
北大核心
2012年第12期9-13,17,共6页
China Coal
基金
国家科技重大专项项目(2011ZX05034)
国家"973"项目(2009CB219605)
国家自然科学基金重点项目(40730422)
青年科学基金项目(40802032)
关键词
BP神经网络
煤层气井
产能预测
BP neural network, coalbed methane well, productivity prediction
