神经网络优化组合预测模型在油气产量预测中的应用

Application of a neural network optimization combinatorial prediction model to oil-gas yield forecasting

采用组合预测方法对油气产量预测进行研究,首先选取油藏工程领域多种油气产量预测模型建立组合预测模型库,基于权系数的时效性,利用三层前馈BP神经网络建立油气产量变权组合预测模型,并进行实例分析,结果表明该方法能提高预测精度,增强预测模型的实用性.

This paper is organized as follows:making use of combinatorial prediction method to study the forecast of oil and gas yield,choosing several prediction models to establish a model setting, on the basis of timing efficiency of weight,taking the advantage of BP to establish the weight-changing combinatorial prediction model,and then,taking an instance analysis,and the result shows that this method can improve the accuracy of prediction and increase the practicality of this prediction model.