节点文献
基于多元线性回归和BP神经网络的单井能力预测
Single Well Capacity Prediction Based on Multiple Linear Regression and Back Propagation Neural Network
【摘要】 为提高单井能力预测的精度和可靠性,提出利用地震属性数据,结合多元线性回归方法和BP神经网络方法进行预测。首先提取了研究区目的层的地震属性,然后利用多元线性回归方法和BP神经网络方法建立了单井能力与地质、地震属性之间的函数关系,得出了半定量-定量化的单井产量设计模型,并且验证了模型的预测结果。结果显示:单井能力预测精度总体在80%以上,其中BP神经网络模型预测精度更高,吻合度更好,证明了利用多种地震属性联合预测单井产能是一种卓有成效的方法。
【Abstract】 In order to improve the accuracy and reliability of the prediction of single well capability,raised a idea of prediction using seismic attribute data,combined with multiple linear regression method and back propagation neural network method. Firstly,the seismic attributes of the target layer in the study area are extracted,and then the functional relationship between the single well capability and geological and seismic attributes is established by using the multiple linear regression method and the BP neural network method. The semi-quantification-quantitative single well production design model is obtained,and the prediction results of the model are verified. The results show that the prediction accuracy of single well capability is more than 80%,in which the BP neural network model has higher prediction accuracy and better coincidence. It is proved that using multiple seismic attributes to predict single well productivity is an effective method.
【Key words】 daily oil production level; seismic attributes; correlation analysis; BP neural network; multiple linear regression;
- 【文献出处】 科学技术与工程 ,Science Technology and Engineering , 编辑部邮箱 ,2019年29期
- 【分类号】P631.4;TE319
- 【被引频次】7
- 【下载频次】408