一种基于变权重模糊识别的调驱效果预测方法

A Prediction Method of Profile Control and Flooding Effect Based on Variable Weight Fuzzy Recognition

效果预测是进行调驱措施决策和方案设计的重要内容。提出一种基于变权重模糊识别的调驱预测方法:采用模糊数学理论,收集已施工井组参数形成原始样本,然后应用灰色关联分析方法进行主控因素分析并对样本进行降维,最后以此为基础创建非对称贴进度计算公式,进行模糊识别预测计算。将该方法以井组增油量为评价指标应用于秦皇岛油田S区块,主控影响因素依次为渗透率变异系数、初始充满度、碾平地层系数、体系总用量等,对11口井进行预测计算,有7口井预测结果在10%以内,较等权重预测方式误差率更低,提高了小样本预测准确度。

Effect prediction is an important content of profile control and flooding measure decision-making and scheme design.In this paper,a profile control and flooding prediction method based on variable weight fuzzy identification is proposed:the fuzzy mathematics theory is used to collect the parameters of the constructed well groups to form the original samples,and then the grey correlation analysis method is used to analyze the main control factors and reduce the dimension of the samples.Finally,based on this,an asymmetric sticking progress calculation formula is created for fuzzy identification and prediction calculation.The method is applied to block s of Qinhuangdao oilfield with the oil increase of well group as the evaluation index.The main influencing factors are permeability variation coefficient,initial fullness,flattening formation coefficient and total system consumption.The prediction calculation of 11 wells shows that the prediction results of 7 wells are within 10%,which is lower than the error rate of equal weight prediction,and improves the prediction accuracy of small samples.