Cluster Discriminant Prediction of Oil Well Production Based on Mahalanobis Distance. (January 2020)

• Record Type: Journal Article
• Authors: Huang, Bo; Kang, Yunwei; Chen, Ang; Guo, Zixi; Sun, Yicheng
• Is Part Of: Journal of physics. Volume 1437(2020)
• Publication Date: 2020-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1437/1/012089
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: The cost of oil field drilling engineering is very high. Effective well selection and formation selection will avoid waste of energy and resources. Aiming at the problem of well selection and reservoir selection in oilfield, this paper presents a clustering discriminant prediction method for oil well production based on Mahalanobis distance. Based on the field data of Xinjiang oilfield, the main control factors with greater influence are selected after data pretreatment in this paper. Then we randomly divide the data into training data set and prediction data set, and establish a discriminant model of oil well classification based on Mahalanobis distance. Finally, the model is used to predict the production of oil wells in the forecasting data set, and the prediction accuracy reaches 87.5%.