Analysis of influencing factors of wellbore pressure imbalance based on BP-DEMATEL-ISM model

Wellbore pressure balance is essential for optimal drilling. The imbalance of wellbore pressure during drilling will easily lead to downhole complications such as kick, lost circulation, and wellbore collapse, which will seriously affect drilling efficiency. Thus, it remains a hot topic to analyze the influencing factors of wellbore pressure imbalance during the drilling process. In this article, a factor analysis method is established based on BP neural network, DEMATEL, and ISM algorithms. More specifically, the BP neural network is adopted to realize the nonlinear mapping from the input parameters to the output working conditions, based on which the direct correlation matrix between the factors is obtained. Then, based on DEMATEL and ISM algorithms, the attribute determination and hierarchy division of influencing factors can be performed through cause-effect diagram and causative network. The proposed method is applied to five exploration wells. The results indicate that the influencing factors can be divided into different levels. The key to prevent downhole complications is to manage the core influencing factors. The proposed method can extract complicated nonlinear relationship in the downhole environment by data-driven, and establish causative network of wellbore pressure imbalance, which can provide technical support and a theoretical basis for preventing downhole complications.