The development of a technology forecasting ESP failures is one of the key tasks of the oil industry today. Simple statistical methods do not allow to predict the equipment's failure and its cause, which would allow to select and conduct the planned preventive measure in time. This paper describes the methodology of ESP failure prediction developed based on field data. The main stage of the methodology is the creation of an ensemble model of machine training, the application of which allows for the taking into account of many factors and extensive experience in operating ESPs contained in field data, so considerable time has been devoted to working with them. The uniqueness of the presented work is the use of field information on well operation in Western Siberia, accumulated for the last 5-7 years from the discrete measurements of one day, in which there was a significant amount of information omission. To improve the quality of forecasting, it required multilevel pre-processing of initial data and formation of additional analytical features, which allowed improvement of the quality of predictions. The study of the developed model for the prediction of the ESP failures at different prediction horizons was carried out and it was determined that the quality of prediction increases when the interval of prediction decreases. The developed model shows the best results when predicting the ESP failure 1-3 days before its actual stop. The groups of parameters, on which the duration of failure-free operation of pumping equipment in a well depends to a great extent, have been determined this is information about the well operation mode, information about ESP operation parameters, dynamic information about complicating factors of the ESP operation and additional analytical parameters describing the processes occurring in the system "Wellbore – ESP – Tubing". The ESP failure prediction model, the development of which is described in this work, can become the basis of the decision support system, its implementation in production will allow to identify in advance the cases of possible downhole pumping equipment failure and to take timely measures based on this information. Based on the obtained results and high relevance of the problem under consideration, the main directions for further improvement of the developed methodology have been defined.

The main technology used to optimize field development is hydrodynamic modeling, which is very costly in terms of computing resources and expert time to configure the model. And in the case of brownfields, the complexity increases exponentially. The paper describes the stages of developing a hybrid geological-physical-mathematical proxy model using machine learning methods, which allows performing multivariate calculations and predicting production including various injection well operating regimes. Based on the calculations, we search for the optimal ratio of injection volume distribution to injection wells under given infrastructural constraints. The approach implemented in this work takes into account many factors (some features of the geological structure, history of field development, mutual influence of wells, etc.) and can offer optimal options for distribution of injection volumes of injection wells without performing full-scale or sector hydrodynamic simulation. To predict production, we use machine learning methods (based on decision trees and neural networks) and methods for optimizing the target functions. As a result of this research, a unified algorithm for data verification and preprocessing has been developed for feature extraction tasks and the use of deep machine learning models as input data. Various machine learning algorithms were tested and it was determined that the highest prediction accuracy is achieved by building machine learning models based on Temporal Convolutional Networks (TCN) and gradient boosting. Developed and tested an algorithm for finding the optimal allocation of injection volumes, taking into account the existing infrastructure constraints. Different optimization algorithms are tested. It is determined that the choice and setting of boundary conditions is critical for optimization algorithms in this problem. An integrated approach was tested on terrigenous formations of the West Siberian field, where the developed algorithm showed effectiveness.

No abstract

No abstract

Geosteering is an important area and its quality determines the efficiency of formation drilling by horizontal wells, which directly affects the project NPV. This paper presents the automated geosteering optimization platform which is based on live well data. The platform implements online corrections of the geological model and forecasts well performance from the target reservoir. The system prepares recommendations of the best reservoir production interval and the direction for horizontal well placements based on reservoir performance analytics. This paper describes the stages of developing a comprehensive system using machine-learning methods, which allows multivariate calculations to refine and predict the geological model. Based on the calculations, a search for the optimal location of a horizontal well to maximize production is carried out. The approach realized in the work takes into account many factors (some specific features of geological structure, history of field development, wells interference, etc.) and can offer optimum horizontal well placement options without performing full-scale or sector hydrodynamic simulation. Machine learning methods (based on decision trees and neural networks) and target function optimization methods are used for geological model refinement and forecasting as well as for selection of optimum interval of well placement. As the result of researches we have developed the complex system including modules of data verification and preprocessing, automatic inter-well correlation, optimization and target interval selection. The system was tested while drilling hydrocarbons in the Western Siberian fields, where the developed approach showed efficiency.