Data analysis and event alarms are essential part of any production monitoring system. Most often standard event alarms in production monitoring are based on selected measurements. Oil rate, pump intake pressure and temperature, water cut are some of them. Less often alarms are based on calculated values, for example production increase potential. However, they always indicate something goes wrong but never indicate why. Alarms can indicate there are deviations from planned values but do not give any clue about deviation reasons. Production engineer should investigate deviation reasons himself. From author's point of view, smart alarms are the tool to overcome these challenges. Smart alarms in production monitoring system should be able to determine reasons of parameters deviation and to predict deviations before they become critical. Smart alarms should use all the information available in order to increase estimation and prediction accuracy. They should classify and rank problems and problem reasons identified from potential future problems to problems required immediate reactions. Smart alarms should give reasonable results based on partial data, and should be able to analyze thousands wells per day. Primary goal for smart alarm tool is to automate business process for 80% of well stock working in a standard way and to allow engineers to concentrate on 20% of complicated wells. Smart alarm tool based on Bayesian network framework is under development and pilot implementation in TNK BP of Samotlorskoe oil field. Smart alarm tool is a part of corporate production monitoring system. This paper discusses Bayesian network application for engineering tool development and results of pilot implementation including algorithm accuracy, lessons learned and development plans.

No abstract

Summary The Samotlor field developed by TNK-BP is the largest oilfield in Russia. The first oil in the Samotlor field was produced in the 1960s. Today, the operating production well stock exceeds 8700, most of them equipped with ESP. At fields with such a high number of wells, every minute there are thousands of events that should be correctly processed to make a correct control decision. Efficient production requires prompt data, fast processing of that data and an appropriate response. By introducing an integrated real-time production monitoring, analysis and control system it is possible to eliminate the process gaps and improve cost-efficiency. To introduce the production optimization process in real time, a three-phase multidisciplinary project was initiated: (1) installation of the submersible telemetry transducers at the ESP's and data transfer to the workstations; (2) implementation of the well remote control function; (3) implementation of the real-time production monitoring system. During the first phase, 60% of the wells were equipped with the submersible telemetry transducers, 100% of data was transferred to the SCADA. Implementation of the second phase resulted in creating the functions of the ESP remote control. These functions were implemented in the SCADA software, which enables the ESP start up, shutdown, frequency variation and change of the key operation parameters. During the third phase, a real-time production monitoring analytical system was implemented based on the exception criteria. During the fourth phase of the project, the approaches implemented for the production well stock will be extended to the surface facilities (oil processing facilities, reservoir pressure maintenance system), injection well stock, pipelines, which will be one more step in the implementation of the intelligent field concept. For mature fields, such as Samotlor, efficient operation is extremely important. The use of the real-time production optimization process allows for improvement of profitability and extension of field life. This approach is especially relevant in the development of Arctic oilfields as it allows for streamlined control of production process with minimum personnel directly on site.

Nowadays the "Intelligent Field" concept is being actively implemented in TNK-BP, with Samotlorskoe field (OJSC "Samotlorneftegas") at the forefront in this conceptual area. The term "intelligent field" means arrangement of additional value of oil and gas asset by forming a cycle of gathering of qualitative data, treatment, modeling, decision making and their prompt performance. The concept is implemented step by step. At the first stage of implementation in 2009 – 2010 the main focus was on its technical constituent, the following technologies were reviewed and implemented: –use of different primary transducers for real-time data receiving;–upgrading SCADA, including use of remote control;–use of different real-time expert and simulating systems. Implementation of such technologies on a large scale adds value to the process of decision-making and oil production control. It has become evident that efficient implementation of technologies is impossible without changing production control processes both at the technological and organizational level. It also becomes essential to organize the process of implementation of such changes. In 2011 – 2012, in addition to the technical phase, the organizational phase was started in parallel. The issues related to technology influence on the current business processes and organizational changes required for efficient use of the technology were addressed to, the personnel's objectives were reconsidered and the team for implementation of changes was formed. The paper outlines technical aspects of technologies implementation and evaluates their influence on oil production process. The issues related to changes in organizational structure and business processes relevant to implementation of "intelligent field" technologies are presented. The effect resultant from technology implementation is evaluated.

The current problem related to poor-quality control of artificial lift operational parameters can be solved by means of development and application or real-time monitoring, control and analysis systems. As one way to solve this problem, TNK-BP has implemented the real-time SRP monitoring system. The SRP monitoring system is a specialized SCADA and expert system for SRP. The system displays and analyzes the information from the controllers, gives a possibility of remote control by means of controllers on the wells. SRP controllers are installed on the well sites in order to gather and analyze the data received from the transducers for SRP monitoring and operational control. The controller technology is based on processing a dynagraph for each pump jack stroke, which enables to ensure SRP control as per the rated parameters settings, diagnose the SRP condition, change the operational mode depending on the influx from the formation. To date the flow rates are measured periodically (once or twice a day), which is not enough. The monitoring and diagnostics system enables to receive real-time pressure data from the submersible transducer and use this information for automatic calculation of "instantaneous" flow rate. For this purpose the Company carries out pilot projects to try out the submersible telemetry systems (Russian-made) with additional transducers that record pressure and fluid temperature at the submersible pump discharge end and their transmittal to the external devices. Russian manufacturers of submersible telemetry are taking initial steps in producing telemetry systems with additional transducers. Also, in field development the oil companies face the problem of solids flow-back from the wells. The use of ultrasonic transducer to evaluate amounts of solids flown back from the well and their type is the most advanced practice. Ultrasonic transducer for solids detection has the following technological advantage: it enables to ensure optimal rate for the complex wells stock by means of data-based control and prompt real-time response to changes. In this paper the authors described application of such systems.