How Routine Reservoir Surveillance with Neural Networks and Simplified Reservoir Models can Convert Data into Information
- Gert J. de Jonge (Chevron Texaco) | Michael Stundner (Decision Team - Software)
- Document ID
- Society of Petroleum Engineers
- European Petroleum Conference, 29-31 October, Aberdeen, United Kingdom
- Publication Date
- Document Type
- Conference Paper
- 2002. Society of Petroleum Engineers
- 5.6.4 Drillstem/Well Testing, 5.5.8 History Matching, 5.6.11 Reservoir monitoring with permanent sensors, 5.1.5 Geologic Modeling, 7.1.5 Portfolio Analysis, Management and Optimization, 4.3.4 Scale, 5.1.1 Exploration, Development, Structural Geology, 7.6.6 Artificial Intelligence, 2 Well Completion, 7.6.1 Knowledge Management, 2.3 Completion Monitoring Systems/Intelligent Wells, 5.1.2 Faults and Fracture Characterisation, 3.2.2 Downhole intervention and remediation (including wireline and coiled tubing), 3 Production and Well Operations, 6.1.5 Human Resources, Competence and Training, 3.3 Well & Reservoir Surveillance and Monitoring, 5.5 Reservoir Simulation, 7.6.4 Data Mining, 4.4.2 SCADA
- 1 in the last 30 days
- 955 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
Current levels of Reservoir Surveillance technology associated with intelligent well completions, such as fibre optics and permanent downhole gauges, create an increasing flow of data.
Conventional routine Reservoir Surveillance tools do not help the knowledge worker anymore to cope with high-frequency real-time data. Overloaded with data handling work, the knowledge worker in our industry is not capable to reveal the great potential inherent in this data.
A radical different work process and new applications of Data Mining technologies are presented to support the industry's next goal - The Smart Field.
A learning Data Mining approach is presented to detect discrepancies from expected trends and patterns. These trends and discrepancies are then translated into business rules to enable the closed-loop control of oil and gas assets.
Lessons learned are presented and necessary future developments are identified.
The reservoir's response on the applied production strategy is measured with dramatically increasing resolution in time and space.
Conventional reservoir modeling techniques like numerical reservoir simulation were developed to predict reservoir performance with a minimum of individual well production information (i.e. monthly data). While these well specific performance data become available at a magnitude of 10.000 to 100.000 (e.g., 10-seconds data), CPU time consumption and project turnaround time of numerical simulation models do not allow this type of models to provide results in real-time.
Reservoir Surveillance can play a more important role to meet the industry's requirements for real-time decision support to control Smart Fields if it can overcome the following problems:
The industry is facing problems with data overload and data delivery
This is coupled with the inability to deliver the proper data in a timely fashion to the end users
Management of vast quantities of real-time, sporadic and static data available to asset managers makes the task of creating value through production optimization almost impossible today
Emerging technologies and new working processes are needed to be designed to make better decisions faster
A Reservoir Surveillance tool therefore should:
anticipate the actual reservoir performance and recovery mechanisms which will likely deviate from the planned model
identify any discrepancies in performance as early as possible
provide information regarding the cause of these deviations
use all data available to identify these discrepancies
not only include data acquisition and data visualization, but also decision support tools
An "Intelligent Operations" concept was developed to meet these requirements. Data Mining methods like Back Propagation Neural Networks, Self-Organizing Maps together with Expert Systems and reservoir modeling tools were implemented in a software package.
One of the main objectives is to save time in the continuous Reservoir Surveillance process. As a first step, present work processes were analyzed and improvements were developed before certain technologies were introduced into the concept.
The necessary change in Reservoir Surveillance work processes implies that the involved knowledge workers will need to acquire new skillsets. Furthermore, work processes and technologies being applied in other industries have been evaluated as part of the project scope.
|File Size||1 MB||Number of Pages||13|