Turning an Offshore Analog Field into Digital Using Artificial Intelligence
- Roberto Espinoza (Dragon Oil) | Jimmy Thatcher (Digital Energy) | Morgan Eldred (Digital Energy)
- Document ID
- Society of Petroleum Engineers
- SPE Middle East Oil and Gas Show and Conference, 18-21 March, Manama, Bahrain
- Publication Date
- Document Type
- Conference Paper
- 2019. Society of Petroleum Engineers
- 7 Management and Information, 7.6 Information Management and Systems, 7.6.6 Artificial Intelligence
- virtual analog data, artificial intelligence, Computer vision
- 24 in the last 30 days
- 27 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
Replacing all analogue sensors in the oil field is very costly and normally only a fraction of them is done. Currently, there is no cost-effective method to efficiently, reliably and accurately capture analogue meter readings in a digital format. Operators are then left with only two options: either replace them with digital (high capex) or continue with manual gathering (high opex). This paper shows how computer vision and artificial intelligence was used for the first time to capture analogue field gauges data with dramatic reduction of cost and increase reliability.
This unique solution was implemented in the Cheleken Oil field, Caspian Sea, Turkmenistan. In the offshore platforms, only low-cost cameras were necessary, and gauges were identified using QR codes. During the field trial, operators were only required to take pictures of the gauges at a given interval of time and upload the photos to the application. After an innovative process of calibration, the acquired images were processed using artificial intelligence and deep learning computer vision.
Routine manually gathered data was compared with data collected using this solution with the following observations made:
Date/time: Operators usually round time. The solution described records time on the captured pictures automatically.
Value: Manually gathered data is subject to reading, typing and transcription errors. This solution has no error (provided a good calibration is done).
Data Modification: Data gathered automatically with this solution has no human intervention. Therefore, is not subject to alteration, copying or duplication.
Data collection with pictures was completed in 1/10th of the time that manual processes take.
The business benefits from quicker operator rounds with improved accuracy in meter reading data, and time stamps. The administrative burden for operators of filling in extensive spreadsheets which are prone to error was reduced, this allowed them to collect more meter readings or be reassigned by management to more important scopes of work that bring greater value to the business. Once more it was proved that "a picture is worth a thousand words ".
This solution offers an excellent opportunity for digitizing the marginal section of the field and provides a unique way to turn all analogue data into digital with a very low cost of implementation, on an infinitely scalable platform that is vendor agnostic and simple to manage.
|File Size||1 MB||Number of Pages||11|
Espinoza R. 2015. Digital Oil Field Powered with New Empirical Equations for Oil Rate Prediction. Presented at the SPE Middle East Intelligent Oil & Gas Conference & Exhibition, Abu Dhabi, UAE, 15–16 September. SPE- 176750-MS. 10.2118/176750-MS
Espinoza R. and Rivadeneira I. 2015. Improvement of Decision-Making Cycle by Introduction of a Centralized Data Gathering System - Offshore field case from Turkmenistan. Presented at the Abu Dhabi International Petroleum Exhibition and Conference. Abu Dhabi, UAE, 9–12 November. SPE-177946-MS. 10.2118/177946-MS