Each year, the SPE Artificial Lift Conference and Exhibition (ALCE) brings together E&P innovators from major IOC’s, NOC’s, and independent operators to exchange ideas that advance technical knowledge in artificial lift across multiple applications. Since announcing the extended partnership with Equinor, Ambyint made its appearance in last week’s SPE ALCE, hosted at the Woodlands Waterway Marriott and Convention Center. The theme of this year’s conference, “Pushing the Limits of Artificial Lift,” was well suited for Ambyint as the company seeks to revolutionize the ways of thinking about Artificial Lift optimization. As E&P developments become more complex, Ambyint seeks to use the vast amounts of data that is gathered to advance and enable machine learning and artificial intelligence, in order to optimize well production, increase BOPD, and automate redundant high-cost tasks.
Ambyint’s Brian Arnst, Director or Optimization, delivered a presentation on the recently published SPE paper “Enabling Autonomous Well Optimization Via Using IoT-Enabled Devices and Machine Learning in Bakken Horizontal Wells,” which was co-authored with Equinor. A copy of the paper can be obtained at OnePetro.
At the SPE event, Arnst discussed Ambyint’s approach to driving autonomous well classification and optimization of setpoints with the deployment of a system that is capable of real-time analysis and higher-order mathematics. An Internet of Things (IoT) controller with high-performance computational capabilities and direct communication with a cloud-based analytics software platform to enable artificial intelligence and machine learning on high-resolution data, sampled in real-time from the rod pump control system.
The SPE paper further discusses Equinor’s deployment of Ambyint’s technology on 50 wells in the Bakken.The 50 wells that were chosen are highly representative of “typical” Bakken horizontal wells. The controller was connected into the legacy rod pump controller via Modbus connection. Where immediate differences in key downhole parameters were observed when comparing the results from the traditional rod pump controller to the IoT.
According to Arnst, “Equinor was able to automate well optimization setpoint decisions, resulting in reduced well volatility, better pump efficiency, and increased pump fillage. Equinor was able to achieve these improvements while maintaining production in all cases. […] For wells that were under-pumping, Equinor was able to increase oil production by up to 33%. For wells that were over-pumping, Equinor was able to decrease the number of strokes by 11% and increase pump efficiency by 14%.”
Overall, Arnst was pleased to “receive such positive feedback from the event and the general excitement expressed by the audience as we explore new ways of driving production optimization using edge-controllers and proven technology and methods.”
Next, Arnst will be co-presenting with ConocoPhillips on their recent pilot case and the value that is being delivered by Ambyint to the operator. The presentation will be delivered at the 2018 International Sucker Rod Pumping Workshop, which will be held in Oklahoma City on Sept. 12 and 13. The topic will be on “Economically Enabling Autonomous Pump by Exception on Sub-3 BOPD Permian Basin Stripper Wells Using IOT-Enabled Edge Controllers.”