ROI Case Study: Can Gas Lift Optimization Models Learn to Calibrate Themselves?
Gas Lift Optimization Models is the topic of our discussion today. Recently, we did a series of ROI case studies to demonstrate the impact of early detection on your bottom line. In today’s blog, we are sharing a sample of 60 days of results of our gas injection recommended implementation. The light and dark green bars indicate the Oil production rates before and after the gas injection changes, respectively. The corresponding grey bars indicate a change in gas injection rates.
As you can see in wells 3, 7 & 9 the oil production rates have remained fairly constant or have increased after reducing the gas injection rate (such as on well 9). On wells 10,12,13, 14 &15 we see an increase in gas injection rate resulting in an increase in oil production rate. However, well 11 sees a significant increase in injection rate but really did not see an increase in production. Here, we have a few wells where we increase the gas injection rate but did not see an increase in the oil production rate. Or in some cases where the well was declining severely and when we reduced the gas injection rate, we may have seen a relative drop in oil production rate.
What is dynamic about our models is that assigning whether the drop is because of the decline or due to change in gas injection rate is something the model learns over time, with each step. The fact is: You may not get the expected outcome but are able to learn from it at each individual well. Furthermore, the model makes a recommendation based on the most likely conditions of the well at that time. But when the model sees a response which is contrary to its expectation, we learn more about the underlying operation of the well.
In conclusion, our models learn to calibrate either through gas injection changes through our recommendations or through using the changes made from historical data. The model utilizes historical data to calibrate itself and learn.
If you want to maximize your oil production and increase your ROI, contact us to set up an appointment with our sales team to discuss easy implementation on your oilfields. We say easy because Production Unified Monitoring is a cloud-based tool that can be accessed from any web browser without any hardware or software installs, meaning there are no capital expenditures. Contact Us Today!