Production optimization on a network level has been proven to be an effective method to maximize production potential of a field with low capital. But as it stands, it is a heavy process to start along with its several challenges such as data quality issues, tedious plus repetitive work processes to deploy and reuse a complete network model. Leveraging technologies from a flow assurance simulator, python Application Programming Interface (API) toolkit, open-source machine learning packages in python, and a commercial visualization dashboard, this paper proposed a series of workflows to simplify model deployment and set up an automatic advisory system to provide insight as a mean to justify an engineer’s day to-day engineering decision.
A total of three steps was prepared to achieve field-level automated optimization system. First, is the creation of digital twin of well and network model. To eliminate potential data errors, reduce time consumed, and to merge various part of the model into one, a scalable python script was made. Second, an automated calibration workflow is created as performance issues also arises for individual branch calibration matching. Hence a combination of technologies was utilized to automate daily data acquisition and model update from production database and run a supervised machine learning model to continuously calibrate the network model. The last one is creating the customizable optimization workflow based of field KPIs, which results are derived from daily optimization run. The results are available in a personalized network surveillance dashboard accessible for engineers to create rapid decisions.
From the first and second steps, time consumed was reduced from 30 minutes/well to 10 minutes/well in bulk well modelling workflow and from 2 hours to 10 minutes for the network model merge with the assumption of 100 wells in one network. It would also greatly increase data integrity and consistency issues as it eliminates wearisome input process. On the last step, the model was successfully updated with the latest production data and the well IPRs’ Liquid PI, reservoir pressure, and holdup factor are predicted from ML with more than 90% accuracy. As result delivery, the surveillance dashboard will be populated daily with the network production data, flowing parameters, and operation recommendations. It is estimated more than 90% time is saved from manual individual runs to digital comprehensive optimization.