Optimization of Near Wellbore Divertors: A Machine Learning Approach
A research project focusing on the optimization of near wellbore diverters in Hydraulic Fracturing with the help of data collected through lab experiments and the development machine learning model to predict the pressure for given concentrations of Bead, Powder, and Flakes. The project was primarily focused on the end goal of web app development that lets users predict the pressure on custom observations of Beads, Powder, and Flakes in Hydraulic Fracturing.
The project optimization of near wellbore divertors was a complete blend of experimental study and machine learning model development. The lab experiments were conducted to study the pattern and collect the data of different concentrations of the Bead, Powder and flakes with their respective pressure.
The collected data was then analyzed, cleaned, preprocessed and fed to the machine learning model. Multiple ML algorithms were used for obtaining better accuracy and precised predictions.
The model was finally deployed as web app allowing users to predict the pressure from multiple and combination of algorithms for custom concentrations of the Bead, Powder and Flakes.
