فهرست نشریات علمی دسترسی آزاد ایران

Fishing operations are one of the most essential parts of drilling operations. If the fishing operation fails, the other direction should be considered to continue drilling and reach the desired depth, which can be achieved using sidetracking operations. Long-term fishing operations increase the cost and time of the drilling operation; therefore, we should try to have a successful fishing operation in the shortest possible time. It can be stated that the execution of the fishing operation is economical as long as the costs are less or at least equal to the cost of the sidetracking operation. Therefore, the optimal fishing time must be determined to make the drilling operation economical. Many statistical analysis methods have been used to determine the optimal time, but they are not popular due to insufficient accuracy and time-consuming calculations. This study used a machine-learning (ML) model with a regression algorithm to estimate the optimal time for fishing operations in the Gachsaran oil field. The fishing cost rate and depth as input data were first collected and categorized based on different sections of the Gachsaran oil field to calculate the optimal fishing time. Then, the sidetracking cost was predicted by the machine learning model, and this cost was equated to the fishing cost in the worst conditions. As a result, the optimal fishing time was calculated for each section. The result showed that the model could estimate the cost of sidetracking with an error of less than 2%. Using the designed model and the input data of the Gachsaran oil field, considering the optimal fishing time, it was possible to save $1 million and 16 h in drilling a well.