Non Productive Time Reduction Through a Deep Rig Time Analysis, Case Study

摘要

As time goes by, increase in world energy demand forces oil and gas companies to drill deeper in order to produce more oil and gas for balancing world’s offer and demand. This requires drilling layers with various characteristics and dealing with more drilling problems as drilling progresses. Reduction of drilling problems can help drillers to reduce their cost effectively. Rig time break down of more than 300 wells in one south west Iranian oil field has been analyzed to determine effective parameters on non-productive time amount. Results show that the most common drilling problems always have been experienced by drilling engineers are Equipment failure, stuck pipe and lost circulation. They expose huge expenses to the oil companies because of either drilling fluid supplement or subsequent drilling problems like fishing and side tracking. Next step was determination of new methods for reduction of lost rig times. Some new methods such as artificial neural network, genetic algorithm and curve fitting were used to predict occurrence of these phenomena for reducing or preventing them. Several factors while drilling will govern how severe mud loss and stuck pipe would occur. These actually make analytical modeling of lost circulation or pipesticking to somehow complicated. Hereby, employing artificial intelligence can be a leeway with proven capability and accuracy. In this research, operational parameters in Maroun oilfields are used for prediction of the mud loss severity along different sectors of this oilfield. Performed cross validations show fairly good compatibility with what happened in reality. Also artificial neural network was employed to predict stuck pipe position and stuck pipe severity before happening. as well results are well-matched with reality.