Path Planning Optimizer for Workover Rigs and Stimulation Vessels: Efficiency and Emissions Management

Abstract In this study we focus on utilization of path planning algorithms with machine learning (ML) to optimize the distance travelled. Two high-value use cases have been detailed. Rig mobilization process requires careful management to optimize cost and benefit. Activities like workover jobs are done when intervention costs justify the potential productivity gains, with operators incurring hefty expenses. Also, large fleet mobilizations contribute to high emissions and inefficiencies in equipment management such as idle time, suboptimal routing, and lack of regular maintenance can further elevate emissions. Moving the rig from one wellsite to another is time consuming, costly, and it directly depends on the location and distance between wellsites. The objective here is to identify the potential production gain of each well, thus providing the team with an optimized path for mobilization and operations using ML techniques that can help minimize the rig time cost and reduce greenhouse gas (GHG) emissions and enhance well integrity. The solution used ML-based efficient optimization algorithms for path planning, aiming to reduce the distance of rig movements along with petroleum engineering methods and calculations. A data-driven decision-support system was implemented for standard intervention screening techniques. Here intervention candidate evaluations were performed, and wells were ranked based on historical production, petrophysics properties, and nearby well performance. Different scenarios were run for identifying the most optimum path to be traversed covering wells with a good margin of potential gain. Because the total distance for rig mobilization was to be kept to a minimum, a comparative scenario was also studied where the production gain should reach a threshold to be considered for implementation, since that would be economically and environmentally consequential. The algorithms run several times by checking a different start point of the well and finding the most efficient route. The interactive dashboards, available on cloud and on-premises, enabled the asset managers to simplify logistics and planning and helped in quicker decision-making circumstances. This workflow has the potential to reduce emissions and rig mobilization time by up to 42% and enhance the earnings on the project by reducing other costs. For enhanced logistics and planning for swift operations, all procedures along with the well's potential concerns, production, reservoir deterioration, and facilities, have been taken into consideration. In today's era, when operators want to run at the forefront of the pack, this solution can calculate the optimum distance between workover candidate wells using ML-based advanced algorithms. The candidates are evaluated for their predictive post-workover gains, locations, and operational parameters. The deployment enables saving time, money, resources, and GHG emissions while improving safety and efficiency, thereby making it an all-in-one development for optimizing well integrity.