A Cost-Effective Computational Approach to Integrate Offshore Inspections Planning and Routing Vessels

Abstract The oil and gas industries operate critical equipment, particularly in offshore platforms. Therefore, ensuring reliability and compliance with regulatory standards is always under investigation. One important measure is the periodic inspection of equipment, enabling predictive maintenance and avoiding disasters. However, the high cost of these inspections makes it essential to properly define priorities and optimize planning. Traditionally, these plans are developed by experts with extensive experience, who create inspection schedules for specific equipment and plants. As an alternative, computational tools have been proposed to assist these experts in the planning of these operations. This study investigates an approach to reduce the computational cost of a tool designed for planning inspections of offshore equipment and routing vessels involved in these operations. The tool uses the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to optimize system-wide risk and the total cost of operations, while an Ant Colony Optimization (ACO) algorithm is applied for vessel routing. The risk is calculated based on a Top Logic Model (TLM). Once the genetic algorithm converges on promising regions of the solution space, the ACO algorithm is applied to incorporate routing. This approach is compared in terms of risk, inspection plan costs, and computational efficiency to two baseline methods. Based on the experimental results, it can be inferred that using post-processing for vessel routing may offer a computationally efficient alternative when a small number of equipment or shorter inspection windows are considered.