Designing Subsea Processing Systems Using a Hybrid Genetic Algorithm

Abstract

Designing a subsea production system is a task that takes several months to complete by an experienced and multidisciplinary team of engineers. In this work, a computerized hybrid method to find optimal designs and support subsea production system design using a genetic algorithm combined with a gradient search method is proposed. The genetic algorithm is formulated to optimize the structure of the production system, while the gradient method solves the continuous non-linear variables related to flow rates, reservoir deliverability, equipment capacities, and others. The study case is based on the Goliat field. This hybrid approach is compared with an exact method. The hybrid method successfully finds subsea configurations that maximize the net present value in shorter running times when compared to an exact method. The methodology presented provides an advancement toward modelling and automated decision-making in subsea production system design.