Development of offshore maintenance service scheduling system with workers allocation Guilherme Angelo Leite Electrical Engineering Department PUC-RIO Rio de Janeiro, Brazil guialeite92@gmail.com Marley Maria Bernardes Rebuzzi Vellasco Electrical Engineering Department PUC-RIO Rio de Janeiro, Brazil marley@ele.puc-rio.br Abstract—In order to develop an offshore maintenance sched- ule support system, this work presents a new model for con- strained combinatorial problems: CPSO+. This model is a combi- nation of two previous models: the PSO+, which presented good results in problems with nonlinear constrains; and the CPSO, which is an adaptation of PSO for application in combinatorial problems. The proposed model has been adapted to solve the complex problem of defining the best sequence of offshore maintenance activities and allocated staff to maximize service provider profitability within three months, while respecting all service completion time constraints and specific offshore work constraints. To evaluate the performance of this new model in solving the proposed problem, two CPSO+ variants were evalu- ated against the original CPSO model, in six proposed simulation cases. The results of the simulations indicate that the proposed CPSO+ model with reduced initialization variation outperforms other evaluated models in execution time and solution quality to the given problem. Index Terms—Particle Swarm Optimization, Optimization, Combinatorial Problem, Offshore Maintenance, Combinatorial PSO. I. I NTRODUCTION The oil and gas industry is an economic strategic sector in Brazil. Therefore, the solution to relevant problems in this field is highly important to the country. In this context, one of the challenges of this sector is to replace the manual and archaic procedures for modern, automated and data driven techniques, specially on the scheduling segment [1]. Among the different support areas associated to offshore oil extraction, the main department is the offshore maintenance team, which is responsible to ensure the equipment’s correct setup and performance. In this segment, the most outdated process is the workers boarding scheduling, with no proper tool to assist on this task which considers the necessary restrictions. This problem is known as Flexible Job-shop Scheduling Problem, an optimization problem to solve machine and resources allocation in tasks with known restrictions [2]. Today, on the Brazilian industry, some companies still operate without this kind of software support, depending, instead, on expert decisions. Others, utilize generic software that does not analyze the offshore work specific restrictions, resulting in sub-optimal solutions that request further manual tuning to be implemented on the field. Even though the companies operates in that way, this process can take several days of different specialists and is highly susceptible to human errors. Since there are no techniques specifically designed for offshore restrictions, this study uses as reference other industry segment algorithms with similar restrictions. Those segments are: the problem to balance the data process on multiple cores [3]; the information path selection on network environments with bandwidth limitation [4] and papers on modeling Job Shop Scheduling Problems [5]–[7]. These studies support that the Flexible Job Shop Scheduling Problems, the literature name for the presented offshore problem, is a relevant problem to be studied, especially with multiple workers and constrains. The Particle Swarm Optimization (PSO) [8] algorithm has presented good results both in terms of processing speed and quality of the solution for high dimensional problems with constrains, so it has a good fit with the proposed problem. Although, the model adaptations does not cover all applica- tions yet. Variations of the original PSO have been developed, such as PSO+ [9], which extends the PSO to deal with nonlinear restrictions using a multiple swarm logic, and the CPSO [10], which is suitable for combinatorial optimization problems. However, there is no PSO version that incorporates both capabilities. Therefore, the main objective of this work is to propose a new Flexible Job Shop Scheduling Problem optimization model specifically designed for the offshore maintenance sector restrictions. This new model, called CPSO+, is inspired on the PSO+ high performance tools and the combinatorial adaptations from the CPSO model, allowing it to benefit from the advantages of both models. II. OFFSHORE MAINTENANCE SCHEDULING Oil platforms in Brazil are mainly offshore constructions similar to ships that should never leave the sea. Although similar to normal ships, the offshore platforms need a va- riety of services to keep operation, such as food supply, accommodation facilities, electricity, transportation to land, loading / offloading, telecommunications, medical services, and maintenance, safety and emergency equipments [11]. Even though those services are similar to onshore services, they are regulated by different laws dedicated to offshore jobs. Those regulations impose that: 978-1-7281-6929-3/20/$31.00 ©2020 IEEE