Floating Production Storage and Offloading Electric Power Demand Modelling using Soft Computing Techniques

Daniel C. de Araujo, Jr.; Vitor H. Ferreira; Artur A. Pessoa; Marcio Z. Fortes; Bruno S. M. C. Borba; Andre A. Augusto; André C. Pinho; Angelo C. Colombini; Marcos L. Ramos; Gabriel R. F. Q. Mafra

doi:10.20906/SBAI-SBSE-2023/3934

Daniel C. de Araujo, Jr. Departamento de Engenharia de Produção, Universidade Federal Fluminense, RJ
Vitor H. Ferreira Departamento de Engenharia Elétrica, Universidade Federal Fluminense, RJ
Artur A. Pessoa Departamento de Engenharia de Produção, Universidade Federal Fluminense, RJ
Marcio Z. Fortes Departamento de Engenharia Elétrica, Universidade Federal Fluminense, RJ
Bruno S. M. C. Borba Departamento de Engenharia Elétrica, Universidade Federal Fluminense, RJ
Andre A. Augusto Departamento de Engenharia Elétrica, Universidade Federal Fluminense, RJ
André C. Pinho Departamento de Engenharia Elétrica, Universidade Federal Fluminense, RJ
Angelo C. Colombini Departamento de Engenharia Elétrica, Universidade Federal Fluminense, RJ
Marcos L. Ramos Petrobras, RJ
Gabriel R. F. Q. Mafra Petrobras, RJ

DOI: https://doi.org/10.20906/SBAI-SBSE-2023/3934

Keywords: FPSO, Machine Learning, Modelling, Neural Network, Artificial Intelligence

Abstract

This work presents a case study of the application of soft computing techniques to model the load of the main electric equipments of three of Petrobras’ FPSO units. The methodology proposed was used in the development of a modelling and simulation tool called FPSO Power Demand Analytics (FPDA), developed in a partnership between Universidade Federal Fluminense (UFF) and Petrobras. The applied methodology resulted in a library of models from which the median absolute error rarely exceeds the 3% mark. The median of the median absolute errors observed across platforms and test scenarios is often less than 1%. The presented results were found satisfactory by UFF and Petrobras’ teams.