A group of nine researchers, including two doctoral students and two members of the management committee of the National Agency of Petroleum, Natural Gas, and Biofuels (ANP) Human Resources Program (PRH) 38.1 - Risk Analysis and Environmental Modeling in Oil and Gas Exploration, Development, and Production, representing the Center for Studies and Testing in Risk and Environmental Modeling (CEERMA-UFPE), participated actively in the 33rd European Safety and Reliability Conference (ESREL) held in Southampton, United Kingdom.

ESREL 2023, held at the University of Southampton from September 3rd to 7th, 2023, is an annual flagship event in the field of reliability analysis, risk assessment, risk management, and the optimization of safety performance in socio-technological systems. The event is organized by the European Safety and Reliability Association (ESRA) and gathers experts in safety and reliability from around the world.

PRH-38.1 researchers together with other CEERMA researchers presented a total of 19 articles subdivided into three main categories: Advances in Machine Learning and Quantum Optimization, Bayesian Inference and in the Advances in Reliability Engineering and Risk Management sessions in Oil and Gas Industries. In addition, other works covered the theme of Human Reliability. The presentations demonstrated the group's commitment to contributing significantly to the advancement of knowledge in their areas of research.

These studies cover a wide range of topics, from quantum optimization to risk analysis in the oil and gas industry, as well as demonstrating the diversity and depth of research carried out at Ceerma-UFPE. Participation in this type of international event plays a fundamental role in the training of its researchers, in conducting applied scientific research and in actions such as university extension aimed at the oil, natural gas, biofuels and renewable energy industries. PRH-38.1's active participation in ESREL2023 reinforces its commitment to cutting-edge research and contributing to improving safety and reliability across a variety of critical industrial sectors.

Below are the titles and links to the abstracts of the works presented:

1.           Quantum Optimization for Redundancy Allocation Problem Considering Various Subsystems

2.           Rotating Machinery Health State Diagnosis through Quantum Machine Learning

3.           Quantum Machine Learning for Drowsiness Detection with EEG Signals

4.           NLP Advances in Risk Analysis Context: Application of Quantum Computing

5.           Experimental Set-Up for Evaluating Operator Performance through Operations Control Room Simulation in the Oil and Gas Industry

6.           Deep Learning Models Applied to Intelligent Diagnosis of Rotating Machines

7.           A Bayesian Inference and Metaheuristics Model for Estimating the Frequency of Maritime Accidents: The Case of Fernando de Noronha

8.           A Bayesian Population Variability-based Methodology for Reliability Assessment in the Oil and Gas Industry

9.           Human Factor Detection in Aviation Accidents Using NLP

10.         PetroBayes’ Modules for Reliability Assessment in the Oil and Gas Industry

11.         Reliability Criteria Estimation of O&G Industry Equipment in the Concept Selection Process

12.         Methodology for Extracting Reliability Parameters from the Qualification Standard Tests ISO-23936

13.         Proposal of a Test Protocol for Reliability Assessment of the New All-Electric Intelligent Completion Interface

14.         Software Reliability Analysis in the O&G Industry: A Review with Applications

15.         Development of a Software Tool to Implement Reliability Assessment of Developing Technologies

16.         Thermal Influence on Plastic Optical Fiber: A Reliability Diagnosis

17.         Influence of Transformation Capacity Expansion of a Substation on the Distribution Network Resilience: A Study of a Substation in the Metropolitan Region of Recife-Brazil

18.         Design and Validation of a Digital Twin for Intelligent Well Completion

19.         Wind Turbine Bearing Prognostics Using Deep Learning Approaches