July Bias Macedo

Pós-doutorado

Formação complementar

Idiomas

Áreas de atuação

Participação em bancas

Orientou

Produções bibliográficas

• VALCAMONICO, DARIO ; BARALDI, PIERO ; MACÊDO, JULY BIAS ; MOURA, MÁRCIO DAS CHAGAS ; BROWN, JONATHAN ; GAUTHIER, STÉPHANE ; ZIO, ENRICO . A systematic procedure for the analysis of maintenance reports based on a taxonomy and BERT attention mechanism. RELIABILITY ENGINEERING & SYSTEM SAFETY , v. 257, p. 110834, 2025.

• MACEDO, JULY BIAS ; MAIOR, CAIO SOUTO ; LINS, ISIS DIDIER ; AZEVEDO, RAFAEL ; MOURA, MÁRCIO DAS CHAGAS ; DA SILVA, MANOEL FELICIANO ; SILVA NÓBREGA, MARCOS VINÍCIUS DA ; VITALE, GUILHERME ; VASQUES, RICARDO REVES . Using experts’ opinion for Bayesian prior reliability distribution of on-demand equipment: A case study of a novel sliding sleeve valve for open-hole wells. RELIABILITY ENGINEERING & SYSTEM SAFETY , v. 238, p. 109430, 2023.

• MACÊDO, JULY BIAS ; DAS CHAGAS MOURA, MÁRCIO ; AICHELE, DIEGO ; LINS, ISIS DIDIER . Identification of risk features using text mining and BERT-based models: Application to an oil refinery. PROCESS SAFETY AND ENVIRONMENTAL PROTECTION , v. 158, p. 382-399, 2022.

• MACEDO, JULY BIAS ; JOSÉ DAS CHAGAS MOURA, MÁRCIO ; RAMOS, MARÍLIA ; LINS, ISIS DIDIER ; ZIO, ENRICO . Machine learning-based models to prioritize scenarios in a Quantitative Risk Analysis: An application to an actual atmospheric distillation unit. JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES , v. 77, p. 104797, 2022.

• MACÊDO, JULY B. ; RAMOS, P. M. S. ; MAIOR, C.B.S. ; MOURA, M. J. C. ; LINS, I. D. ; VILELA, R. . Identifying low-quality patterns in accidents reports from textual data. International Journal of Occupational Safety and Ergonomics , v. X, p. 1-13, 2022.

• RAMOS, PLÍNIO MS ; MACEDO, JULY B ; MAIOR, CAIO BS ; MOURA, MÁRCIO C ; LINS, ISIS D . Combining BERT with numerical variables to classify injury leave based on accident description. Proceedings of the Institution of Mechanical Engineers Part O-Journal of Risk and Reliability , v. X, p. 1748006X2211401-X, 2022.

• MAIOR, CAIO B.S. ; MACÊDO, JULY B. ; LINS, ISIS D. ; MOURA, MÁRCIO C. ; AZEVEDO, RAFAEL V. ; SANTANA, JOÃO M.M. ; DA SILVA, MANOEL F. ; MAGALHÃES, MARCUS V.C. . Bayesian prior distribution based on generic data and experts? opinion: A case study in the O&G industry. JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING , v. 210, p. 109891, 2022.

• MACEDO, JULY BIAS ; ARAÚJO, LAVÍNIA MARIA MENDES ; LINS, ISIS DIDIER ; MOURA, MARCIO JOSE DAS CHAGAS ; SILVA JUNIOR, MANOEL FELICIANO DA ; NOBREGA, MARCOS VINICIUS DA SILVA ; VITALE, GUILHERME ; REVES, RICARDO . Addressing Excessively Strong Prior Distributions: A Study on Bayesian Reliability Estimation in Novel Sliding Sleeve Valves for Deepwater Oil e Gas Applications. In: ROG.e Conference, 2024, Rio de Janeiro. org.crossref.xschema._1.Title@426b8b4f, 2024. p. 4201.

• LIMA, GUSTAVO CAMARGO ROCHA ; SILVA, PEDRO JORGE LIMA DA ; ALCÂNTARA FILHO, JORGE ; MACEDO, JULY BIAS ; OLIVEIRA, PAULO ESTEVÃO LEMOS DE . Computer Vision techniques applied in the Oil e Gas industry to enhance safety: detection of equipments, people and vehicles. In: ROG.e Conference, 2024, Rio de Janeiro. org.crossref.xschema._1.Title@6b269f55, 2024. p. 2191.

• MACEDO, JULY B ; RAMOS, P. M. S. ; MAIOR, C.B.S. ; MOURA, M. J. C. ; LINS, I. D. . Human Factor Identification in Aviation Accidents Using Contextual Word Embeddings. In: European Safety and Reliability Conference (ESREL 2023), 2023, Southampton. Proceedings of the 33nd European Safety and Reliability Conference (ESREL 2023). Singapore: Research Publishing, 2023. p. 2603.

• MACEDO, JULY B ; RAMOS, P. M. S. ; MAIOR, C.B.S. ; MOURA, M. J. C. ; LINS, I. D. . Automated Identification of Human Factors in Aviation Accidents Using BERT-based Classifier and Topic Modeling. In: VIII Encontro Científico e X Encontro de Pesquisa e Pós-Graduação em Engenharia de Produção, 2023, Rio de Janeiro. VIII EPPGEP, 2023.

• RAMOS, P. M. S. ; MACÊDO, JULY B. ; MAIOR, CAIO B.S. ; DAS CHAGAS MOURA, MÁRCIO ; LINS, ISIS D. . Combining BERT with Numerical Features to Classify Injury Leave Based on Accident Description. In: Probabilistic Safety Assessment and Management PSAM 16, 2022, Honolulu, Hawaii. Proceedings of the Probabilistic Safety Assessment and Management PSAM 16, 2022.

• MACEDO, J. B. ; MOURA, M. J. C. ; LINS, I. D. ; ZIO, ENRICO . Identification of Features of Rare Risk Events in Oil Refineries Using Natural Language Processing (NLP). In: European Safety and Reliability Conference (ESREL), 2022, Dublin. Proceedings of the 32nd European Safety and Reliability Conference (ESREL 2022), 2022.

• MACEDO, J. B. ; AICHELE, D. ; MOURA, M. J. C. ; LINS, I. D. . Web app to support hazard identification of oil refineries. In: 31st European Safety and Reliability Conference, 2021, Angers. Proceedings of the 31st European Safety and Reliability Conference, 2021.

• MACEDO, J. B. ; AICHELE, D. ; MOURA, M. J. C. ; LINS, I. D. . A text mining and NLP approach for identifying potential consequences of accidents in an oil refinery. In: ESREL2020 PSAM 15, 2020, Venice. Proceedings of the 30th European Safety and Reliability Conference and the 15th Probabilistic Safety Assessment and Management Conference, 2020.

• MAIOR, C.B.S. ; SANTANA, J. M. M. ; NASCIMENTO, L. M. ; MACEDO, J. B. ; MOURA, M. J. C. ; LINS, I. D. ; DROGUETT, E. A. L. . Personal protective equipament detection in industrial facilities using camera video streaming. In: Esrel (European, Safety and Reliability Conference), 2018, Trondheim. Safety and Reliability - Safe Societies in a Changing World, 2018.

• NASCIMENTO, L. M. ; SANTANA, J. M. M. ; MACEDO, J. B. ; MOURA, M. J. C. . Modelo de previsão da classificação do Campeonato Brasileiro 2017 utilizando Simulação Monte Carlo via Cadeias de Markov. In: ENEGEP (Encontro Nacional de Engenharia de Produção), 2018, Maceió. XXXVIII Encontro Nacional de Engenharia de Produção, 2018.

• MACEDO, J. B. ; SANTANA, J. M. M. ; NASCIMENTO, L. M. ; MOURA, M. J. C. . Análise e modelagem de um sistema de filas de um Supermercado. In: ENEGEP (Encontro Nacional de Engenharia de Produção), 2018, Maceió. XXXVIII Encontro Nacional de Engenharia de Produção, 2018.

• MAIOR, C.B.S. ; SANTANA, J. M. M. ; NASCIMENTO, L. M. ; MACEDO, J. B. ; MOURA, M. J. C. ; LINS, I. D. ; DROGUETT, E. A. L. . Personal protective equipment detection in industrial facilities using camera video streaming. In: EPPGEP (Encontro de Pesquisa e Pós-Graduação em Engenharia de Produção), 2018, Florianópolis. III EPPGEP 2018, 2018.

• MAIOR, C.B.S. ; MOURA, M. J. C. ; SANTANA, J. M. M. ; NASCIMENTO, L. M. ; MACEDO, J. B. ; LINS, I. D. ; DROGUETT, E. A. L. . Real-time SVM Classification for Drowsiness Detection Using Eye Aspect Ratio. In: PSAM, 2018, Los Angeles. PSAM 14, 2018.

• SILVA, G. T. L. ; SILVA, E. O. ; MACEDO, J. B. ; MOURA, M. J. C. ; LINS, I. D. ; DROGUETT, E. A. L. . Application of Dijkstra algorithm in the multiobjective optmization of evacuation routes In toxic cloud scenario. In: ongresso da Associação Brasileira de Análise de Risco, Segurança de Processos e Confiabilidade - ABRISCO, 2017, Rio de Janeiro. Anais do Congresso Abrisco, 2017.

• MAIOR, C.B.S. ; SANTANA, J. M. M. ; MOURA, M. J. C. ; NASCIMENTO, L. M. ; MACEDO, J. B. ; LINS, I. D. ; DROGUETT, E. A. L. . SVM Classification for Drowsiness Detection Using Eye Aspect Ratio. In: Congresso da Associação Brasileira de Análise de Risco, Segurança de Processos e Confiabilidade - ABRISCO, 2017, Rio de Janeiro. Anais do Congresso Abrisco, 2017.

• NUNES, C. E. S. ; MACEDO, JULY B ; VERZA, N. ; MAIOR, C.B.S. ; MOURA, M. J. C. ; LINS, I. D. ; ORLOWSKI, R. . Subsea Equipment Reliability: Critical Analysis Of Existing Literature. In: European Safety and Reliability Conference (ESREL 2024), 2024, Krakow. Advances in Reliability, Safety and Security ESREL 2024 Collection of Extended Abstracts, 2024.

• MACEDO, JULY B ; RAMOS, P. M. S. ; ARAUJO, L. M. M. ; MAIOR, C.B.S. ; LINS, I. D. ; MOURA, M. J. C. . Quantum Natural Language Processing To Human Factor Identification In Accident Reports. In: European Safety and Reliability Conference (ESREL 2024), 2024, Krakow. Advances in Reliability, Safety and Security ESREL 2024 Collection of Extended Abstracts, 2024.

• MACEDO, JULY B ; MAIOR, C.B.S. ; RAMOS, P. M. S. ; MOURA, M. J. C. ; LINS, I. D. . Exploring Quantum Natural Language Processing in Risk Analysis: A Comparative Study on Aviation Accident Reports. In: Simpósio Brasileiro de Pesquisa Operacional, 2024, Fortaleza. Anais do LVI Simpósio Brasileiro de Pesquisa Operacional, 2024. v. 56.

• NEVES, L. ; MACEDO, JULY B ; LINS, I. D. ; MAIOR, C.B.S. ; MOURA, M. J. C. . Comparação De Modelos Clássicos E Quânticos De NLP Para Classificação De Acidentes Envolvendo Hidrogênio. In: Simpósio Brasileiro de Pesquisa Operacional, 2024, Fortaleza. Anais do LVI Simpósio Brasileiro de Pesquisa Operacional, 2024. v. 56.

• RAMOS, P. M. S. ; MACEDO, JULY B ; MAIOR, C.B.S. ; LINS, I. D. ; MOURA, M. J. C. . Quantum NLP for Predicting Injury Leaves in Occupational Accident Reports. In: Simpósio Brasileiro de Pesquisa Operacional, 2024, Fortaleza. Anais do LVI Simpósio Brasileiro de Pesquisa Operacional, 2024. v. 56.

• MACEDO, JULY B ; RAMOS, P. M. S. ; MAIOR, C.B.S. ; LINS, I. D. ; MOURA, M. J. C. . Enhancing Preventive Measures in Hydrogen Industries: Root Cause Identification Using NLP Techniques. In: Probabilistic Safety Assessment and Management & Asian Symposium on Risk Assessment and Management, 2024, Sendai. 17th Probabilistic Safety Assessment and Management & Asian Symposium on Risk Assessment and Management 2024, 2024.

• MACEDO, JULY B ; RAMOS, P. M. S. ; MAIOR, C.B.S. ; LINS, I. D. ; MOURA, M. J. C. . Quantum Computing for Predicting Environmental Impacts: A Focus on Hydrogen Safety in Industry. In: Probabilistic Safety Assessment and Management & Asian Symposium on Risk Assessment and Management, 2024, Sendai. 17th Probabilistic Safety Assessment and Management & Asian Symposium on Risk Assessment and Management 2024, 2024.

• ARAÚJO, LAVÌNIA MARIA MENDES ; MACEDO, JULY BIAS ; LINS, ISIS DIDIER ; MOURA, MÁRCIO JOSÉ DAS CHAGAS ; SILVA, MANOEL FELICIANO DA ; MAGALHÃES, MARCUS VINICIUS CAMPOS . Reliability Criteria Estimation of O & G Industry Equipment in the Concept Selection Process. In: 33rd European Safety and Reliability Conference, 2023, Southampton. Proceeding of the 33rd European Safety and Reliability Conference, 2023. p. 2314.

• MACEDO, JULY BIAS ; LINS, ISIS DIDIER ; MOURA, MÁRCIO JOSÉ DAS CHAGAS . NLP Advances in Risk Analysis Context: Application of Quantum Computing. In: 33rd European Safety and Reliability Conference, 2023, Southampton. Proceeding of the 33rd European Safety and Reliability Conference, 2023. p. 2613.

• AZEVEDO, R. ; MOURA, M. J. C. ; LINS, I. D. ; MACEDO, J. B. ; MAIOR, CAIO B.S. ; DA SILVA, MANOEL F. ; NOBREGA, M . The use of Weibull-GRP Virtual Age Model for Addressing Degradation due to Demand Induced Stress in Reliability Analysis of On-demand Systems. In: European Safety and Reliability Conference (ESREL), 2022, Dublin. Proceedings of the 32nd European Safety and Reliability Conference (ESREL 2022), 2022.

• MACEDO, J. B. ; MAIOR, CAIO B.S. ; LINS, I. D. ; AZEVEDO, R. ; MOURA, M. J. C. ; DA SILVA, MANOEL F. ; NOBREGA, M . A Bayesian prior distribution for novel on-demand equipment based on experts? opinion: A case study in the O&G industry. In: European Safety and Reliability Conference (ESREL), 2022, Dublin. Proceedings of the 32nd European Safety and Reliability Conference (ESREL 2022), 2022.

• AZEVEDO, RAFAEL V. ; LINS, I. D. ; MOURA, M. J. C. ; MENEZES, E. J. N. ; MACEDO, JULY BIAS ; MAIOR, CAIO B.S. ; SANTANA, J. M. M. ; DA SILVA, MANOEL F. ; NOBREGA, M . Methodology for Assessing the Reliability of Equipment under Development. In: European Safety and Reliability Conference (ESREL), 2022, Dubling. Proceedings of the 32nd European Safety and Reliability Conference (ESREL 2022), 2022.

• MACEDO, J. B. ; AICHELE, D. ; MOURA, M. J. C. ; LINS, I. D. . Identification of risk features using text mining and BERT-based models: Application to an oil refinery. In: ABRISCO, 2021, Rio de Janeiro. Congresso ABRISCO 2021, 2021.

• MACEDO, J. B. ; RAMOS, P. M. S. ; MAIOR, C.B.S. ; MOURA, M. J. C. ; LINS, I. D. . Assessing Low-Quality Accident Reports Using Natural Language Processing. In: ABRISCO, 2021, Rio de Janeiro. Congresso ABRISCO 2021, 2021.

• MAIOR, C.B.S. ; MACEDO, J. B. ; LINS, I. D. ; AZEVEDO, R. ; MOURA, M. J. C. ; SANTANA, J. M. M. ; DA SILVA, MANOEL F. ; MAGALHÃES, MARCUS V.C. . Estimation of reliability prior distribution based on generic data and experts? opinion: a case study in the O&G industry. In: ABRISCO, 2021, Rio de Janeiro. Congresso ABRISCO 2021, 2021.

• MACEDO, J. B. ; MOURA, M. J. C. ; LINS, I. D. ; ZIO, E . Machine Learning-based Decision Support Models for Performing Preliminary Hazard Analysis: An Application to an Atmospheric Distillation. In: ABRISCO, 2019, Rio de Janeiro. ABRISCO, 2019.

• MACEDO, J. B. ; MOURA, M. J. C. ; LINS, I. D. ; ZIO, E . Automated preliminary hazard analysis of oil refineries by using support vector machines. In: Encontro de Pesquisa e Pós-Graduação em Engenharia de Produção, 2019, Porto Alegre. Encontro de Pesquisa e Pós-Graduação em Engenharia de Produção, 2019.

Projetos de pesquisa

• 2023 - Atual

  Modelos de aprendizado (máquina, profundo e quantum) para monitoramento da saúde de ativos e confiabilidade humana, Descrição: Recent technological developments have impacted society on the entire structure of production systems. Sensors and transmitters have evolved and ways of collecting and storing data are becoming more efficient and cheaper. Thus, the databases generated in productive systems can be quite large (Big Data), which requires adequate management and analysis. In this context, the use of Artificial Intelligence (AI) allows interesting approaches in solving industrial problems in the context of predictive maintenance and reliability, disruptive technology in industry 4.0. In particular, machine learning is a field of computer learning that seeks the automated detection of meaningful patterns in data. Basically, there are three characteristics to achieve good results: (1) there is a pattern; (2) it is not possible (or feasible) to represent it mathematically; (3) there is data for the variables. The main objective of this research project is, based on AI, to provide learning methodologies (machine, deep and quantum), for problems to monitor key parameters in the context of prognostication and monitoring of asset health and human reliability. Specifically, the diagnosis and prediction of failure in machinery will be sought from signs of degradation (e.g., vibration and temperature) and the identification of the operator's attention level in critical activities. Thus, the developed models will provide real-time information and help in the decision-making process from advanced tools within the industrial context. Universal 402761/2023-5.. , Situação: Em andamento; Natureza: Pesquisa. , Integrantes: July Bias Macedo - Integrante / Márcio José das Chagas Moura - Integrante / Isis Didier Lins - Integrante / Caio Bezerra Souto Maior - Coordenador / Plínio Marcio da Silva Ramos - Integrante / RAMOS, MARÍLIA - Integrante / Lavínia Maria Mendes Araújo - Integrante / Mayra Macedo de Aquino - Integrante / Sandrely Pereira Da Silva - Integrante., Financiador(es): Conselho Nacional de Desenvolvimento Científico e Tecnológico - Auxílio financeiro.

• 2022 - Atual

  Combining Computer Fluid Dynamics, Virtual Reality, Machine and Deep Learning for Risk and Reliability Modeling in the Process Industry, Descrição: This project proposes a comprehensive methodology to tackle undesirable situations in the process industry (e.g., leakage of hazardous chemical substances) to avoid severe consequences to humans, the environment, and technical systems. The methodology development relies on deep learning models for hardware and human anomaly detection, computational fluid dynamics (CFD), and virtual reality. The learning process involves the interaction between these techniques as follows: many accidental scenarios with various inputs (e.g., leakage location, wind speed, wind direction) feed CFD models, which simulate gas dispersion in the surrounding environment. The generated CFD data is used in two ways. Firstly, gas concentrations time series on several points of the processing unit (e.g., sensor locations) will be inputted into the hardware anomaly detection model. Secondly, 3D mesh-grids feed a serious game involving a virtual reality approaching the real processing unit, which will simulate the occurrence of the undesired event. The serious game objective is that the player (e.g., emergency operator) needs to stop or mitigate the leakage considering the dispersion behavior. During the game, the player will carry wearables to monitor biological signals that will enter the human anomaly detection model. It has the potential to turn into a technological product to assist in training emergency teams. Their immersion, with wearables, in virtual scenarios that mimic rare stressful situations is an opportunity to gather data to enhance human reliability models, training programs, and emergency responses, which are of utmost importance in the process industry. Finally, whenever the deep learning and CFD models are trained and adjusted, they can be part of the processing unit safety barriers as additional tools to support rapid decision-making toward human, environmental, and system integrity. APQ-0394-3.08/22.. , Situação: Em andamento; Natureza: Pesquisa. , Integrantes: July Bias Macedo - Integrante / Márcio José das Chagas Moura - Integrante / Isis Didier Lins - Coordenador / Caio Bezerra Souto Maior - Integrante / João Mateus Marques de Santana - Integrante / Plínio Marcio da Silva Ramos - Integrante / Lavínia Maria Mendes Araújo - Integrante / Paulo Renato Ferreira Targino Soares - Integrante / Sávio Souza Venâncio Vianna - Integrante / Leonardo Streck Raupp - Integrante.

• 2022 - Atual

  Exploring quantum technologies for safety, risk and reliability engineering, Descrição: In engineering, machine learning and optimization methods are used to support decision in many applications on safety, risk and reliability. The aim is to avoid system failures and their negative consequences, which may represent social, environmental, and financial losses. However, the increasing sophistication of systems establishes complex problems where the traditional methods may be limited. In recent years, quantum research are gaining importance in the literature, focused on elds of physics and computer science. Indeed, there is still a gap on exploring the useful tools provided by quantum methods to safety, risk and reliability engineering. Relevant areas include diagnosis and prognosis of equipment failure modes, investigation of human factors (e.g., drowsiness) that degrades task performance, identication of patterns in process safety using natural language processing, and optimization problems such as reliability/redundancy allocation and risk-based inspection planning. Indeed, the mentioned problems have direct link with already developed quantum-based methods such as Quantum Neural Networks, Quanvolutional Neural Networks, and the Quantum Approximative Optimization Algorithm. Therefore, this project aims to develop quantum-based methodologies suited for safety, risk, and reliability problems. The goal is to combine experts from different research domains (e.g., physicists and engineers) to establish a multi-disciplinary research collaboration. 409701/2022-0.. , Situação: Em andamento; Natureza: Pesquisa. , Integrantes: July Bias Macedo - Integrante / Márcio José das Chagas Moura - Integrante / Isis Didier Lins - Coordenador / Caio Bezerra Souto Maior - Integrante / Plínio Marcio da Silva Ramos - Integrante / Lavínia Maria Mendes Araújo - Integrante / Askery Alexandre Canabarro Barbosa da Silva - Integrante / Rafael Chaves Souto Araújo - Integrante.

• 2021 - Atual

  Aprendizagem de máquina e profunda aplicadas à Engenharia de Confiabilidade e Risco, Descrição: O setor industrial passa por um processo de transformação decorrente da rápida evolução tecnológica e das mudanças na estrutura produtiva e na própria sociedade. Sensores e transmissores evoluíram as formas de coletas e armazenamento de dados estão se tornando mais eficientes e baratas. Assim, as bases de dados geradas em sistemas produtivos podem ser bastante grandes (Big Data), o que exige gerenciamento e análise adequados. Nesse contexto, o uso de Inteligência Artificial (IA) permite abordagem distintas na solução de problemas como por exemplo: processamento de linguagem, carros autônomos, reconhecimento de imagens, diagnóstico de doenças. Dentro da Indústria 4.0, sensores podem ser utilizados para monitorar parâmetros chaves de risco e confiabilidade do sistema. Previsão de falha em maquinários a partir de sinais de vibração e temperatura, verificação automática correto uso de equipamentos de proteção, identificação do nível atenção do operador em atividades críticas, são algumas das tarefas analisadas nesse projeto usando algoritmos de IA. Especificamente, modelos de aprendizagem de máquina e aprendizagem profunda são desenvolvidos para fornecer informações em tempo real e ajudar no processo de tomada de decisão a partir de ferramentas avançadas dentro do contexto industrial. Projeto aprovado no Edital 6/2021 de Auxílio a Projetos de Pesquisa para Jovens Pesquisadores da FACEPE (APQ-JP). Processo:1101-3.08/21.. , Situação: Em andamento; Natureza: Pesquisa. , Alunos envolvidos: Graduação: (2) / Doutorado: (2) . , Integrantes: July Bias Macedo - Integrante / Márcio José das Chagas Moura - Integrante / Isis Didier Lins - Integrante / Caio Bezerra Souto Maior - Coordenador / Plínio Marcio da Silva Ramos - Integrante / Thaylon Gomes Silva - Integrante / Nathália Giovanna Siqueira Bomfim - Integrante., Financiador(es): Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco - Outra.

• 2019 - Atual

  Desenvolvimento de metodologias para projeto de testes de confiabilidade para equipamentos e sistemas aplicados à construção de poços de petróleo, Descrição: testes acelerados de vida (TAVs) chegam a ser realizados mais frequentemente que testes de vida comuns. Testes acelerados em confiabilidade consistem na exposição de componentes/equipamentos a condições mais extremas (ex. de temperatura, pressão, vibração, choque) que a condição normal (nominal) de utilização. Em geral, tais testes são aplicados a sistemas que apresentam alto tempo médio até a falha (mean time to failure ? MTTF), para os quais testes envolvendo condições nominais são demasiado demorados e custosos e o período de tempo para gerar uma amostra razoável de tempos de falha é, normalmente, intolerável. Nesse contexto, os dois principais problemas associados aos testes acelerados de vida são: (1) planejar o teste de forma ótima, e (2) realizar a inferência estatística dos dados de falha e dados censurados provenientes do teste para estimação da confiabilidade do equipamento. Esta pesquisa está relacionada a ambos problemas, desenvolvendo metodologias distintas para cada problema.. , Situação: Em andamento; Natureza: Pesquisa. , Alunos envolvidos: Doutorado: (3) . , Integrantes: July Bias Macedo - Integrante / Márcio José das Chagas Moura - Coordenador / Isis Didier Lins - Integrante / Caio Bezerra Souto Maior - Integrante / João Mateus Marques de Santana - Integrante / Diego Aichele - Integrante / Eduardo José Novaes Menezes - Integrante / Rafael Azevedo - Integrante.

Prêmios