Ádamo Henrique Rocha De Oliveira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ádamo Henrique Rocha De Oliveira has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Gideon V. Leandro
Departamento de Engenharia Elétrica, UFPR, Curitiba
3 shared publicationsRoman Kuiava
Departamento de Engenharia Elétrica, UFPR, Curitiba
3 shared publicationsWagner F. S. Souza
Departamento de Engenharia Elétrica, UFPR, Curitiba
3 shared publicationsGideon Leandro
2 shared publications- Gideon Villar Leandro
Electrical Engineering Department, Federal University of Paran, Curitiba, Brazil
2 shared publications - Marcelo de Souza Picanço
Universidade federal do Pará
2 shared publications
Latest Publications
- Open Access
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 213669-213696
A New Hybrid Reference Vector and Grid-Based Evolutionary Algorithm for Dynamic Many-Objective Optimization
Dynamic many-objective optimization problems (DMaOPs) are a class of problems involving more than three objectives. Their objective functions, search space, or constraints may change over time. Dynamic many-objective evolutionary algorithms (DMaOEAs) are typically used to solve DMaOPs and primarily consist of a static optimizer, a change detection mechanism, and a change response mechanism. In this paper, a new hybrid DMaOEA based on the reference vector guided evolutionary algorithm (RVEA) and the grid-based evolutionary algorithm (GrEA), called the dynamic reference vector and grid-based evolutionary algorithm (DRVGrEA), is proposed. In the selection stage of DRVGrEA, a new dynamic angle-penalized distance (DAPD) is introduced to balance convergence and diversity uniformly across all dynamic environments of the problem. At this stage, the GrEA grid-based indicators are still used as a secondary selection mechanism. These mechanisms are applied to different parts of the solutions. To evaluate the performance of the proposed algorithm, several experiments were conducted that compared DRVGrEA with six DMaOEAs, including five based on classical algorithms from the literature and one recently proposed method. The experiments used the SDP1–15 benchmark with 4, 6, 8, 10, 12, and 15 objectives. The results demonstrate that DRVGrEA outperforms or at least matches the performance of the other DMaOEAs. Furthermore, DRVGrEA was also applied to a real-world control problem, namely the PID tuning of an Automatic Voltage Regulator system, where it achieved superior performance compared to all competing algorithms.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 213669-213696
Open AccessA New Hybrid Reference Vector and Grid-Based Evolutionary Algorithm for Dynamic Many-Objective Optimization
Dynamic many-objective optimization problems (DMaOPs) are a class of problems involving more than three objectives. Their objective functions, search space, or constraints may change over time. Dynamic many-objective evolutionary algorithms (DMaOEAs) are typically used to solve DMaOPs and primarily consist of a static optimizer, a change detection mechanism, and a change response mechanism. In this paper, a new hybrid DMaOEA based on the reference vector guided evolutionary algorithm (RVEA) and the grid-based evolutionary algorithm (GrEA), called the dynamic reference vector and grid-based evolutionary algorithm (DRVGrEA), is proposed. In the selection stage of DRVGrEA, a new dynamic angle-penalized distance (DAPD) is introduced to balance convergence and diversity uniformly across all dynamic environments of the problem. At this stage, the GrEA grid-based indicators are still used as a secondary selection mechanism. These mechanisms are applied to different parts of the solutions. To evaluate the performance of the proposed algorithm, several experiments were conducted that compared DRVGrEA with six DMaOEAs, including five based on classical algorithms from the literature and one recently proposed method. The experiments used the SDP1–15 benchmark with 4, 6, 8, 10, 12, and 15 objectives. The results demonstrate that DRVGrEA outperforms or at least matches the performance of the other DMaOEAs. Furthermore, DRVGrEA was also applied to a real-world control problem, namely the PID tuning of an Automatic Voltage Regulator system, where it achieved superior performance compared to all competing algorithms.
- Open Access
- 31 January 2025
- Published by FapUNIFESP (SciELO) in Ambiente Construído
- Vol. 25, e137002
Strength prediction of mortar reinforced with babassu coconut fiber using artificial neural networks
Using natural fibers as reinforcement in cement composites is a sustainable alternative in the construction industry. Nevertheless, the dosage of these materials employing traditional methods depends on laboratory tests and tends to be laborious and expensive. Thus, predicting composites characteristics can save time and reduce operating costs. In this study, Artificial Neural Networks (ANN) trained with Extreme Learning Machine (ELM) were used to predict the tensile and compressive strengths of mortar reinforced with babassu coconut fiber. Babassu coconut is an abundant product in the region where this research was carried out, and its use tends to bring socio-economic benefits. The data was obtained experimentally, generating a total of 51 samples. The ANN topologies have six parameters in the input layer (cement, sand, water/cement ratio, maximum fiber length, fiber percentage, and slump), one parameter in the output layer (tensile or compressive strength), and one hidden layer, which contains 6 and 7 neurons, respectively, in the tensile (ELM-T) and compressive (ELM-C) strength prediction models. Simulation results indicated that both models are promising tools for predicting the mechanical behavior of mortars reinforced with babassu coconut fibers.
- 31 January 2025
- Published by FapUNIFESP (SciELO) in Ambiente Construído
- Vol. 25, e137002
Open AccessStrength prediction of mortar reinforced with babassu coconut fiber using artificial neural networks
Using natural fibers as reinforcement in cement composites is a sustainable alternative in the construction industry. Nevertheless, the dosage of these materials employing traditional methods depends on laboratory tests and tends to be laborious and expensive. Thus, predicting composites characteristics can save time and reduce operating costs. In this study, Artificial Neural Networks (ANN) trained with Extreme Learning Machine (ELM) were used to predict the tensile and compressive strengths of mortar reinforced with babassu coconut fiber. Babassu coconut is an abundant product in the region where this research was carried out, and its use tends to bring socio-economic benefits. The data was obtained experimentally, generating a total of 51 samples. The ANN topologies have six parameters in the input layer (cement, sand, water/cement ratio, maximum fiber length, fiber percentage, and slump), one parameter in the output layer (tensile or compressive strength), and one hidden layer, which contains 6 and 7 neurons, respectively, in the tensile (ELM-T) and compressive (ELM-C) strength prediction models. Simulation results indicated that both models are promising tools for predicting the mechanical behavior of mortars reinforced with babassu coconut fibers.
- Open Access
- 15 November 2024
- Published by FapUNIFESP (SciELO) in Brazilian Archives of Biology and Technology
- Vol. 67, e24241072
Day-Ahead Operational Planning of Isolated Microgrids Considering Over/Underestimation Costs for Solar and Wind Power Generation and Battery Degradation Costs
This paper proposes a methodology for the day-ahead operational planning of isolated microgrids equipped with renewable distributed generation based on solar photovoltaic and wind generation systems, energy storage systems, and diesel generation as backup power sources. As one of the main contributions of this paper, the proposed methodology is based on optimal power flow (OPF), considering cost minimization as the objective function that combines probabilistic costs of the renewable distributed generation systems with the determinist cost associated with the degradation of the battery bank. In addition, the cost of fuel consumption associated with the diesel generator is also considered. The costs associated with the renewable distributed generation are modeled by probability density functions, where a reserve cost for overestimation and a penalty cost for underestimation of the output power from these renewable sources are adopted. Hence, the proposed OPF avoids the over/underestimation of the available day-ahead solar and wind generations. The differential evolution optimization technique was used to solve the proposed OPF formulation and to obtain a minimum cost of operation considering the deterministic load profile for the operation of the microgrid under study. The proposed formulation was tested for different solar photovoltaic and wind generation scenarios in a microgrid in Lençóis Island, Brazil, another important contribution of the paper. The obtained results showed that the considered microgrid's day-ahead planning is sensitive to climatic conditions that impact the generation scenario and minimize long-term operating costs.
- 15 November 2024
- Published by FapUNIFESP (SciELO) in Brazilian Archives of Biology and Technology
- Vol. 67, e24241072
Open AccessDay-Ahead Operational Planning of Isolated Microgrids Considering Over/Underestimation Costs for Solar and Wind Power Generation and Battery Degradation Costs
This paper proposes a methodology for the day-ahead operational planning of isolated microgrids equipped with renewable distributed generation based on solar photovoltaic and wind generation systems, energy storage systems, and diesel generation as backup power sources. As one of the main contributions of this paper, the proposed methodology is based on optimal power flow (OPF), considering cost minimization as the objective function that combines probabilistic costs of the renewable distributed generation systems with the determinist cost associated with the degradation of the battery bank. In addition, the cost of fuel consumption associated with the diesel generator is also considered. The costs associated with the renewable distributed generation are modeled by probability density functions, where a reserve cost for overestimation and a penalty cost for underestimation of the output power from these renewable sources are adopted. Hence, the proposed OPF avoids the over/underestimation of the available day-ahead solar and wind generations. The differential evolution optimization technique was used to solve the proposed OPF formulation and to obtain a minimum cost of operation considering the deterministic load profile for the operation of the microgrid under study. The proposed formulation was tested for different solar photovoltaic and wind generation scenarios in a microgrid in Lençóis Island, Brazil, another important contribution of the paper. The obtained results showed that the considered microgrid's day-ahead planning is sensitive to climatic conditions that impact the generation scenario and minimize long-term operating costs.
- Open Access
- 1 July 2024
- Published by Brazilian Journals in Caderno Pedagógico
- Vol. 21 (7) , e6080
Uso de inteligência artificial para previsão de características de compósitos cimentícios reforçados com fibras: uma revisão sistemática
A utilização de compósitos se dá a partir da necessidade de tecnologias capazes de melhorar a qualidade dos materiais empregados. Na construção civil, os compósitos mais comuns são aqueles de matriz cimentícia reforçados com fibras. Entretanto, a dosagem de concretos e argamassas pelos métodos tradicionais depende de ensaios laboratoriais e tende a ser trabalhosa, cara e com possíveis ajustes por tentativa e erro. Desta forma, o desenvolvimento de modelos confiáveis para a previsão de características de compósitos pode proporcionar economia de tempo e redução de custos operacionais. Portanto, este trabalho propõe uma revisão sistemática da literatura de modo a identificar os avanços realizados até o momento no que se refere à utilização de técnicas preditivas de Inteligência Artificial (IA) a partir de dados de compósitos reforçados com fibras. Os principais processos desta revisão consistem em pesquisa acerca da temática, triagem do material, classificação dos artigos, seleção dos artigos do portifólio e leitura e síntese dos artigos. Dessa forma foram elencados os tipos de fibra empregados como reforço, as características previstas e as técnicas de IA utilizadas pelos principais trabalhos disponíveis na literatura. Foi possível perceber que a temática proposta está em crescente desenvolvimento apresentando muitas oportunidades de pesquisa.
- 1 July 2024
- Published by Brazilian Journals in Caderno Pedagógico
- Vol. 21 (7) , e6080
Open AccessUso de inteligência artificial para previsão de características de compósitos cimentícios reforçados com fibras: uma revisão sistemática
A utilização de compósitos se dá a partir da necessidade de tecnologias capazes de melhorar a qualidade dos materiais empregados. Na construção civil, os compósitos mais comuns são aqueles de matriz cimentícia reforçados com fibras. Entretanto, a dosagem de concretos e argamassas pelos métodos tradicionais depende de ensaios laboratoriais e tende a ser trabalhosa, cara e com possíveis ajustes por tentativa e erro. Desta forma, o desenvolvimento de modelos confiáveis para a previsão de características de compósitos pode proporcionar economia de tempo e redução de custos operacionais. Portanto, este trabalho propõe uma revisão sistemática da literatura de modo a identificar os avanços realizados até o momento no que se refere à utilização de técnicas preditivas de Inteligência Artificial (IA) a partir de dados de compósitos reforçados com fibras. Os principais processos desta revisão consistem em pesquisa acerca da temática, triagem do material, classificação dos artigos, seleção dos artigos do portifólio e leitura e síntese dos artigos. Dessa forma foram elencados os tipos de fibra empregados como reforço, as características previstas e as técnicas de IA utilizadas pelos principais trabalhos disponíveis na literatura. Foi possível perceber que a temática proposta está em crescente desenvolvimento apresentando muitas oportunidades de pesquisa.
- Open Access
- 10 May 2023
- Published by Brazilian Journals in Contribuciones A Las Ciencias Sociales
- Vol. 16 (5) , 2901-2917
Automatização do teste de agilidade utilizando Arduino
Avaliação física no início de rotinas de práticas corporais é recomendada para que professores de Educação Física obtenham informações importantes sobre condições físicas dos seus alunos e a criação de protótipos e a automatização de testes, que viabilizem a coleta dos dados torna-se extremamente útil e funcional nesse processo. O objetivo desse artigo é apresentar os dados referentes à automatização de um teste físico, conhecido como teste do Quadrado, bem como a avaliação de sua eficiência quanto a aplicabilidade, na mensuração automática da capacidade física agilidade. Para montagem do recurso que captasse os comandos para início e fim do teste utilizou-se microcontroladores e sensores eletrônicos, através de uma plataforma eletrônica de código aberto baseada em hardware e software livres, conhecida como Arduino. Concluída a fase de montagem do recurso seguiu-se para a fase de execução dos testes tendo sete (07) alunos voluntários do IFMA campus Santa Inês para mensuração da agilidade, tendo seus desempenhos medidos através dos modos convencional e automatizado, simultaneamente. Observou-se que os tempos medidos por ambos os modos apresentaram boa proximidade entre os valores da execução de cada aluno, indicando que o modo automatizado pode representar um substituto confiável para o modo convencional. A pesquisa também mostrou benefícios e vantagens para professores de Educação Física, quanto ao aspecto referente ao armazenamento das informações de forma automática no próprio sistema evitando desta forma, a utilização de várias fichas de protocolo e anotações durante a fase de realização dos testes.
- 10 May 2023
- Published by Brazilian Journals in Contribuciones A Las Ciencias Sociales
- Vol. 16 (5) , 2901-2917
Open AccessAutomatização do teste de agilidade utilizando Arduino
Avaliação física no início de rotinas de práticas corporais é recomendada para que professores de Educação Física obtenham informações importantes sobre condições físicas dos seus alunos e a criação de protótipos e a automatização de testes, que viabilizem a coleta dos dados torna-se extremamente útil e funcional nesse processo. O objetivo desse artigo é apresentar os dados referentes à automatização de um teste físico, conhecido como teste do Quadrado, bem como a avaliação de sua eficiência quanto a aplicabilidade, na mensuração automática da capacidade física agilidade. Para montagem do recurso que captasse os comandos para início e fim do teste utilizou-se microcontroladores e sensores eletrônicos, através de uma plataforma eletrônica de código aberto baseada em hardware e software livres, conhecida como Arduino. Concluída a fase de montagem do recurso seguiu-se para a fase de execução dos testes tendo sete (07) alunos voluntários do IFMA campus Santa Inês para mensuração da agilidade, tendo seus desempenhos medidos através dos modos convencional e automatizado, simultaneamente. Observou-se que os tempos medidos por ambos os modos apresentaram boa proximidade entre os valores da execução de cada aluno, indicando que o modo automatizado pode representar um substituto confiável para o modo convencional. A pesquisa também mostrou benefícios e vantagens para professores de Educação Física, quanto ao aspecto referente ao armazenamento das informações de forma automática no próprio sistema evitando desta forma, a utilização de várias fichas de protocolo e anotações durante a fase de realização dos testes.
- 19 October 2022
- Published by SWGE Sistemas Ltda in Proceedings Xxii Congresso Brasileiro de Automática
- Vol. 3 (1)
Programação da Operação de um Dia à Frente de Microrredes Isoladas
This paper develops a day-ahead operational planning based on optimal power flow (OPF) for isolated microgrids which are equipped with battery bank, diesel generation and renewable resources. The renewable resources available in the studied microgrid are the photovoltaic solar and wind energies, which present an intermittent behavior, and so it is modeled by a probability density function in the proposed OPF formulation, in order to make the objective function sensitive to climatic uncertainties inherent to the intermittent resources. The objective function of the OPF incorporates in its formulation the costs associated with the operation of diesel generators and the use of the battery bank, in order to minimize fuel consumption and maximize the lifetime of the battery bank. The differential evolution optimization technique was used to solve the proposed formulation and to obtain a minimum cost of operation of the microgrid under study. The proposed formulation was tested in different scenarios and the obtained results showed that the day-ahead operational planning in microgrids is sensitive to variations in weather conditions, that occur at each hour of the day, and the changes made in the state of charge of the battery bank.
- 19 October 2022
- Published by SWGE Sistemas Ltda in Proceedings Xxii Congresso Brasileiro de Automática
- Vol. 3 (1)
Programação da Operação de um Dia à Frente de Microrredes Isoladas
This paper develops a day-ahead operational planning based on optimal power flow (OPF) for isolated microgrids which are equipped with battery bank, diesel generation and renewable resources. The renewable resources available in the studied microgrid are the photovoltaic solar and wind energies, which present an intermittent behavior, and so it is modeled by a probability density function in the proposed OPF formulation, in order to make the objective function sensitive to climatic uncertainties inherent to the intermittent resources. The objective function of the OPF incorporates in its formulation the costs associated with the operation of diesel generators and the use of the battery bank, in order to minimize fuel consumption and maximize the lifetime of the battery bank. The differential evolution optimization technique was used to solve the proposed formulation and to obtain a minimum cost of operation of the microgrid under study. The proposed formulation was tested in different scenarios and the obtained results showed that the day-ahead operational planning in microgrids is sensitive to variations in weather conditions, that occur at each hour of the day, and the changes made in the state of charge of the battery bank.
- 14 August 2020
- Published by Sociedade Brasileira de Automatica
- Vol. 1 (1)
Fluxo de Potência Ótimo Aplicado à Programação da Operação de um Dia à Frente de Microrredes Isoladas
- 14 August 2020
- Published by Sociedade Brasileira de Automatica
- Vol. 1 (1)
Fluxo de Potência Ótimo Aplicado à Programação da Operação de um Dia à Frente de Microrredes Isoladas
- 2 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Stochastic Optimal Power Flow Applied in Day-Ahead Planning of Isolated Microgrids
Due to the growing demand for energy in the last decades, the electric power system has been facing challenges to supply the power consumed by population. In this sense, isolated microgrids have emerged as a viable alternative based on the use of local energy resources to feed hard to reach areas. In this context, this paper develops a day-ahead energy based on optimal power flow for an isolated microgrid in Brazil equipped with storage system, backup generation and renewable resources. The renewable resource available in the studied microgrid is the photovoltaic solar energy, which presents an intermittent behavior, and so it is modeled by a probability density function in the proposed OPF formulation. The storage system represents approximately 52% of the total microgrid investment. Considering that, the objective function of the OPF incorporates the costs associated to the life cycle of the storage system and the fuel consumption with the backup generation, as well as, a stochastic model to estimate the costs of the photovoltaic solar energy. The proposed formulation was solved using Differential Evolution algorithm to obtain a minimal generation cost considering the load profile of a typical day.
- 2 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Stochastic Optimal Power Flow Applied in Day-Ahead Planning of Isolated Microgrids
Due to the growing demand for energy in the last decades, the electric power system has been facing challenges to supply the power consumed by population. In this sense, isolated microgrids have emerged as a viable alternative based on the use of local energy resources to feed hard to reach areas. In this context, this paper develops a day-ahead energy based on optimal power flow for an isolated microgrid in Brazil equipped with storage system, backup generation and renewable resources. The renewable resource available in the studied microgrid is the photovoltaic solar energy, which presents an intermittent behavior, and so it is modeled by a probability density function in the proposed OPF formulation. The storage system represents approximately 52% of the total microgrid investment. Considering that, the objective function of the OPF incorporates the costs associated to the life cycle of the storage system and the fuel consumption with the backup generation, as well as, a stochastic model to estimate the costs of the photovoltaic solar energy. The proposed formulation was solved using Differential Evolution algorithm to obtain a minimal generation cost considering the load profile of a typical day.