Joao Fabro | UTFPR - UNIVERSIDADE TECNOLOGICA FEDERAL DO PARANÁ (original) (raw)
Papers by Joao Fabro
Anais do Workshop de …, 2008
This research provides a computer environment to support the students learning process. This envi... more This research provides a computer environment to support the students learning process. This environment allows teachers to build games of cards contextualized to the students' socio-cultural reality, using common vocabulary, myths, beliefs, taboos and knowledge of this students group. Thus, students will have the information in a familiar language, in order to allow a meaningful learning process. As teachers are co-authors of all game content, the game is fitted to their pedagogical goals. SBC 2008 29
Anais do Simpósio …, 2007
When an adolescents' teacher proposes in classroom the subject contraceptive methods, one of his ... more When an adolescents' teacher proposes in classroom the subject contraceptive methods, one of his worry is situations board that he believes to be a relative to an apprentice, like "the periodic abstinence is not one of the most efficient methods". But does the teacher know which method is used in that group of students? There proposes here a computational web game supported by the knowledge of common sense to board the transversal themes of the curriculum, like sexual orientation, helping the teacher in the context of the content presented to the local culture of the students, promoting the significant apprenticeship, where a new knowledge is related to an already existent knowledge in the cognitive structure of the student.
Martini, G.H.K and Fabro, J.A. "Hybrid filter for high-power converter systems", Proceedings of the 26th Symposium on Integrated Circuits and Systems Design (SBCCI), 2013 , Sep 2013
This paper presents a digital hybrid filter which can be applied to power electronics control sys... more This paper presents a digital hybrid filter which can be applied to power electronics control systems. The filter suppresses high-frequency noises while still providing a fast step response, its weighting algorithm is based on an open-loop criteria that analyses the discrepancy between an Infinite Impulse Response (IIR) and a Moving Average (MA) filter. The filter performance is compared to classical implementations through a step response and a Signal-to-Noise Ratio (SNR) analysis. The computational cost is also evaluated to verify its use on hard realtime systems. To evaluate the proposed filter, experiments were made on a microcontroller-based high-power frequency inverter with hard-time constraints, ensuring its applicability.
Neri, J.R.F.;Zatelli, M.R.;Fabro, J.A.; Santos, C.H.F. 2012, "A Proposal of QLearning to Control the Atack of a 2D Robot Soccer Simulation Team", Brazilian Robotics Symposium and Latin American Robotics Symposium
This document presents a novel approach to control the attack behavior of a team of simulated soc... more This document presents a novel approach to control the attack behavior of a team of simulated soccer playing robot of the Robocup 2D category. The presented approach modifies the behavior of each player only when in the state "controlling the ball". The approach is based on a modified Q-Learning algorithm that implements a continuous machine learning process. After an initial learning phase, each player uses its previous experience during the simulation of the game to decide if it should dribble, pass or kick the ball to the adversary goal. Simulation results show that the proposed approach is capable of learn how to score goals, even when faced with the -champion of the previous world championship.
Page 1. 1 AUTONOMOUS ROBOT NAVIGATION ON A FUZZY MAPPED ENVIRONMENT THROUGH NEURAL NETWORKS, WITH... more Page 1. 1 AUTONOMOUS ROBOT NAVIGATION ON A FUZZY MAPPED ENVIRONMENT THROUGH NEURAL NETWORKS, WITH EVOLUTIONARY PATH PLANNING João A. Fabro, Heitor S. Lopes, Lúcia Valéria R. Arruda ...
Page 1. A Proposal of a Fuzzy-Neuro Predictive Control, Tuned by Genetic Algorithms, with applica... more Page 1. A Proposal of a Fuzzy-Neuro Predictive Control, Tuned by Genetic Algorithms, with application to the Start-Up Control of a Distillation Column Joao Alberto Fabro UNIOESTE State University of West Paraná Av. Tarquınio ...
This paper presents two models for the Liquefied Petroleum Gas (LPG) transfer and storage operati... more This paper presents two models for the Liquefied Petroleum Gas (LPG) transfer and storage operations in a refinery. First, a simulation model is proposed, based on Petri Nets, which integrates the continuous and discrete parts of the process. The second model uses mixed integer linear programming techniques for the optimisation and scheduling of the system. The models allow the visualization and simulation of the problem, helping the system operator to easily test and correct scheduling plans despite the complexity of the operations. Results from the simulation model, when applied on the optimisation model, can then be used to reduce the severity of the problem.
This paper proposes the development of a fuzzy predictive control. Genetic algorithms (GA's) are ... more This paper proposes the development of a fuzzy predictive control. Genetic algorithms (GA's) are used to automatically tune the controller. A recurrent neural network is used to identify the process, and then provides predictions about the process behavior, based on control actions applied to the system. These predictions are used by the fuzzy controller, in order to accomplish a better control of an alcoholic fermentation process from chemical industry. This problem has been chosen due to its non-linearity and large accommodation time, that make it hard to control by standard controllers. Comparison of performance is made with non-predictive approaches(PID and Fuzzy-PD), and also with another predictive approach, GPC(Generalized Predictive Control).
Computers & Chemical Engineering, 2005
This work proposes the development of an intelligent predictive controller. Recurrent neural netw... more This work proposes the development of an intelligent predictive controller. Recurrent neural networks are used to identify the process, providing predictions about its behavior, based on control actions applied to the system. These information are then used by fuzzy controllers to accomplish a better control performance. Moreover, the fuzzy controller membership functions are evolved by Genetic algorithms (GA's) allowing an automatic tune of controllers.The combined use of these techniques make possible the control of multi-variable processes using several fuzzy controllers where the coupling among controlled variables are modeled by neural networks, and control objectives can be inserted into the GA fitness function.The methodology was applied to a simulation of the startup of a continuous distillation column. This process is chosen due to their characteristics, such as inertia, large accommodation time and conflicting control objectives that make these processes hard to control with traditional methods.
Anais do Workshop de …, 2008
This research provides a computer environment to support the students learning process. This envi... more This research provides a computer environment to support the students learning process. This environment allows teachers to build games of cards contextualized to the students' socio-cultural reality, using common vocabulary, myths, beliefs, taboos and knowledge of this students group. Thus, students will have the information in a familiar language, in order to allow a meaningful learning process. As teachers are co-authors of all game content, the game is fitted to their pedagogical goals. SBC 2008 29
Anais do Simpósio …, 2007
When an adolescents' teacher proposes in classroom the subject contraceptive methods, one of his ... more When an adolescents' teacher proposes in classroom the subject contraceptive methods, one of his worry is situations board that he believes to be a relative to an apprentice, like "the periodic abstinence is not one of the most efficient methods". But does the teacher know which method is used in that group of students? There proposes here a computational web game supported by the knowledge of common sense to board the transversal themes of the curriculum, like sexual orientation, helping the teacher in the context of the content presented to the local culture of the students, promoting the significant apprenticeship, where a new knowledge is related to an already existent knowledge in the cognitive structure of the student.
Martini, G.H.K and Fabro, J.A. "Hybrid filter for high-power converter systems", Proceedings of the 26th Symposium on Integrated Circuits and Systems Design (SBCCI), 2013 , Sep 2013
This paper presents a digital hybrid filter which can be applied to power electronics control sys... more This paper presents a digital hybrid filter which can be applied to power electronics control systems. The filter suppresses high-frequency noises while still providing a fast step response, its weighting algorithm is based on an open-loop criteria that analyses the discrepancy between an Infinite Impulse Response (IIR) and a Moving Average (MA) filter. The filter performance is compared to classical implementations through a step response and a Signal-to-Noise Ratio (SNR) analysis. The computational cost is also evaluated to verify its use on hard realtime systems. To evaluate the proposed filter, experiments were made on a microcontroller-based high-power frequency inverter with hard-time constraints, ensuring its applicability.
Neri, J.R.F.;Zatelli, M.R.;Fabro, J.A.; Santos, C.H.F. 2012, "A Proposal of QLearning to Control the Atack of a 2D Robot Soccer Simulation Team", Brazilian Robotics Symposium and Latin American Robotics Symposium
This document presents a novel approach to control the attack behavior of a team of simulated soc... more This document presents a novel approach to control the attack behavior of a team of simulated soccer playing robot of the Robocup 2D category. The presented approach modifies the behavior of each player only when in the state "controlling the ball". The approach is based on a modified Q-Learning algorithm that implements a continuous machine learning process. After an initial learning phase, each player uses its previous experience during the simulation of the game to decide if it should dribble, pass or kick the ball to the adversary goal. Simulation results show that the proposed approach is capable of learn how to score goals, even when faced with the -champion of the previous world championship.
Page 1. 1 AUTONOMOUS ROBOT NAVIGATION ON A FUZZY MAPPED ENVIRONMENT THROUGH NEURAL NETWORKS, WITH... more Page 1. 1 AUTONOMOUS ROBOT NAVIGATION ON A FUZZY MAPPED ENVIRONMENT THROUGH NEURAL NETWORKS, WITH EVOLUTIONARY PATH PLANNING João A. Fabro, Heitor S. Lopes, Lúcia Valéria R. Arruda ...
Page 1. A Proposal of a Fuzzy-Neuro Predictive Control, Tuned by Genetic Algorithms, with applica... more Page 1. A Proposal of a Fuzzy-Neuro Predictive Control, Tuned by Genetic Algorithms, with application to the Start-Up Control of a Distillation Column Joao Alberto Fabro UNIOESTE State University of West Paraná Av. Tarquınio ...
This paper presents two models for the Liquefied Petroleum Gas (LPG) transfer and storage operati... more This paper presents two models for the Liquefied Petroleum Gas (LPG) transfer and storage operations in a refinery. First, a simulation model is proposed, based on Petri Nets, which integrates the continuous and discrete parts of the process. The second model uses mixed integer linear programming techniques for the optimisation and scheduling of the system. The models allow the visualization and simulation of the problem, helping the system operator to easily test and correct scheduling plans despite the complexity of the operations. Results from the simulation model, when applied on the optimisation model, can then be used to reduce the severity of the problem.
This paper proposes the development of a fuzzy predictive control. Genetic algorithms (GA's) are ... more This paper proposes the development of a fuzzy predictive control. Genetic algorithms (GA's) are used to automatically tune the controller. A recurrent neural network is used to identify the process, and then provides predictions about the process behavior, based on control actions applied to the system. These predictions are used by the fuzzy controller, in order to accomplish a better control of an alcoholic fermentation process from chemical industry. This problem has been chosen due to its non-linearity and large accommodation time, that make it hard to control by standard controllers. Comparison of performance is made with non-predictive approaches(PID and Fuzzy-PD), and also with another predictive approach, GPC(Generalized Predictive Control).
Computers & Chemical Engineering, 2005
This work proposes the development of an intelligent predictive controller. Recurrent neural netw... more This work proposes the development of an intelligent predictive controller. Recurrent neural networks are used to identify the process, providing predictions about its behavior, based on control actions applied to the system. These information are then used by fuzzy controllers to accomplish a better control performance. Moreover, the fuzzy controller membership functions are evolved by Genetic algorithms (GA's) allowing an automatic tune of controllers.The combined use of these techniques make possible the control of multi-variable processes using several fuzzy controllers where the coupling among controlled variables are modeled by neural networks, and control objectives can be inserted into the GA fitness function.The methodology was applied to a simulation of the startup of a continuous distillation column. This process is chosen due to their characteristics, such as inertia, large accommodation time and conflicting control objectives that make these processes hard to control with traditional methods.