Francisco da Costa Lopes
Research Subjects
Francisco da Costa Lopes has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Edson H. Watanabe
Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
6 shared publications- Derick Furquim Pereira
Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
3 shared publications Luis Guilherme B. Rolim
Department of Electrical Engineering, The Alberto Luiz Coimbra Institute for Graduate Studies and Research in Engineering (COPPE), Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
2 shared publications- Alexander Polasek
Electric Power Research Center, Brazil
1 shared publication Camila Barreto Fernandes
Engenharia Elétrica - CEFET/RJ, Centro Federal de Educação Tecnológica, Celso Suckow da Fonseca, Angra dos Reis, Brasil
1 shared publication- Edson Hirokazu Watanabe
Department of Electrical Engineering, COPPE/Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
1 shared publication
Latest Publications
- Top Cited Papers
- 18 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 68 (4) , 3213-3223
Nonlinear Model Predictive Control for the Energy Management of Fuel Cell Hybrid Electric Vehicles in Real Time
This paper proposes an energy management system (EMS) for a fuel cell hybrid electric vehicle (FCHEV). The EMS is based on nonlinear model predictive control (NMPC) and employs a recurrent neural network (RNN) for modeling a proton exchange membrane (PEM) fuel cell (FC). The NMPC makes it possible the formulation of control objectives not allowed by a linear model predictive control (MPC), such as maximum efficiency point tracking (MEPT) of the FC, while the RNN can accurately predict the FC nonlinear dynamics. The EMS was implemented on a low-cost development board, and the experiments were performed in real-time on a hardware-in-the-loop (HiL) test bench equipped with a real 3 kW FC stack. The experimental results demonstrate that the NMPC EMS is able to meet the vehicle's energy demand, as well as to operate the FC in its most efficient region. Moreover, a comparative study is performed between the proposed NMPC, a linear MPC and hysteresis band control (HBC). The results of this comparative study demonstrate that the NMPC provides a better fuel economy and can reduce FC degradation.
- 18 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 68 (4) , 3213-3223
Top Cited PapersNonlinear Model Predictive Control for the Energy Management of Fuel Cell Hybrid Electric Vehicles in Real Time
This paper proposes an energy management system (EMS) for a fuel cell hybrid electric vehicle (FCHEV). The EMS is based on nonlinear model predictive control (NMPC) and employs a recurrent neural network (RNN) for modeling a proton exchange membrane (PEM) fuel cell (FC). The NMPC makes it possible the formulation of control objectives not allowed by a linear model predictive control (MPC), such as maximum efficiency point tracking (MEPT) of the FC, while the RNN can accurately predict the FC nonlinear dynamics. The EMS was implemented on a low-cost development board, and the experiments were performed in real-time on a hardware-in-the-loop (HiL) test bench equipped with a real 3 kW FC stack. The experimental results demonstrate that the NMPC EMS is able to meet the vehicle's energy demand, as well as to operate the FC in its most efficient region. Moreover, a comparative study is performed between the proposed NMPC, a linear MPC and hysteresis band control (HBC). The results of this comparative study demonstrate that the NMPC provides a better fuel economy and can reduce FC degradation.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1878-1883
Neural Generalized Predictive Control for Tracking Maximum Efficiency and Maximum Power Points of PEM Fuel Cell Stacks
This work proposes a Neural Generalized Predictive Control (NGPC) for tracking the maximum efficiency or the maximum power point of proton exchange membrane fuel cell (PEMFC) stacks. The NGPC consists of a nonlinear type of model predictive control (MPC) in which the prediction model is a neural network (NN). Such control strategy combines the advantages of PEMFC modeling using NNs and the MPC family of controllers. NNs are capable of modeling the whole nonlinear dynamics and the time-varying behavior of PEMFC stacks, while the MPC can easily handle system constraints and it manipulates multiple control variables of complex systems. Through its optimization algorithm, the NGPC determines an optimal current necessary for the stack to operate at maximum efficiency or maximum power. This paper demonstrates the operation of the proposed control technique through a simulation study of a grid-connected PEMFC power generation system.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1878-1883
Neural Generalized Predictive Control for Tracking Maximum Efficiency and Maximum Power Points of PEM Fuel Cell Stacks
This work proposes a Neural Generalized Predictive Control (NGPC) for tracking the maximum efficiency or the maximum power point of proton exchange membrane fuel cell (PEMFC) stacks. The NGPC consists of a nonlinear type of model predictive control (MPC) in which the prediction model is a neural network (NN). Such control strategy combines the advantages of PEMFC modeling using NNs and the MPC family of controllers. NNs are capable of modeling the whole nonlinear dynamics and the time-varying behavior of PEMFC stacks, while the MPC can easily handle system constraints and it manipulates multiple control variables of complex systems. Through its optimization algorithm, the NGPC determines an optimal current necessary for the stack to operate at maximum efficiency or maximum power. This paper demonstrates the operation of the proposed control technique through a simulation study of a grid-connected PEMFC power generation system.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1017-1022
Prediction of PEMFC stack efficiency using recurrent neural networks
Hydrogen-related technologies are a promising solution for energy storage systems. The energy surplus from renewables or the off-peak power in a centralized electric system can be used to feed an electrolyzer to produce hydrogen. Then, the stored hydrogen can be converted to electric energy using proton exchange membrane fuel cells (PEMFCs), which have higher efficiency than other conventional energy conversion technologies. However, a PEMFC stack might be subject to variations in its energy conversion efficiency due to undesirable changes in the internal operating conditions, which may lead to a relatively high loss of generation capacity and an increase in the hydrogen consumption. A system identification method using recurrent neural networks (RNNs) able to build prediction models for the efficiency is proposed in this paper aiming at a further use in a control application to maximize the stack's efficiency in real-time. A 3 kW commercial PEMFC stack operating under a typical residential load profile is employed in this work to obtain experimental data. Three models are developed with the aforementioned method using data sets with different sizes for training the RNNs. The results show good agreement between the predicted and the measured efficiency, with a coefficient of determination (R2 coefficient) higher than 0.999 and a validation mean squared error (MSE) lower than 0.02 for most of the models. The results also reveal that, for a fixed prediction horizon of 6.4 h, all the three models present similar performance, with the size of the training data sets making little difference in the performance indicators.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1017-1022
Prediction of PEMFC stack efficiency using recurrent neural networks
Hydrogen-related technologies are a promising solution for energy storage systems. The energy surplus from renewables or the off-peak power in a centralized electric system can be used to feed an electrolyzer to produce hydrogen. Then, the stored hydrogen can be converted to electric energy using proton exchange membrane fuel cells (PEMFCs), which have higher efficiency than other conventional energy conversion technologies. However, a PEMFC stack might be subject to variations in its energy conversion efficiency due to undesirable changes in the internal operating conditions, which may lead to a relatively high loss of generation capacity and an increase in the hydrogen consumption. A system identification method using recurrent neural networks (RNNs) able to build prediction models for the efficiency is proposed in this paper aiming at a further use in a control application to maximize the stack's efficiency in real-time. A 3 kW commercial PEMFC stack operating under a typical residential load profile is employed in this work to obtain experimental data. Three models are developed with the aforementioned method using data sets with different sizes for training the RNNs. The results show good agreement between the predicted and the measured efficiency, with a coefficient of determination (R2 coefficient) higher than 0.999 and a validation mean squared error (MSE) lower than 0.02 for most of the models. The results also reveal that, for a fixed prediction horizon of 6.4 h, all the three models present similar performance, with the size of the training data sets making little difference in the performance indicators.
- 1 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Power management strategy based on the pq-Theory applied to a cascaded modular converter for fuel cell vehicle application
This paper proposes a new power management strategy based on pq-Theory for fuel cell and electric vehicle applications. Using a modular cascaded converter topology, more than one power source could be combined with capacitors to supply active and reactive power in an efficient manner to the electric motor. The control strategy to separate mean and oscillating active power and reactive power, as well as capacitors' voltage regulation control, are described. Simulation results are shown to validate the control strategy. Experimental results using a minimal topology prototype and static load show the practical application of the control.
- 1 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Power management strategy based on the pq-Theory applied to a cascaded modular converter for fuel cell vehicle application
This paper proposes a new power management strategy based on pq-Theory for fuel cell and electric vehicle applications. Using a modular cascaded converter topology, more than one power source could be combined with capacitors to supply active and reactive power in an efficient manner to the electric motor. The control strategy to separate mean and oscillating active power and reactive power, as well as capacitors' voltage regulation control, are described. Simulation results are shown to validate the control strategy. Experimental results using a minimal topology prototype and static load show the practical application of the control.
- 1 June 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Neural network modeling strategy applied to a multi-stack PEM fuel cell system
This work proposes applying a modeling methodology based on recurrent neural networks to a multi-stack fuel cell system composed of four Proton Exchange Membrane Fuel Cell (PEMFC) stacks. Even if the stacks have the same rated power and are from the same manufacturer, very often they present different performances (voltage response, efficiency and power curves). In this way, a model able to predict the behavior of each stack is necessary to guarantee an optimized operation of the whole system. Hence, the aforementioned methodology is used to obtain a prediction model for each stack aiming at their final application in a predictive control system. The models are also able to predict the power availability of the multi-stack system, being useful to be employed in the prognostics of the performance of the system in a vehicular application.
- 1 June 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Neural network modeling strategy applied to a multi-stack PEM fuel cell system
This work proposes applying a modeling methodology based on recurrent neural networks to a multi-stack fuel cell system composed of four Proton Exchange Membrane Fuel Cell (PEMFC) stacks. Even if the stacks have the same rated power and are from the same manufacturer, very often they present different performances (voltage response, efficiency and power curves). In this way, a model able to predict the behavior of each stack is necessary to guarantee an optimized operation of the whole system. Hence, the aforementioned methodology is used to obtain a prediction model for each stack aiming at their final application in a predictive control system. The models are also able to predict the power availability of the multi-stack system, being useful to be employed in the prognostics of the performance of the system in a vehicular application.
- 13 March 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 62 (8) , 5155-5163
A Control-Oriented Model of a PEM Fuel Cell Stack Based on NARX and NOE Neural Networks
Hydrogen-related technologies have been proposed as an alternative to store the energy surplus from renewable sources. Among these technologies, the proton exchange membrane fuel cell (PEMFC) and electrolyzer are the preferred choice for practical applications since they have reached a certain level of maturity and are commercially available at present. In order to achieve a cost-effective operation, a PEMFC stack must operate at maximum efficiency most of the time. Since PEMFC stacks present a time-varying behavior, an adaptive model-based controller should be employed to accomplish this goal. A fixed-parameter electrochemical model may not offer a reliable prediction over a midterm time horizon for such a controller. For this reason, system identification techniques appear as more appropriate choices to obtain an effective model for this class of control systems. In this paper, a system identification modeling methodology employing nonlinear autoregressive with exogenous input (NARX) and nonlinear output error (NOE) neural networks is presented to obtain a black-box model of a PEMFC stack oriented for a predictive control system. The experimental data for the model development are obtained with a commercial 3-kW PEMFC stack. The model built according to the proposed methodology provides accurate predictions of the voltage for the whole operating range of the stack for a long time and, hence, the ability to represent the time-varying behavior of a PEMFC stack for a predictive control application.
- 13 March 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 62 (8) , 5155-5163
A Control-Oriented Model of a PEM Fuel Cell Stack Based on NARX and NOE Neural Networks
Hydrogen-related technologies have been proposed as an alternative to store the energy surplus from renewable sources. Among these technologies, the proton exchange membrane fuel cell (PEMFC) and electrolyzer are the preferred choice for practical applications since they have reached a certain level of maturity and are commercially available at present. In order to achieve a cost-effective operation, a PEMFC stack must operate at maximum efficiency most of the time. Since PEMFC stacks present a time-varying behavior, an adaptive model-based controller should be employed to accomplish this goal. A fixed-parameter electrochemical model may not offer a reliable prediction over a midterm time horizon for such a controller. For this reason, system identification techniques appear as more appropriate choices to obtain an effective model for this class of control systems. In this paper, a system identification modeling methodology employing nonlinear autoregressive with exogenous input (NARX) and nonlinear output error (NOE) neural networks is presented to obtain a black-box model of a PEMFC stack oriented for a predictive control system. The experimental data for the model development are obtained with a commercial 3-kW PEMFC stack. The model built according to the proposed methodology provides accurate predictions of the voltage for the whole operating range of the stack for a long time and, hence, the ability to represent the time-varying behavior of a PEMFC stack for a predictive control application.
- 1 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650454,p. 601-608
Analysis of the time-varying behavior of a PEM fuel cell stack and dynamical modeling by recurrent neural networks
This work presents an analysis of the time-varying behavior of a PEM fuel cell (PEMFC) stack based on experimental results, pointing out some constraints that should be taken into account in the development of a control system for the stack. A system identification methodology based on recurrent neural networks is proposed to model such behavior. A dynamic model using this technique is developed for a commercial PEMFC stack operating under a real load profile. The results show that the neural model is able to track the stack voltage dynamics with a very low error.
- 1 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650454,p. 601-608
Analysis of the time-varying behavior of a PEM fuel cell stack and dynamical modeling by recurrent neural networks
This work presents an analysis of the time-varying behavior of a PEM fuel cell (PEMFC) stack based on experimental results, pointing out some constraints that should be taken into account in the development of a control system for the stack. A system identification methodology based on recurrent neural networks is proposed to model such behavior. A dynamic model using this technique is developed for a commercial PEMFC stack operating under a real load profile. The results show that the neural model is able to track the stack voltage dynamics with a very low error.
- 1 February 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 661-667
A recurrent neural approach for modeling non-reproducible behavior of PEM fuel cell stacks
This work presents a recurrent neural model for PEM fuel cell stacks based on NARX and NOE neural structures. The practical difficulties to employ electrochemical models and the causes of the odd behavior observed in some PEM stacks are discussed. The model developed predicts the terminal voltage of a stack even in the situation where it presents a non-reproducible behavior, such as unexpected voltage fluctuations. The predictive capacity of the model is evaluated in two different scenarios, showing good agreement with the measured data.
- 1 February 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 661-667
A recurrent neural approach for modeling non-reproducible behavior of PEM fuel cell stacks
This work presents a recurrent neural model for PEM fuel cell stacks based on NARX and NOE neural structures. The practical difficulties to employ electrochemical models and the causes of the odd behavior observed in some PEM stacks are discussed. The model developed predicts the terminal voltage of a stack even in the situation where it presents a non-reproducible behavior, such as unexpected voltage fluctuations. The predictive capacity of the model is evaluated in two different scenarios, showing good agreement with the measured data.
- Open Access
- 1 January 2012
- Published by Elsevier in Physics Procedia
- Vol. 36, 1242-1247
Short-Circuit Tests and Simulations with a SCFCL Modular Assembly
- 1 January 2012
- Published by Elsevier in Physics Procedia
- Vol. 36, 1242-1247
Open AccessShort-Circuit Tests and Simulations with a SCFCL Modular Assembly
- 1 September 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650454,p. 775-782
Experimental and theoretical development of a PEM electrolyzer model applied to energy storage systems
Electrolyzers have been pointed out as a promising technology for use in energy storage applications. Basically, electrolyzers convert electrical energy to electrochemical energy, which stays encapsulated in diatomic hydrogen molecule for posterior use in fuel cells, which convert the electrochemical energy back to electrical energy. The main advantages of the electrolysis process are the zero-emission of greenhouse gases, the use of water as the source of hydrogen, and the high efficiency in energy conversion. Electrolyzers can be fed by the grid or by renewable sources such as solar and wind. In both cases a power converter is necessary to conditioning the electrical energy in order to deliver a clean DC current to the electrolyzer. In this context, this work shows a modeling of a PEM (proton exchange membrane) electrolyzer intending its use in conjunction with power converters. The main losses in such electrolyzer are modeled and it is shown the influence of the current ripple in the electrolyzer behavior and efficiency.
- 1 September 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650454,p. 775-782
Experimental and theoretical development of a PEM electrolyzer model applied to energy storage systems
Electrolyzers have been pointed out as a promising technology for use in energy storage applications. Basically, electrolyzers convert electrical energy to electrochemical energy, which stays encapsulated in diatomic hydrogen molecule for posterior use in fuel cells, which convert the electrochemical energy back to electrical energy. The main advantages of the electrolysis process are the zero-emission of greenhouse gases, the use of water as the source of hydrogen, and the high efficiency in energy conversion. Electrolyzers can be fed by the grid or by renewable sources such as solar and wind. In both cases a power converter is necessary to conditioning the electrical energy in order to deliver a clean DC current to the electrolyzer. In this context, this work shows a modeling of a PEM (proton exchange membrane) electrolyzer intending its use in conjunction with power converters. The main losses in such electrolyzer are modeled and it is shown the influence of the current ripple in the electrolyzer behavior and efficiency.