José Vieira - Academia.edu (original) (raw)

Papers by José Vieira

Research paper thumbnail of A High-Performance Stand-Alone Solar PV Power System for LED Lighting

ISRN Renewable Energy, 2013

This paper presents new improvements and real result of a stand-alone photovoltaic power system f... more This paper presents new improvements and real result of a stand-alone photovoltaic power system for LED lighting that was developed previously. The actual system, during day, charges a lead acid battery using MPPT algorithm for power transfer optimization, and, during night, it supervises battery discharge and controls the current in the power LED array. The improvements are in hardware and software. The hardware was simplified using only one DC/DC converter and only one microcontroller making it more efficient. The system board uses an ATMEL ATTINY861V microcontroller, a single-ended primary inductance converter (SEPIC), and sensors to read input and output voltages and currents to control all system. The software improvements are made in the battery charging algorithm, battery discharging algorithm, and in current control of the power LED array adjusting the light intensity. Moreover, results are presented showing the balance of energy in a period of 24 hours: first results of the...

Research paper thumbnail of Adaptable PID Versus Smith Predictive Control Applied to an Electric Water Heater System

Frontiers of Model Predictive Control, 2012

Research paper thumbnail of Implementing the Levenberg-Marquardt Algorithm on-line: A Sliding Window Approach with Early Stopping

IFAC Proceedings Volumes, 2004

The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial... more The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial Neural Networks but its computational complexity and the difficulty to compute the trust region have made it very difficult to develop a true iterative version to use in on-line training. The algorithm is frequently used for off-line training in batch versions although some attempts have been made to implement iterative versions. To overcome the difficulties in implementing the iterative version, a batch sliding window with Early Stopping version, which uses a hybrid Direct/Specialized evaluation procedure is proposed and tested with a real system.

Research paper thumbnail of Hybrid neuro-fuzzy network-priori knowledge model in temperature control of a gas water heater system

Proceedings - HIS 2005: Fifth International Conference on Hybrid Intelligent Systems, 2005

This paper presents an hybrid neuro-fuzzy networkpriori knowledge model in temperature control of... more This paper presents an hybrid neuro-fuzzy networkpriori knowledge model in temperature control of a gas water heater system. The hybrid model consists in a cascade connection of two blocks: an approximate First Principles Model (FPM) and an unknown block. The first principles model is constructed based in the balance equations of the system and in a priori knowledge. The unknown part of the global model is modeled with a neuro-fuzzy structure which is based in a priori knowledge and identified with input/output data of the system. The Neuro-Fuzzy Hybrid Model (NFHM) of the gas water gas heater consists in a cascade connection of a neuro-fuzzy model with a first principles model. The proposed hybrid model is tuned using gradient decent combined with least square algorithm off-line. A Smith predictive controller is constructed based in the water heater hybrid model. Due to the characteristics of the model, the Smith predictive control structure is simplified, linearizing the system relatively to the input gas flow and it presents a special configuration for multiple input with different time delays. Finally, the control of the output water temperature results are shown and discussed.

Research paper thumbnail of Maximum power point tracker applied in batteries charging with PV panels

2008 IEEE International Symposium on Industrial Electronics, 2008

This work deals with the design and a prototype implementation of a real time maximum power point... more This work deals with the design and a prototype implementation of a real time maximum power point tracker (MPPT) for photovoltaic (PV) panel aiming to improve energy conversion efficiency. This MPPT algorithm is integrated in the charging process of lead-acid batteries making an autonomous system that can be used to feed any autonomous application. The photovoltaic system exhibits a non-linear i-v characteristic and its maximum power point varies with solar insolation and temperature. To control the maximum transfer power from a PV panel the Perturbation and Observation (P&O) MPPT algorithm is executed by a simple microcontroller ATMEL ATTINY861V using the PV voltage and current information and controlling the duty cycle of a pulse width modulation (PWM) signal applied in to a DC/DC converter. The schematic and design of the single-ended primary inductance converter (SEPIC) is presented. This DC/DC converter is chosen because the input voltage can be higher or lower than the output voltage witch presents obvious design advantages. With the P&O MPPT algorithm implemented and executed by the microcontroller, the different charging stages of a lead-acid battery are showed and executed. Finally, experimental results of the performance of the designed P&O MPPT algorithm are presented and compared with the results achieved with the direct connection of the PV panel to the battery.

Research paper thumbnail of Implementation of the Delay Compensator Approach

Research paper thumbnail of Maximum Power Point Tracker Applied to Charging Batteries with PV Panels

Solar Collectors and Panels, Theory and Applications, 2010

Research paper thumbnail of Implementation of a stand-alone photovoltaic lighting system with MPPT battery charging and LED current control

Proceedings of the IEEE International Conference on Control Applications, 2010

This paper presents a efficient stand-alone battery photovoltaic (PV) lighting system which can p... more This paper presents a efficient stand-alone battery photovoltaic (PV) lighting system which can provide functional illumination based on power light-emitting diodes (PLEDs). PLED with specific features of small size, long life and high-brightness light will be choices of future light sources. The PLEDs are feed using a lead acid battery that is charged with a PV panel. This paper presents an interface board with a ATMEL ATTINY861V microcontroller, a single-ended primary inductance converter (SEPIC) and input and output voltage and current measurements. The microcontroller runs the perturbation and observation (P&O) maximum power point tracker (MPPT) algorithm used in battery charging process. This algorithm makes the system more efficient. In order to control the PLEDs current, an equal interface board is used running now the proportional integral (PI) current PLED control algorithm adjusting the wanted level of light in the PLEDs array. The two identical interfaces boards based in the economic microprocessor achieved very good results in battery charging and discharge supervision improving the efficiency a lifetime of the lead acid batteries (first board) and presents good current control results in the PLEDs array (second equal board) providing a constant PLEDs light even in voltage battery variations or discharges. The stand alone lighting system monitors the surround area and if it feels any movement it changes the level of light of PLEDs from signal light to illumination light. After a pre-defined time it comes back to signal light, saving energy.

Research paper thumbnail of Thermoelectric generator using water gas heater energy for battery charging

2009 IEEE International Conference on Control Applications, 2009

This work deals with the design and a prototype implementation of a maximum power point tracker (... more This work deals with the design and a prototype implementation of a maximum power point tracker (MPPT) for a thermoelectric (TE) module aiming to improve energy conversion efficiency in battery charging. This system uses TE devices that directly convert heat energy from a water gas heater to electricity to charge a battery. The TE module exhibits a non-linear i-v characteristic and its maximum power point varies with the change of its surfaces temperatures. A SEPIC (single-ended primary inductance converter) DC-DC converter is applied and controlled by a microcontroller and to achieve the maximum power point tracking it is used the perturbation and observation (P&O) algorithm. The microcontroller will also control the charging process of lead-acid battery making an autonomous system that is used to feed the necessary electronics that controls an autonomous gas water heater system. The objectives of this work are to study the principle of TE power generation and to design and develop a TE battery charger that uses heat of a water gas heater system making an autonomous electrical system. The two different charging stages of a lead-acid battery lead us to a good interface board. Finally, experimental results performance of the first stage of charge using P&O MPPT algorithm are presented and compared with the results achieved with the direct connection of the TE module to the battery.

Research paper thumbnail of On the adaptation to non-individualised HRTF auralisations: A longitudinal study

Auralisations with HRTFs are an innovative tool for the reproduction of acoustic space. Their bro... more Auralisations with HRTFs are an innovative tool for the reproduction of acoustic space. Their broad applicability depends on the use of non-individualised models, but little is known on how humans adapt to these sounds. Previous findings have shown that simple exposure to non-individualised virtual sounds did not provide a quick adaptation, but that training and feedback would boost this process. Here, we were interested in analyzing the long-term effect of such training-based adaptation. We trained listeners in azimuth and elevation discrimination in two separate experiments and retested them immediately, one hour, one day, one week and one month after. Results revealed that, with active learning and feedback, all participants lowered their localization errors. This benefit was still found one month after training. Interestingly, participants who had trained previously with elevations were better in azimuth localization and vice-versa. Our findings suggest that humans adapt easily to new anatomically shaped spectral cues and they are able to transfer that adaptation to non-trained sounds.

Research paper thumbnail of Real-time auralisation system for virtual microphone positioning

A computer application was developed to simulate the process of microphone positioning in sound r... more A computer application was developed to simulate the process of microphone positioning in sound recording applications. A dense, regular grid of impulse responses pre-recorded on the region of the room under study allowed the sound captured by a virtual microphone to be auralised through real-time convolution with an anechoic stream representing the sound source. Convolution was performed using a block-based variation on the overlap-add method where the summation of many small subconvolutions produced each block of output data samples. As the applied RIR filter varied on successive audio output blocks, a short cross fade was applied to avoid glitches in the audio. The maximum possible length of impulse response applied was governed by the size of audio processing block (hence latency) employed by the program. Larger blocks allowed a lower processing time per sample. At 23.2ms latency (1024 samples at 44.1kHz), it was possible to apply 9 second impulse responses on a standard laptop computer.

Research paper thumbnail of Special issue on Controlo2012: new applications of artificial neural networks in modeling and control

Neural Computing and Applications, 2013

The Portuguese Conference on Automatic Control, Controlo for short, started in 1994 and had its f... more The Portuguese Conference on Automatic Control, Controlo for short, started in 1994 and had its first edition in Lisbon. It is organized by the Portuguese Association of Automatic Control, which is the Portuguese National Member Organization of the International Federation of Automatic Control (IFAC). The conference has been organized every two years and attracts researchers and practitioners in the area of Automatic Control, in a broad sense, from universities and companies around the world, with a strong emphasis in the Portuguese, Spanish, and Brazilian community. In 2012, the 10th edition of the conference took place in Funchal, Madeira, Portugal, and received a large number of submissions and participants representing all the continents. Since the very beginning of the uprising of Artificial Neural Networks (ANN) with the remarkable milestones such as the first artificial neural network model developed by McCulloch and Pitts [1], the initial Perceptron model by Rosenblatt and Wightman [2], the limitations of the perceptron presented by Minsky and Papert [3], or the proof that ANN could be used as universal approximator by Cybenko [4], among many others, ANN have found

Research paper thumbnail of Passing from a Gas to an Electric Water Heater System: Adaptive PID Versus Smith Predictive Control

Intelligent Engineering Systems, 2007 International Conference on, 2007

This paper presents the control results of an electric water heater system using two approaches: ... more This paper presents the control results of an electric water heater system using two approaches: adaptable proportional integral derivative and Smith predictive control based in the physical internal model control structure. The electric water heater was modelled with two variable blocks connected in series: a first order system and a time delay. In fact, the gain, the time constant and the time delay of the system change linearly with the water that flows in the permutation chamber. The physical model of the electric water heater system was retched based in energy dynamic equations and validated with open loop data of the system in a similar way that was made in a previews study about modelling and controlling a gas water heater. The two different control algorithms explored are the adaptive proportional integral derivative (APID) and the Smith predictive control (SPC) based in the internal physical model control algorithm. The first approach has some problems dealing with the time constant and the time delay variations of the system. This solution can control the overshoot for all different water flows but the time constant of the close loop systems changes with the water flow. The APID does not deal well with water flow variations. The second approach is more adequate to control this kind of systems (first order system followed by a time delay that changes in time). The SPC loop is indicated for control time delay systems and with the à priori knowledge of the physical model we can achieve a very good control result. Finally, these two algorithms are applied in controlling the system and the results are compared using the mean square error criterion.

Research paper thumbnail of A sliding window solution for the on-line implementation of the Levenberg–Marquardt algorithm

Engineering Applications of Artificial Intelligence, 2006

The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial... more The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial Neural Networks but its computational complexity and the difficulty to compute the trust region have made it very difficult to develop a true iterative version to use in on-line training. The algorithm is frequently used for off-line training in batch versions although some attempts have been made to implement iterative versions. To overcome the difficulties in implementing the iterative version, a batch sliding window with Early Stopping, which uses a hybrid Direct/Specialized evaluation procedure, is proposed and tested with a real system.

Research paper thumbnail of Artificial neural networks and neuro-fuzzy systems for modelling and controlling real systems: a comparative study

Engineering Applications of Artificial Intelligence, 2004

This article presents a comparison of artificial neural networks and neuro-fuzzy systems applied ... more This article presents a comparison of artificial neural networks and neuro-fuzzy systems applied for modelling and controlling a real system. The main objective is to model and control the temperature inside of a kiln for the ceramic industry. The details of all system components are described. The steps taken to arrive at the direct and inverse models using the two architectures: adaptive neuro fuzzy inference system and feedforward neural networks are described and compared. Finally, real-time control results using internal model control strategy are presented. Using available Matlab software for both algorithms, the objective is to show the implementation steps for modelling and controlling a real system. Finally, the performances of the two solutions were compared through different parameters for a specific real didactic case.

Research paper thumbnail of Neuro-Fuzzy Systems: A Survey

5th WSEAS NNA International Conference …, 2004

Abstract: – The techniques of artificial intelligence based in fuzzy logic and neural networks ar... more Abstract: – The techniques of artificial intelligence based in fuzzy logic and neural networks are frequently applied together. The reasons to combine these two paradigms come out of the difficulties and inherent limitations of each isolated paradigm. Generically, when they are used in a ...

Research paper thumbnail of Delay Compensator: an Approach to Reduce the Variable Sampling to Actuation Delay Effect in Distributed Real-time Control Systems

2006 IEEE Conference on Emerging Technologies and Factory Automation, 2006

This work presents the Delay Compensator an approach to deal with the sampling to actuation delay... more This work presents the Delay Compensator an approach to deal with the sampling to actuation delay effects in real-time distributed control systems. The Delay Compensator approach bases its action on the amount of the sampling to actuation delay affecting the system at each ...

Research paper thumbnail of A High-Performance Stand-Alone Solar PV Power System for LED Lighting

ISRN Renewable Energy, 2013

This paper presents new improvements and real result of a stand-alone photovoltaic power system f... more This paper presents new improvements and real result of a stand-alone photovoltaic power system for LED lighting that was developed previously. The actual system, during day, charges a lead acid battery using MPPT algorithm for power transfer optimization, and, during night, it supervises battery discharge and controls the current in the power LED array. The improvements are in hardware and software. The hardware was simplified using only one DC/DC converter and only one microcontroller making it more efficient. The system board uses an ATMEL ATTINY861V microcontroller, a single-ended primary inductance converter (SEPIC), and sensors to read input and output voltages and currents to control all system. The software improvements are made in the battery charging algorithm, battery discharging algorithm, and in current control of the power LED array adjusting the light intensity. Moreover, results are presented showing the balance of energy in a period of 24 hours: first results of the...

Research paper thumbnail of Adaptable PID Versus Smith Predictive Control Applied to an Electric Water Heater System

Frontiers of Model Predictive Control, 2012

Research paper thumbnail of Implementing the Levenberg-Marquardt Algorithm on-line: A Sliding Window Approach with Early Stopping

IFAC Proceedings Volumes, 2004

The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial... more The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial Neural Networks but its computational complexity and the difficulty to compute the trust region have made it very difficult to develop a true iterative version to use in on-line training. The algorithm is frequently used for off-line training in batch versions although some attempts have been made to implement iterative versions. To overcome the difficulties in implementing the iterative version, a batch sliding window with Early Stopping version, which uses a hybrid Direct/Specialized evaluation procedure is proposed and tested with a real system.

Research paper thumbnail of Hybrid neuro-fuzzy network-priori knowledge model in temperature control of a gas water heater system

Proceedings - HIS 2005: Fifth International Conference on Hybrid Intelligent Systems, 2005

This paper presents an hybrid neuro-fuzzy networkpriori knowledge model in temperature control of... more This paper presents an hybrid neuro-fuzzy networkpriori knowledge model in temperature control of a gas water heater system. The hybrid model consists in a cascade connection of two blocks: an approximate First Principles Model (FPM) and an unknown block. The first principles model is constructed based in the balance equations of the system and in a priori knowledge. The unknown part of the global model is modeled with a neuro-fuzzy structure which is based in a priori knowledge and identified with input/output data of the system. The Neuro-Fuzzy Hybrid Model (NFHM) of the gas water gas heater consists in a cascade connection of a neuro-fuzzy model with a first principles model. The proposed hybrid model is tuned using gradient decent combined with least square algorithm off-line. A Smith predictive controller is constructed based in the water heater hybrid model. Due to the characteristics of the model, the Smith predictive control structure is simplified, linearizing the system relatively to the input gas flow and it presents a special configuration for multiple input with different time delays. Finally, the control of the output water temperature results are shown and discussed.

Research paper thumbnail of Maximum power point tracker applied in batteries charging with PV panels

2008 IEEE International Symposium on Industrial Electronics, 2008

This work deals with the design and a prototype implementation of a real time maximum power point... more This work deals with the design and a prototype implementation of a real time maximum power point tracker (MPPT) for photovoltaic (PV) panel aiming to improve energy conversion efficiency. This MPPT algorithm is integrated in the charging process of lead-acid batteries making an autonomous system that can be used to feed any autonomous application. The photovoltaic system exhibits a non-linear i-v characteristic and its maximum power point varies with solar insolation and temperature. To control the maximum transfer power from a PV panel the Perturbation and Observation (P&O) MPPT algorithm is executed by a simple microcontroller ATMEL ATTINY861V using the PV voltage and current information and controlling the duty cycle of a pulse width modulation (PWM) signal applied in to a DC/DC converter. The schematic and design of the single-ended primary inductance converter (SEPIC) is presented. This DC/DC converter is chosen because the input voltage can be higher or lower than the output voltage witch presents obvious design advantages. With the P&O MPPT algorithm implemented and executed by the microcontroller, the different charging stages of a lead-acid battery are showed and executed. Finally, experimental results of the performance of the designed P&O MPPT algorithm are presented and compared with the results achieved with the direct connection of the PV panel to the battery.

Research paper thumbnail of Implementation of the Delay Compensator Approach

Research paper thumbnail of Maximum Power Point Tracker Applied to Charging Batteries with PV Panels

Solar Collectors and Panels, Theory and Applications, 2010

Research paper thumbnail of Implementation of a stand-alone photovoltaic lighting system with MPPT battery charging and LED current control

Proceedings of the IEEE International Conference on Control Applications, 2010

This paper presents a efficient stand-alone battery photovoltaic (PV) lighting system which can p... more This paper presents a efficient stand-alone battery photovoltaic (PV) lighting system which can provide functional illumination based on power light-emitting diodes (PLEDs). PLED with specific features of small size, long life and high-brightness light will be choices of future light sources. The PLEDs are feed using a lead acid battery that is charged with a PV panel. This paper presents an interface board with a ATMEL ATTINY861V microcontroller, a single-ended primary inductance converter (SEPIC) and input and output voltage and current measurements. The microcontroller runs the perturbation and observation (P&O) maximum power point tracker (MPPT) algorithm used in battery charging process. This algorithm makes the system more efficient. In order to control the PLEDs current, an equal interface board is used running now the proportional integral (PI) current PLED control algorithm adjusting the wanted level of light in the PLEDs array. The two identical interfaces boards based in the economic microprocessor achieved very good results in battery charging and discharge supervision improving the efficiency a lifetime of the lead acid batteries (first board) and presents good current control results in the PLEDs array (second equal board) providing a constant PLEDs light even in voltage battery variations or discharges. The stand alone lighting system monitors the surround area and if it feels any movement it changes the level of light of PLEDs from signal light to illumination light. After a pre-defined time it comes back to signal light, saving energy.

Research paper thumbnail of Thermoelectric generator using water gas heater energy for battery charging

2009 IEEE International Conference on Control Applications, 2009

This work deals with the design and a prototype implementation of a maximum power point tracker (... more This work deals with the design and a prototype implementation of a maximum power point tracker (MPPT) for a thermoelectric (TE) module aiming to improve energy conversion efficiency in battery charging. This system uses TE devices that directly convert heat energy from a water gas heater to electricity to charge a battery. The TE module exhibits a non-linear i-v characteristic and its maximum power point varies with the change of its surfaces temperatures. A SEPIC (single-ended primary inductance converter) DC-DC converter is applied and controlled by a microcontroller and to achieve the maximum power point tracking it is used the perturbation and observation (P&O) algorithm. The microcontroller will also control the charging process of lead-acid battery making an autonomous system that is used to feed the necessary electronics that controls an autonomous gas water heater system. The objectives of this work are to study the principle of TE power generation and to design and develop a TE battery charger that uses heat of a water gas heater system making an autonomous electrical system. The two different charging stages of a lead-acid battery lead us to a good interface board. Finally, experimental results performance of the first stage of charge using P&O MPPT algorithm are presented and compared with the results achieved with the direct connection of the TE module to the battery.

Research paper thumbnail of On the adaptation to non-individualised HRTF auralisations: A longitudinal study

Auralisations with HRTFs are an innovative tool for the reproduction of acoustic space. Their bro... more Auralisations with HRTFs are an innovative tool for the reproduction of acoustic space. Their broad applicability depends on the use of non-individualised models, but little is known on how humans adapt to these sounds. Previous findings have shown that simple exposure to non-individualised virtual sounds did not provide a quick adaptation, but that training and feedback would boost this process. Here, we were interested in analyzing the long-term effect of such training-based adaptation. We trained listeners in azimuth and elevation discrimination in two separate experiments and retested them immediately, one hour, one day, one week and one month after. Results revealed that, with active learning and feedback, all participants lowered their localization errors. This benefit was still found one month after training. Interestingly, participants who had trained previously with elevations were better in azimuth localization and vice-versa. Our findings suggest that humans adapt easily to new anatomically shaped spectral cues and they are able to transfer that adaptation to non-trained sounds.

Research paper thumbnail of Real-time auralisation system for virtual microphone positioning

A computer application was developed to simulate the process of microphone positioning in sound r... more A computer application was developed to simulate the process of microphone positioning in sound recording applications. A dense, regular grid of impulse responses pre-recorded on the region of the room under study allowed the sound captured by a virtual microphone to be auralised through real-time convolution with an anechoic stream representing the sound source. Convolution was performed using a block-based variation on the overlap-add method where the summation of many small subconvolutions produced each block of output data samples. As the applied RIR filter varied on successive audio output blocks, a short cross fade was applied to avoid glitches in the audio. The maximum possible length of impulse response applied was governed by the size of audio processing block (hence latency) employed by the program. Larger blocks allowed a lower processing time per sample. At 23.2ms latency (1024 samples at 44.1kHz), it was possible to apply 9 second impulse responses on a standard laptop computer.

Research paper thumbnail of Special issue on Controlo2012: new applications of artificial neural networks in modeling and control

Neural Computing and Applications, 2013

The Portuguese Conference on Automatic Control, Controlo for short, started in 1994 and had its f... more The Portuguese Conference on Automatic Control, Controlo for short, started in 1994 and had its first edition in Lisbon. It is organized by the Portuguese Association of Automatic Control, which is the Portuguese National Member Organization of the International Federation of Automatic Control (IFAC). The conference has been organized every two years and attracts researchers and practitioners in the area of Automatic Control, in a broad sense, from universities and companies around the world, with a strong emphasis in the Portuguese, Spanish, and Brazilian community. In 2012, the 10th edition of the conference took place in Funchal, Madeira, Portugal, and received a large number of submissions and participants representing all the continents. Since the very beginning of the uprising of Artificial Neural Networks (ANN) with the remarkable milestones such as the first artificial neural network model developed by McCulloch and Pitts [1], the initial Perceptron model by Rosenblatt and Wightman [2], the limitations of the perceptron presented by Minsky and Papert [3], or the proof that ANN could be used as universal approximator by Cybenko [4], among many others, ANN have found

Research paper thumbnail of Passing from a Gas to an Electric Water Heater System: Adaptive PID Versus Smith Predictive Control

Intelligent Engineering Systems, 2007 International Conference on, 2007

This paper presents the control results of an electric water heater system using two approaches: ... more This paper presents the control results of an electric water heater system using two approaches: adaptable proportional integral derivative and Smith predictive control based in the physical internal model control structure. The electric water heater was modelled with two variable blocks connected in series: a first order system and a time delay. In fact, the gain, the time constant and the time delay of the system change linearly with the water that flows in the permutation chamber. The physical model of the electric water heater system was retched based in energy dynamic equations and validated with open loop data of the system in a similar way that was made in a previews study about modelling and controlling a gas water heater. The two different control algorithms explored are the adaptive proportional integral derivative (APID) and the Smith predictive control (SPC) based in the internal physical model control algorithm. The first approach has some problems dealing with the time constant and the time delay variations of the system. This solution can control the overshoot for all different water flows but the time constant of the close loop systems changes with the water flow. The APID does not deal well with water flow variations. The second approach is more adequate to control this kind of systems (first order system followed by a time delay that changes in time). The SPC loop is indicated for control time delay systems and with the à priori knowledge of the physical model we can achieve a very good control result. Finally, these two algorithms are applied in controlling the system and the results are compared using the mean square error criterion.

Research paper thumbnail of A sliding window solution for the on-line implementation of the Levenberg–Marquardt algorithm

Engineering Applications of Artificial Intelligence, 2006

The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial... more The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial Neural Networks but its computational complexity and the difficulty to compute the trust region have made it very difficult to develop a true iterative version to use in on-line training. The algorithm is frequently used for off-line training in batch versions although some attempts have been made to implement iterative versions. To overcome the difficulties in implementing the iterative version, a batch sliding window with Early Stopping, which uses a hybrid Direct/Specialized evaluation procedure, is proposed and tested with a real system.

Research paper thumbnail of Artificial neural networks and neuro-fuzzy systems for modelling and controlling real systems: a comparative study

Engineering Applications of Artificial Intelligence, 2004

This article presents a comparison of artificial neural networks and neuro-fuzzy systems applied ... more This article presents a comparison of artificial neural networks and neuro-fuzzy systems applied for modelling and controlling a real system. The main objective is to model and control the temperature inside of a kiln for the ceramic industry. The details of all system components are described. The steps taken to arrive at the direct and inverse models using the two architectures: adaptive neuro fuzzy inference system and feedforward neural networks are described and compared. Finally, real-time control results using internal model control strategy are presented. Using available Matlab software for both algorithms, the objective is to show the implementation steps for modelling and controlling a real system. Finally, the performances of the two solutions were compared through different parameters for a specific real didactic case.

Research paper thumbnail of Neuro-Fuzzy Systems: A Survey

5th WSEAS NNA International Conference …, 2004

Abstract: – The techniques of artificial intelligence based in fuzzy logic and neural networks ar... more Abstract: – The techniques of artificial intelligence based in fuzzy logic and neural networks are frequently applied together. The reasons to combine these two paradigms come out of the difficulties and inherent limitations of each isolated paradigm. Generically, when they are used in a ...

Research paper thumbnail of Delay Compensator: an Approach to Reduce the Variable Sampling to Actuation Delay Effect in Distributed Real-time Control Systems

2006 IEEE Conference on Emerging Technologies and Factory Automation, 2006

This work presents the Delay Compensator an approach to deal with the sampling to actuation delay... more This work presents the Delay Compensator an approach to deal with the sampling to actuation delay effects in real-time distributed control systems. The Delay Compensator approach bases its action on the amount of the sampling to actuation delay affecting the system at each ...