Articles de revista
http://hdl.handle.net/2117/7276
2015-11-25T06:38:54ZLTI ODE-valued neural networks
http://hdl.handle.net/2117/24573
LTI ODE-valued neural networks
Velasco García, Manel; Martín Rull, Enric Xavier; Angulo Bahón, Cecilio; Martí Colom, Pau
A dynamical version of the classical McCulloch & Pitts’ neural model is introduced in this paper. In this new approach, artificial neurons are characterized by: i) inputs in the form of differentiable continuous-time signals, ii) linear time-invariant ordinary differential equations (LTI ODE) for connection weights, and iii) activation functions evaluated in the frequency domain. It will be shown that this new characterization of the constitutive nodes in an artificial neural network, namely LTI ODE-valued neural network (LTI ODEVNN), allows solving multiple problems at the same time using a single neural structure. Moreover, it is demonstrated that LTI ODEVNNs can be interpreted as complex-valued neural networks (CVNNs). Hence, research on this topic can be applied in a straightforward form. Standard boolean functions are implemented to illustrate the operation of LTI ODEVNNs. Concluding the paper, several future research lines are highlighted, including the need for developing learning algorithms for the newly introduced LTI ODEVNNs.
2014-11-06T13:02:53ZVelasco García, ManelMartín Rull, Enric XavierAngulo Bahón, CecilioMartí Colom, PauA dynamical version of the classical McCulloch & Pitts’ neural model is introduced in this paper. In this new approach, artificial neurons are characterized by: i) inputs in the form of differentiable continuous-time signals, ii) linear time-invariant ordinary differential equations (LTI ODE) for connection weights, and iii) activation functions evaluated in the frequency domain. It will be shown that this new characterization of the constitutive nodes in an artificial neural network, namely LTI ODE-valued neural network (LTI ODEVNN), allows solving multiple problems at the same time using a single neural structure. Moreover, it is demonstrated that LTI ODEVNNs can be interpreted as complex-valued neural networks (CVNNs). Hence, research on this topic can be applied in a straightforward form. Standard boolean functions are implemented to illustrate the operation of LTI ODEVNNs. Concluding the paper, several future research lines are highlighted, including the need for developing learning algorithms for the newly introduced LTI ODEVNNs.De la farola urbana hacia un elemento urbano multifuncional
http://hdl.handle.net/2117/24181
De la farola urbana hacia un elemento urbano multifuncional
Ruiz, Fèlix; Farré, Josep; Martí Colom, Pau; Martínez Antúnez, Nora Isabel; Llorens Garcia, Ariadna
Se està produciendo un cambio de paradigma, un cambio de concepto de la farola tradicional, transformándose en otra cosa diferente, en el nodo urbano. Esto supone un nuevo paso en la línea de las smart cities. Los autores de este artículo nos describen cómo funcionan estas nuevas farolas
2014-09-29T08:06:12ZRuiz, FèlixFarré, JosepMartí Colom, PauMartínez Antúnez, Nora IsabelLlorens Garcia, AriadnaSe està produciendo un cambio de paradigma, un cambio de concepto de la farola tradicional, transformándose en otra cosa diferente, en el nodo urbano. Esto supone un nuevo paso en la línea de las smart cities. Los autores de este artículo nos describen cómo funcionan estas nuevas farolasHolistic indices for productivity control assessment, applied to the comparative analysis of PID and fuzzy controllers within an Isasmelt furnace
http://hdl.handle.net/2117/23378
Holistic indices for productivity control assessment, applied to the comparative analysis of PID and fuzzy controllers within an Isasmelt furnace
Ojeda Sarmiento, Juan Manuel; Fuertes Armengol, José Mª; Griful Ponsati, Eulàlia
This research aims to contribute to the analysis of control performance assessment in extractive metallurgy. Productivity-based indices are proposed in addition to current measuring techniques. Such criteria are employed to compare conventional PID and fuzzy-based controllers in copper smelting. This process is mathematically modeled in order to be simulated. The comparison confirms a better performance of the fuzzy controller in dealing with the molten bath temperature within an Isasmelt furnace. In normal operating conditions (online tests), the proposed controller achieves a consistent mean square relative error reduction of 72% between measured values and the temperature setpoint and standard deviation of approximately 60% (from 27.8 degrees C to 11.1 degrees C). The productivity criteria establish a lower consumption of raw materials (13%) and energy supply (29%).
2014-07-02T09:23:03ZOjeda Sarmiento, Juan ManuelFuertes Armengol, José MªGriful Ponsati, EulàliaThis research aims to contribute to the analysis of control performance assessment in extractive metallurgy. Productivity-based indices are proposed in addition to current measuring techniques. Such criteria are employed to compare conventional PID and fuzzy-based controllers in copper smelting. This process is mathematically modeled in order to be simulated. The comparison confirms a better performance of the fuzzy controller in dealing with the molten bath temperature within an Isasmelt furnace. In normal operating conditions (online tests), the proposed controller achieves a consistent mean square relative error reduction of 72% between measured values and the temperature setpoint and standard deviation of approximately 60% (from 27.8 degrees C to 11.1 degrees C). The productivity criteria establish a lower consumption of raw materials (13%) and energy supply (29%).El Node urbà : Canvi de concepte del fanal cap a element urbà multifuncional en smart cities
http://hdl.handle.net/2117/23284
El Node urbà : Canvi de concepte del fanal cap a element urbà multifuncional en smart cities
Ruiz, Fèlix; Farré, Josep; Martí Colom, Pau; Martínez Antúnez, Nora Isabel; Llorens Garcia, Ariadna
2014-06-20T10:16:27ZRuiz, FèlixFarré, JosepMartí Colom, PauMartínez Antúnez, Nora IsabelLlorens Garcia, AriadnaDesign of an embedded control system laboratory experiment
http://hdl.handle.net/2117/14313
Design of an embedded control system laboratory experiment
Martí Colom, Pau; Velasco García, Manel; Fuertes Armengol, José Mª; Camacho Santiago, Antonio; Buttazzo, Giorgio
This paper presents a prototype laboratory experiment to be integrated in the education of embedded control system engineers. The experiment, a real-time control of a dynamical system, is designed to drive students to a deeper understanding and integration of the diverse theoretical concepts that often come from different disciplines such as real-time systems and control systems. Rather than proposing the experiment for a particular course within an embedded system engineering curriculum, this paper describes how the experiment can be tailored to the needs and diverse background of both undergraduate and graduate students education.
2011-12-22T13:08:12ZMartí Colom, PauVelasco García, ManelFuertes Armengol, José MªCamacho Santiago, AntonioButtazzo, GiorgioThis paper presents a prototype laboratory experiment to be integrated in the education of embedded control system engineers. The experiment, a real-time control of a dynamical system, is designed to drive students to a deeper understanding and integration of the diverse theoretical concepts that often come from different disciplines such as real-time systems and control systems. Rather than proposing the experiment for a particular course within an embedded system engineering curriculum, this paper describes how the experiment can be tailored to the needs and diverse background of both undergraduate and graduate students education.Simulation study of a remote wireless path tracking control with delay estimation for an autonomous guided vehicle
http://hdl.handle.net/2117/10314
Simulation study of a remote wireless path tracking control with delay estimation for an autonomous guided vehicle
Lozoya, Camilo; Martí Colom, Pau; Velasco García, Manel; Fuertes Armengol, José Mª; Martín Rull, Enric Xavier
Industrial applications involving mobile systems can benefit from the use of wireless technology. However, wireless communication has not been widely accepted on the factory floor due to its difficulty in achieving the timely and reliable transmission of messages
over error-prone wireless channels. This paper presents an autonomous guided vehicle (AGV) path tracking wireless control system where an accurate delay estimation scheme is shown to be the key for successful operation. The control architecture consists
on an AGV connected through a wireless network to a controller. To mitigate the negative effects that varying time delays in data transfer have in the networked control
loop, the controller performs two tasks at each loop operation. First, it uses a Kalman filter to produce an optimal delay estimate considering a simple stochastic model of the wireless delay dynamics. Second, each delay estimate is employed to infer the real AGV position which permits to compute the appropriate control commands. Results show that the proposed technique provides more efficient and effective operation for path
tracking control compared to similar previously proposed solutions.
2010-11-16T13:11:05ZLozoya, CamiloMartí Colom, PauVelasco García, ManelFuertes Armengol, José MªMartín Rull, Enric XavierIndustrial applications involving mobile systems can benefit from the use of wireless technology. However, wireless communication has not been widely accepted on the factory floor due to its difficulty in achieving the timely and reliable transmission of messages
over error-prone wireless channels. This paper presents an autonomous guided vehicle (AGV) path tracking wireless control system where an accurate delay estimation scheme is shown to be the key for successful operation. The control architecture consists
on an AGV connected through a wireless network to a controller. To mitigate the negative effects that varying time delays in data transfer have in the networked control
loop, the controller performs two tasks at each loop operation. First, it uses a Kalman filter to produce an optimal delay estimate considering a simple stochastic model of the wireless delay dynamics. Second, each delay estimate is employed to infer the real AGV position which permits to compute the appropriate control commands. Results show that the proposed technique provides more efficient and effective operation for path
tracking control compared to similar previously proposed solutions.Performing flexible control on low cost microcontrollers using a minimal real-time kernel
http://hdl.handle.net/2117/9812
Performing flexible control on low cost microcontrollers using a minimal real-time kernel
Marau, Ricardo; Leite, Paulo; Velasco García, Manel; Martí Colom, Pau; Almeida, Luis; Pedreiras, Paulo; Fuertes Armengol, José Mª
In recent years, approaches to control performance
and resource optimization for embedded control systems have
been receiving increased attention. Most of them focus on theory,
whereas practical aspects are omitted. Theoretical advances
demand flexible real-time kernel support for multitasking and
preemption, thus requiring more sophisticated and expensive software/
hardware solutions. On the other hand, embedded control
systems often have cost constraints related with mass production
and strong industrial competition, thus demanding low-cost solutions.
In this paper, it is shown that these conflicting demands can be
softened and that a compromise solution can be reached. We advocate
that recent research results on optimal resource management
for control tasks can be implemented on simple multitasking
preemptive real-time kernels targeting low-cost microprocessors,
which can be easily built in-house and tailored to actual application
needs. The experimental evaluation shows that significant control
performance improvement can be achieved without increasing
hardware costs.
2010-10-19T11:56:39ZMarau, RicardoLeite, PauloVelasco García, ManelMartí Colom, PauAlmeida, LuisPedreiras, PauloFuertes Armengol, José MªIn recent years, approaches to control performance
and resource optimization for embedded control systems have
been receiving increased attention. Most of them focus on theory,
whereas practical aspects are omitted. Theoretical advances
demand flexible real-time kernel support for multitasking and
preemption, thus requiring more sophisticated and expensive software/
hardware solutions. On the other hand, embedded control
systems often have cost constraints related with mass production
and strong industrial competition, thus demanding low-cost solutions.
In this paper, it is shown that these conflicting demands can be
softened and that a compromise solution can be reached. We advocate
that recent research results on optimal resource management
for control tasks can be implemented on simple multitasking
preemptive real-time kernels targeting low-cost microprocessors,
which can be easily built in-house and tailored to actual application
needs. The experimental evaluation shows that significant control
performance improvement can be achieved without increasing
hardware costs.On the timing of discrete events in event-driven control systems
http://hdl.handle.net/2117/9159
On the timing of discrete events in event-driven control systems
Velasco García, Manel; Martí Colom, Pau; Lozoya, Camilo
This paper presents an analysis method to determine offline at what intervals have to be taken the samples for various types of event-
driven control systems.
2010-09-29T12:26:24ZVelasco García, ManelMartí Colom, PauLozoya, CamiloThis paper presents an analysis method to determine offline at what intervals have to be taken the samples for various types of event-
driven control systems.