Controle inteligente aplicado a uma mesa de coordenadas de dois graus de liberdade

This work presents the design and construction of an X-Y table of two degrees of freedom, as well as the development of a fuzzy system for its position and trajectory control. The table is composed of two bases that move perpendicularly to each other in the horizontal plane, and are driven by two DC motors. Base position is detected by position sensors attached to the motor axes. A data acquisition board performs the interface between a laptop and the plant. The fuzzy system algorithm was implemented in LabVIEW® programming environment that processes the sensors signals and determines the control variables values that drive the motors. Experimental results using position reference signals (step type signal) and straight and circular paths reference signals are presented to demonstrate the dynamic behavior of fuzzy system

Modelos de dispositivos de microondas e ópticos através de redes neurais artificiais de alimentação direta

This dissertation contributes for the development of methodologies through feed forward artificial neural networks for microwave and optical devices modeling. A bibliographical revision on the applications of neuro-computational techniques in the areas of microwave/optical engineering was carried through. Characteristics of networks MLP, RBF and SFNN, as well as the strategies of supervised learning had been presented. Adjustment expressions of the networks free parameters above cited had been deduced from the gradient method. Conventional method EM-ANN was applied in the modeling of microwave passive devices and optical amplifiers. For this, they had been proposals modular configurations based in networks SFNN and RBF/MLP objectifying a bigger capacity of models generalization. As for the training of the used networks, the Rprop algorithm was applied. All the algorithms used in the attainment of the models of this dissertation had been implemented in Matlab

Metodologia para re-sintonia de controladores PID industriais

The present work has as objective to present a method of project and implementation of controllers PID, based on industrial instrumentation. An automatic system of auto-tunning of controllers PID will be presented, for systems of first and second order. The software presented in this work is applied in controlled plants by PID controllers implemented in a CLP. Software is applied to make the auto-tunning of the parameters of controller PID of plants that need this tunning. Software presents two stages, the first one is the stage of identification of the system using the least square recursive algorithm and the second is the stage of project of the parameters of controller PID using the root locus algorithm. An important fact of this work is the use of industrial instrumentation for the accomplishment of the experiments. The experiments had been carried through in controlled real plants for controllers PID implemented in the CLP. Thus has not only one resulted obtained with theoreticians experiments made with computational programs, and yes resulted obtained of real systems. The experiments had shown good results gotten with developed software

Estudo e implementação em plantas físicas de um controlador preditivo generalizado com restrições

This work shows a study about the Generalized Predictive Controllers with Restrictions and their implementation in physical plants. Three types of restrictions will be discussed: restrictions in the variation rate of the signal control, restrictions in the amplitude of the signal control and restrictions in the amplitude of the Out signal (plant response). At the predictive control, the control law is obtained by the minimization of an objective function. To consider the restrictions, this minimization of the objective function is done by the use of a method to solve optimizing problems with restrictions. The chosen method was the Rosen Algorithm (based on the Gradient-projection). The physical plants in this study are two didactical systems of water level control. The first order one (a simple tank) and another of second order, which is formed by two tanks connected in cascade. The codes are implemented in C++ language and the communication with the system to be done through using a data acquisition panel offered by the system producer

Uma contribuição à solução do problema dos k-servos usando aprendizagem por reforço

Neste trabalho é proposto um novo algoritmo online para o resolver o Problema dos k-Servos (PKS). O desempenho desta solução é comparado com o de outros algoritmos existentes na literatura, a saber, os algoritmos Harmonic e Work Function, que mostraram ser competitivos, tornando-os parâmetros de comparação significativos. Um algoritmo que apresente desempenho eficiente em relação aos mesmos tende a ser competitivo também, devendo, obviamente, se provar o referido fato. Tal prova, entretanto, foge aos objetivos do presente trabalho. O algoritmo apresentado para a solução do PKS é baseado em técnicas de aprendizagem por reforço. Para tanto, o problema foi modelado como um processo de decisão em múltiplas etapas, ao qual é aplicado o algoritmo Q-Learning, um dos métodos de solução mais populares para o estabelecimento de políticas ótimas neste tipo de problema de decisão. Entretanto, deve-se observar que a dimensão da estrutura de armazenamento utilizada pela aprendizagem por reforço para se obter a política ótima cresce em função do número de estados e de ações, que por sua vez é proporcional ao número n de nós e k de servos. Ao se analisar esse crescimento (matematicamente, ) percebe-se que o mesmo ocorre de maneira exponencial, limitando a aplicação do método a problemas de menor porte, onde o número de nós e de servos é reduzido. Este problema, denominado maldição da dimensionalidade, foi introduzido por Belmann e implica na impossibilidade de execução de um algoritmo para certas instâncias de um problema pelo esgotamento de recursos computacionais para obtenção de sua saída. De modo a evitar que a solução proposta, baseada exclusivamente na aprendizagem por reforço, seja restrita a aplicações de menor porte, propõe-se uma solução alternativa para problemas mais realistas, que envolvam um número maior de nós e de servos. Esta solução alternativa é hierarquizada e utiliza dois métodos de solução do PKS: a aprendizagem por reforço, aplicada a um número reduzido de nós obtidos a partir de um processo de agregação, e um método guloso, aplicado aos subconjuntos de nós resultantes do processo de agregação, onde o critério de escolha do agendamento dos servos é baseado na menor distância ao local de demanda

Desenvolvimento de esquema de controle com realimentação visual para um robô manipulador

This work proposes a kinematic control scheme, using visual feedback for a robot arm with five degrees of freedom. Using computational vision techniques, a method was developed to determine the cartesian 3d position and orientation of the robot arm (pose) using a robot image obtained through a camera. A colored triangular label is disposed on the robot manipulator tool and efficient heuristic rules are used to obtain the vertexes of that label in the image. The tool pose is obtained from those vertexes through numerical methods. A color calibration scheme based in the K-means algorithm was implemented to guarantee the robustness of the vision system in the presence of light variations. The extrinsic camera parameters are computed from the image of four coplanar points whose cartesian 3d coordinates, related to a fixed frame, are known. Two distinct poses of the tool, initial and final, obtained from image, are interpolated to generate a desired trajectory in cartesian space. The error signal in the proposed control scheme consists in the difference between the desired tool pose and the actual tool pose. Gains are applied at the error signal and the signal resulting is mapped in joint incrementals using the pseudoinverse of the manipulator jacobian matrix. These incrementals are applied to the manipulator joints moving the tool to the desired pose

Algoritmos genéricos para otimização de uma arquitetura de controle inteligente híerárquico

A hierarchical fuzzy control scheme is applied to improve vibration suppression by using an electro-mechanical system based on the lever principle. The hierarchical intelligent controller consists of a hierarchical fuzzy supervisor, one fuzzy controller and one robust controller. The supervisor combines controllers output signal to generate the control signal that will be applied on the plant. The objective is to improve the performance of the electromechanical system, considering that the supervisor could take advantage of the different techniques based controllers. The robust controller design is based on a linear mathematical model. Genetic algorithms are used on the fuzzy controller and the supervisor tuning, which are based on non-linear mathematical model. In order to attest the efficiency of the hierarchical fuzzy control scheme, digital simulations were employed. Some comparisons involving the optimized hierarchical controller and the non-optimized hierarchical controller will be made to prove the efficiency of the genetic algorithms and the advantages of its use

Controle de Manipulador Redundante Utilizando Realimentação Visual

In conventional robot manipulator control, the desired path is specified in cartesian space and converted to joint space through inverse kinematics mapping. The joint references generated by this mapping are utilized for dynamic control in joint space. Thus, the end-effector position is, in fact, controlled indirectly, in open-loop, and the accuracy of grip position control directly depends on the accuracy of the available kinematic model. In this report, a new scheme for redundant manipulator kinematic control, based on visual servoing is proposed. In the proposed system, a robot image acquired through a CCD camera is processed in order to compute the position and orientation of each link of the robot arm. The robot task is specified as a temporal sequence of reference images of the robot arm. Thus, both the measured pose and the reference pose are specified in the same image space, and its difference is utilized to generate a cartesian space error for kinematic control purposes. The proposed control scheme was applied in a four degree-of-freedom planar redundant robot arm, experimental results are shown

Estratégias baseadas em aprendizado para coordenação de uma frota de robôs em tarefas cooperativas

In multi-robot systems, both control architecture and work strategy represent a challenge for researchers. It is important to have a robust architecture that can be easily adapted to requirement changes. It is also important that work strategy allows robots to complete tasks efficiently, considering that robots interact directly in environments with humans. In this context, this work explores two approaches for robot soccer team coordination for cooperative tasks development. Both approaches are based on a combination of imitation learning and reinforcement learning. Thus, in the first approach was developed a control architecture, a fuzzy inference engine for recognizing situations in robot soccer games, a software for narration of robot soccer games based on the inference engine and the implementation of learning by imitation from observation and analysis of others robotic teams. Moreover, state abstraction was efficiently implemented in reinforcement learning applied to the robot soccer standard problem. Finally, reinforcement learning was implemented in a form where actions are explored only in some states (for example, states where an specialist robot system used them) differently to the traditional form, where actions have to be tested in all states. In the second approach reinforcement learning was implemented with function approximation, for which an algorithm called RBF-Sarsa($lambda$) was created. In both approaches batch reinforcement learning algorithms were implemented and imitation learning was used as a seed for reinforcement learning. Moreover, learning from robotic teams controlled by humans was explored. The proposal in this work had revealed efficient in the robot soccer standard problem and, when implemented in other robotics systems, they will allow that these robotics systems can efficiently and effectively develop assigned tasks. These approaches will give high adaptation capabilities to requirements and environment changes.

Classificação de padrões através de um comitê de máquinas aprimorado por aprendizagem por reforço

Reinforcement learning is a machine learning technique that, although finding a large number of applications, maybe is yet to reach its full potential. One of the inadequately tested possibilities is the use of reinforcement learning in combination with other methods for the solution of pattern classification problems. It is well documented in the literature the problems that support vector machine ensembles face in terms of generalization capacity. Algorithms such as Adaboost do not deal appropriately with the imbalances that arise in those situations. Several alternatives have been proposed, with varying degrees of success. This dissertation presents a new approach to building committees of support vector machines. The presented algorithm combines Adaboost algorithm with a layer of reinforcement learning to adjust committee parameters in order to avoid that imbalances on the committee components affect the generalization performance of the final hypothesis. Comparisons were made with ensembles using and not using the reinforcement learning layer, testing benchmark data sets widely known in area of pattern classification

Roteamento em Redes de Sensores Sem Fios Com Base Em Aprendizagem Por Reforço

The use of wireless sensor and actuator networks in industry has been increasing past few years, bringing multiple benefits compared to wired systems, like network flexibility and manageability. Such networks consists of a possibly large number of small and autonomous sensor and actuator devices with wireless communication capabilities. The data collected by sensors are sent directly or through intermediary nodes along the network to a base station called sink node. The data routing in this environment is an essential matter since it is strictly bounded to the energy efficiency, thus the network lifetime. This work investigates the application of a routing technique based on Reinforcement Learning s Q-Learning algorithm to a wireless sensor network by using an NS-2 simulated environment. Several metrics like energy consumption, data packet delivery rates and delays are used to validate de proposal comparing it with another solutions existing in the literature

Estudo de Superfícies Seletivas de Frequência com o Uso de Inteligência Computacional

The main objective of this work is to optimize the performance of frequency selective surfaces (FSS) composed of crossed dipole conducting patches. The optimization process is performed by determining proper values for the width of the crossed dipoles and for the FSS array periodicity, while the length of the crossed dipoles is kept constant. Particularly, the objective is to determine values that provide wide bandwidth using a search algorithm with representation in bioinspired real numbers. Typically FSS structures composed of patch elements are used for band rejection filtering applications. The FSS structures primarily act like filters depending on the type of element chosen. The region of the electromagnetic spectrum chosen for this study is the one that goes from 7 GHz to 12 GHz, which includes mostly the X-band. This frequency band was chosen to allow the use of two X-band horn antennas, in the FSS measurement setup. The design of the FSS using the developed genetic algorithm allowed increasing the structure bandwidth

Análise de escalabilidade de uma implementação paralela do simulated annealing acoplado

This paper analyzes the performance of a parallel implementation of Coupled Simulated Annealing (CSA) for the unconstrained optimization of continuous variables problems. Parallel processing is an efficient form of information processing with emphasis on exploration of simultaneous events in the execution of software. It arises primarily due to high computational performance demands, and the difficulty in increasing the speed of a single processing core. Despite multicore processors being easily found nowadays, several algorithms are not yet suitable for running on parallel architectures. The algorithm is characterized by a group of Simulated Annealing (SA) optimizers working together on refining the solution. Each SA optimizer runs on a single thread executed by different processors. In the analysis of parallel performance and scalability, these metrics were investigated: the execution time; the speedup of the algorithm with respect to increasing the number of processors; and the efficient use of processing elements with respect to the increasing size of the treated problem. Furthermore, the quality of the final solution was verified. For the study, this paper proposes a parallel version of CSA and its equivalent serial version. Both algorithms were analysed on 14 benchmark functions. For each of these functions, the CSA is evaluated using 2-24 optimizers. The results obtained are shown and discussed observing the analysis of the metrics. The conclusions of the paper characterize the CSA as a good parallel algorithm, both in the quality of the solutions and the parallel scalability and parallel efficiency

Algoritmos genéticos aplicados a um comitê de LS-SVM em problemas de classificação

The pattern classification is one of the machine learning subareas that has the most outstanding. Among the various approaches to solve pattern classification problems, the Support Vector Machines (SVM) receive great emphasis, due to its ease of use and good generalization performance. The Least Squares formulation of SVM (LS-SVM) finds the solution by solving a set of linear equations instead of quadratic programming implemented in SVM. The LS-SVMs provide some free parameters that have to be correctly chosen to achieve satisfactory results in a given task. Despite the LS-SVMs having high performance, lots of tools have been developed to improve them, mainly the development of new classifying methods and the employment of ensembles, in other words, a combination of several classifiers. In this work, our proposal is to use an ensemble and a Genetic Algorithm (GA), search algorithm based on the evolution of species, to enhance the LSSVM classification. In the construction of this ensemble, we use a random selection of attributes of the original problem, which it splits the original problem into smaller ones where each classifier will act. So, we apply a genetic algorithm to find effective values of the LS-SVM parameters and also to find a weight vector, measuring the importance of each machine in the final classification. Finally, the final classification is obtained by a linear combination of the decision values of the LS-SVMs with the weight vector. We used several classification problems, taken as benchmarks to evaluate the performance of the algorithm and compared the results with other classifiers

Estimação de Fasores para Proteção de Sistemas Elétricos Baseada em Mínimos Quadrados e Morfologia Matemática

This work proposes a new technique for phasor estimation applied in microprocessor numerical relays for distance protection of transmission lines, based on the recursive least squares method and called least squares modified random walking. The phasor estimation methods have compromised their performance, mainly due to the DC exponential decaying component present in fault currents. In order to reduce the influence of the DC component, a Morphological Filter (FM) was added to the method of least squares and previously applied to the process of phasor estimation. The presented method is implemented in MATLABr and its performance is compared to one-cycle Fourier technique and conventional phasor estimation, which was also based on least squares algorithm. The methods based on least squares technique used for comparison with the proposed method were: forgetting factor recursive, covariance resetting and random walking. The techniques performance analysis were carried out by means of signals synthetic and signals provided of simulations on the Alternative Transient Program (ATP). When compared to other phasor estimation methods, the proposed method showed satisfactory results, when it comes to the estimation speed, the steady state oscillation and the overshoot. Then, the presented method performance was analyzed by means of variations in the fault parameters (resistance, distance, angle of incidence and type of fault). Through this study, the results did not showed significant variations in method performance. Besides, the apparent impedance trajectory and estimated distance of the fault were analysed, and the presented method showed better results in comparison to one-cycle Fourier algorithm