Search

The generation of electric energy by photovoltaic (PV) panels depends on many parameters, one of them is the sun’s angle of incidence. By using solar active trackers, it is possible to maximize generation capacity through real-time positioning. However, if the engines that update the position of the panels use more energy than the difference in efficiency, the solar tracker system becomes ineffective. In this way, a time series forecasting method can be assumed to determine the generation capacity in a pre-established horizon prediction to evaluate if a position update would provide efficient results. Among a wide range of algorithms that can be used in forecasting, this work considered a Neuro-Fuzzy Inference System due to its combined advantages such as smoothness property from Fuzzy systems and adaptability property from neural networks structures. Focusing on time series forecasting, this article presents a model and evaluates the solar prediction capacity using the Wavelet Neuro-Fuzzy algorithm, where Wavelets were included in the model for feature extraction. In this sense, this paper aims to evaluate whether it is possible to obtain reasonable accuracy using a hybrid model for electric power generation forecasting considering solar trackers. The main contributions of this work are related to the efficiency improvement of PV panels. By assuming a hybrid computational model, it is possible to make a forecast and determine if the use of solar tracking is interesting during certain periods. Finally, the proposed model showed promising results when compared to traditional Nonlinear autoregressive model structures.

Identifying defects in electrical power systems during field inspections is a difficult task, since faults are generally not visible and may be intermittent. To find possible adverse conditions, specific inspection equipment is used. The ultrasound detector is the equipment normally used to inspect outdoor insulating systems; however, using it demands operator experience. To improve the defect condition classification, artificial intelligence techniques are applied to assist the operator in the decision task and thereby facilitate the identification of faulty insulating devices in the grid. The training of artificial neural network (ANN) models is an important step in solving the classification problem. This study aims to evaluate the training capacity in terms of the performance of different optimisation methods for the calculation of the mean square error after convergence. Traditional methods such as Gradient Descent and its variations will be presented, as well as methods that employ high computational effort such as quasi-Newton and Levenberg–Marquardt. In order to base these concepts, a review will be presented on the use of these algorithms and on the problem of classification of insulators in distribution networks. The results show that there is a considerable performance difference between the calculation methods.

In this chapter, the problem of trajectory tracking control of DWMRs based only on their kinematic model, described in rectangular coordinates, is investigated taking into account uncertainties and disturbances during its movement, so that the statement of perfect velocity tracking is not maintained in practice. Thus, in front of such scenario, controller variants based on sliding mode control theory (SMC) are used to provide robustness.

To verify the performance of the controllers treated in this book, they are implemented and evaluated for the trajectory tracking control problem in simulation and in real experiments. This chapter describes the simulation and experimental environments, dealing with the implementation design considering data and information from the PowerBot DWMR, the trajectory adopted, as well as the ideal, realistic, and experimental scenarios.

In this chapter, a first-order quasi-sliding mode control (FOQSMC) are developed intending to mitigate the chattering phenomenon. The stability analysis of this controller, using Lyapunov theory, is presented as well as the effectiveness of the controller variants is verified through simulations and experiments.

In this chapter, the theoretical foundation on control problems and systems are reviewed. The concepts of trajectory tracking problem, PD dynamic control, posture error dynamics, robustness considerations, and generic model for nonlinear systems are introduced. All these concepts are used throughout the book.

In this chapter, to attenuate the chattering phenomenon, the discontinuous term of the controllers in Chap. 5 is replaced by single-input single-output (SISO) radial basis function neural networks (RBFNNs), which are non-linear and continuous functions, thus resulting in adaptive neural sliding mode control (ANSMC). And, to relax the demands of knowing the bounds of the uncertainties and disturbances suffered by the system, the output layer weights of the RBFNNs are updated online to compensate for these uncertainties and disturbances as well as to guarantee the stability of the system without any prior knowledge of them and its bounds.

In this chapter, the kinematic and dynamic DWMR models used in the course of the book are presented for ease of understanding. This models take into account mobility constraints and only conventional fixed wheels. These models of the DWMR are used as the basis for the synthesis of the controllers and the simulations.

This chapter aims to describe leader-follower formation controllers based on SMC applied to DWMRs that are robust to the incidence of uncertainties and disturbances in solving the trajectory tracking control problem. To ensure this, the FOSMC-B discussed in Chap. 5 is used, however, this controller causes the chattering phenomenon, and to mitigate it the FOQSMC-B and AFSMC-A treated in Chaps. 6 and 7 respectively are also used. Moreover, stability analyzes of the closed-loop control system are guaranteed based on the Lyapunov theory, and simulation results in the ideal and realistic scenarios are explored to confirm the effectiveness of used leader-follower formation control strategies.

In this paper, we analyze the performance of two bio-inspired algorithms applied in text-independent speaker recognition through voice signal. The analyzed algorithms are particle swarm optimization and grey wolf optimization. The complete methodology described in this paper was specifically developed in the context of this work. First, a widely known model of the speaker is determined based on discrete transfer functions. Then a method of estimation of the input signal is determined. The bio-inspired algorithms are custom-developed and applied to parameterize the transfer functions based on the models. The proposed method is composed by three major parts, first the fitness used in the bio-inspired algorithms is created based on the cross-correlation. Second, a method to create a database with speakers’ identities is proposed, and third, a method to compare the characteristics of the speaker is proposed, to identify or distinguish two different speakers. Finally, experiments were made considering 4 speakers with 2 speech each, a representation of the identity of each speaker was created through both algorithms, totalizing 16 entries on the database. The experiment had a total of 240 runs, comparing the entries to each other. Results show that all comparison results were accurate. The algorithms identify the speaker even when two different speeches were compared, and, as expected, distinguish when two different speakers were compared.

In this paper an adaptive fuzzy variable structure control (kinematic control) integrated with a proportional plus derivative control (dynamic control) is proposed as a robust solution to the trajectory tracking control problem for a differential wheeled mobile robot. The variable structure controller, based on the sliding mode theory, is a well known, proven control method, fit to deal with uncertainties and disturbances (e.g., structural and parameter uncertainties, external disturbances and operating limitations). To minimize the problems found in practical implementations of the classical variable structure controllers, an adaptive fuzzy logic controller replaces the discontinuous portion of the control signals (avoiding the chattering), causing the loss of invariance, but still ensuring the robustness to uncertainties and disturbances without having any a priori knowledge of their boundaries. Moreover, the adaptive fuzzy logic controller is a feasible tool to approximate any real continuous nonlinear system to arbitrary accuracy, and has a simple structure by using triangular membership functions, a low number of rules that must be evaluated, resulting in a lower computational load for execution, making it feasible for real time implementation. Stability analysis and the convergence of tracking errors as well as the adaptation laws are guaranteed with basis on the Lyapunov theory. Simulation and experimental results are explored to show the verification and validation of the proposed control strategy.

espanolEste articulo presenta el desarrollo de un robot modular multiproposito y su adaptacion para ser usado en tareas de limpieza de playas. El robot presenta un diseno robusto, orientado a soportar las inclemencias de varios tipos de ambientes. Con la configuracion presentada, el robot es capaz de recolectar autonomamente latas dispersas por el ambiente, utilizando una garra similar a la de una excavadora. Ademas de detallar el proyecto y el desarrollo del sistema, tambien es presentado una descripcion de los modulos electronicos desarrollados, el control de velocidad en malla cerrada utilizado y los algoritmos de flujo optico, que mediante el uso de vision artificial permite evitar obstaculos y rastrear las latas que van a ser recolectadas. EnglishThis paper presents the development of a modular mobile robot platform for multiple purposes and its adaptation into a beach cleaner setup. The robot has a robust construction allowing it to endure several sorts of environments. In the presented configuration, the developed robot is able to autonomously collect cans using an excavator-like claw. In addition to detailing the system's design and construction, this paper presents the description of the developed embedded electronics modules, a motor closed-loop speed control system and the optical flow algorithms that allows the computer vision system to detect and avoid obstacles and track the cans to be collected.

In this paper, a trajectory tracking control for a nonholonomic mobile robot subjected to kinematic disturbances is proposed. A variable structure controller based on the sliding mode theory is used, and applied to compensate these disturbances. To minimize the problems found in practical implementations of the classical variable structure controllers, and eliminate the chattering phenomenon a neural compensator is used, which is nonlinear and continuous, in lieu of the discontinuous portion of the control signals present in classical forms. The proposed neural compensator is designed by the Gaussian radial basis function neural networks modeling technique and does not require the time-consuming training process. Stability analysis is guaranteed based on the Lyapunov method. Simulation results are provided to show the effectiveness of the proposed approach.

In this paper, a trajectory tracking control for a nonholonomic mobile robot by the integration of a kinematic controller and a torque controller is investigated. The proposed torque controllers (PTCs) are based on a Gaussian radial basis function neural network (RBFNN) modeling technique, which are used to compensate the mobile robot dynamics, significant uncertainties and disturbances. Also, the PTCs are not dependent of the robot dynamics neither requires the off-line training process. The stability analysis and the convergence of tracking errors to zero, as well as the learning algorithms (for weights, centers, and widths) are guaranteed with basis on Lyapunov's theory. In addition, the simulation results shows the efficiency of the PTCs.

This paper presents an image-based camera control, mounted on a nonholonomic mobile robot platform, traking a mobile target as reference, via task function approach. The system stability is guaranteed by the Lyapunov theory. Due to parametric uncertainties (target depth), actuator (acceleration and velocity) and visual constraints, the gain is generated via LMIs (Linear Matrix Inequalities), in order to maximize the stability region associated with the closed loop. A convex optimization package was used to obtain the feedback gain, and simulations are presented to visualize the system behavior.

In this paper, a trajectory tracking control problem for a nonholonomic mobile robot by the integration of a kinematic neural controller (KNC) and a torque neural controller (TNC) is proposed, where both the kinematic and dynamic models contains disturbances. The KNC is a variable structure controller (VSC) based on the sliding mode control theory (SMC), and applied to compensate the kinematic disturbances. The TNC is a inertia-based controller constituted of a dynamic neural controller (DNC) and a robust neural compensator (RNC), and applied to compensate the mobile robot dynamics, and bounded unknown disturbances. Stability analysis with basis on Lyapunov method and simulations results are provided to show the effectiveness of the proposed approach.

In this paper, a trajectory tracking control for a nonholonomic mobile robot by the integration of a neural kinematic controller (NKC) and neural dynamic controller (NDC) is investigated, where the wheel actuator (e.g., dc motor) dynamics is integrated with mobile robot dynamics and kinematics so that the actuator input voltages are the control inputs, as well as both the kinematic and dynamic models contains parametric and/or nonparametric uncertainties. The proposed neural controller (PNC) is constituted of the NKC and the NDC, and were designed by use of a modelling technique of Gaussian radial basis function neural networks (RBFNNs). The NKC is applied to compensate the uncertainties in the kinematic parameters of the mobile robot. The NDC, based on the sliding mode theory, is applied to compensate the mobile robot dynamics, and parametric and/or nonparametric uncertainties. Also, the PNC are not dependent of the mobile robot kinematics and dynamics neither require the off-line training process. Stability analysis with basis on Lyapunov theory and numerical simulation is provided to show the effectiveness of the PNC.

In this paper, a trajectory tracking control for a nonholonomic mobile robot by the integration of a kinematic controller and neural dynamic controller is investigated, where the wheel actuator dynamics is integrated with mobile robot dynamics and kinematics so that the actuator input voltages are the control inputs. The proposed neural dynamic controller (PNDC), based on the sliding mode theory, is constituted by a neural voltage controller (NVC) and a neural robust compensator (NRC), which has as objective compensates the uncertainties and disturbances in the dynamics. Stability analysis and numerical simulation are provided to show the effectiveness of the PNDC.

In this paper, a trajectory tracking control for a nonholonomic mobile robot by the integration of a kinematic neural controller (KNC) and a torque neural controller (TNC) is proposed, where both the kinematic and dynamic models contains parametric and nonparametrics uncertainties. The proposed neural controller (PNC) is constituted of the KNC and the TNC, and were designed by use of a modeling technique of Gaussian radial basis function neural networks (RBFNNs). The KNC is applied to compensate the uncertainties of the mobile robot. The TNC, based on the computed torque control, is applied to compensate the mobile robot dynamics, significant uncertainties, bounded unknown disturbances, neural networks modeling errors, influence of payload, and unknown kinematic parameters. Also, the PNC are not dependent of the mobile robot kinematics and dynamics neither require the off-line training process. Stability analysis and convergence of tracking errors to zero, as well as the learning algorithms for weights, centers, and variances (becoming nonlinearly parameterized RBFNNs) are guaranteed with basis on Lyapunov theory. In addition, the simulations results are provided to show the efficiency of the PNC.

In this paper, a trajectory tracking control for a nonholonomic mobile robot by the integration of a kinematic controller and a neural torque controller is proposed. The suggested neural torque controller (SNTC), based on the sliding mode theory, is constituted by a dynamic neural controller (DNC) and a robust neural compensator (RNC). The SNTC is designed by use of a modeling technique of Gaussian radial basis function neural networks (RBFNNs), and applied to compensate the mobile robot dynamics, bounded unknown disturbances, neural network modeling errors, and influence of payload. To alleviate the problems met in practical implementation using classical sliding mode controllers and to eliminate the chattering phenomenon is used the RNC of the SNTC, which is nonlinear and continuous, in lieu of the discontinuous part of the control signals present in classical forms. Also, the SNTC neither requires the knowledge of the mobile robot dynamics nor the time-consuming training process. Stability and convergence analysis of tracking errors, as well as the learning algorithms (for weights, centers, and widths) are guaranteed based on the Lyapunov method. Numerical simulations are provided to show the effectiveness of the suggested approach.

In this paper, a trajectory tracking control for a nonholonomic mobile robot by the integration of a kinematic neural controller (KNC) and a torque neural controller (TNC) is proposed, where both the kinematic and dynamic models contains parametric and nonparametric uncertainties. The proposed neural controller (PNC) is constituted of the KNC and the TNC, and designed by use of a modeling technique of Gaussian radial basis function neural networks (RBFNNs). The KNC is applied to compensate the parametric uncertainties of the mobile robot kinematics. The TNC, based on the sliding mode theory, is constituted of a dynamic neural controller (DNC) and a robust neural compensator (RNC), and applied to compensate the mobile robot dynamics, significant uncertainties, bounded unknown disturbances, neural network modeling errors, influence of payload, and unknown kinematic parameters. To alleviate the problems met in practical implementation using classical sliding mode controllers and to eliminate the chattering phenomenon is used the RNC of the TNC, which is nonlinear and continuous, in lieu of the discontinuous part of the control signals present in classical forms. Also, the PNC neither requires the knowledge of the mobile robot kinematics and dynamics nor the time-consuming training process. Stability analysis and convergence of tracking errors to zero as well as the learning algorithms for weights are guaranteed with basis on Lyapunov method. Simulations results are provided to show the effectiveness of the proposed approach.

In this paper, a trajectory tracking control for a nonholonomic mobile robot by the integration of a kinematic controller and neural dynamic controller is investigated, where the wheel actuator (e.g., dc motor) dynamics is integrated with mobile robot dynamics and kinematics so that the actuator input voltages are the control inputs. The proposed neural dynamic controller (PNDC), based on the sliding mode theory, is applied to compensate the mobile robot dynamics, bounded unknown disturbances, and influence of payload. This controller is obtained by modeling the Radial Basis Functions Neural Networks (RBFNNs) of the centripetal and Coriolis matrix through of the inertia matrix of the mobile robot dynamics. Thus, PNDC is constituted of static RBFNNs only, what makes possible the reduction of the size of the RBFNNs, of the computational load and the implementation in real time. Stability analysis and numerical simulations are provided to show the effectiveness of the PNDC.

There is a growing demand for automatic control systems for unmanned aircraft due to the large number of civilian and military applications. An autopilot system in an aircraft seeks to improve the steering and pilotage mechanisms of an airplane, and is composed of complex and sophisticated controllers. This work contributes to the advancement in the development of these systems, and its general objective is to design an autopilot with advanced controllers for the Cessna 172/182 airplane. The classical control technique, which uses PID controllers, is the most used because it is efficient and easily developed, but it has limitations. Variations not foreseen in the aircraft and disturbances during the flight may not be compensated by the control system. Therefore the use of advanced control techniques is justified to improve the efficiency and reliability of the system. In this work we also propose procedures to optimize the gains of PID controllers designed from simulated transfer functions in the Matlab/Simulink software, establishing a model-in-the-loop system, and then with the integration of Matlab/Simulink and the X-Plane flight simulator, forming a software-in-the-loop system. The implementation of the designed controllers was done on an Arduino board, which was coupled to the flight simulator, constituting a hardware-in-the-loop system. In this context, results of simulations are acquired allowing to verify the effectiveness of the use of the optimization proposals made in this work. Several advanced controller options, as alternatives to the PID controller, were used, which allowed the proposed ISA-PID-EG-Fuzzy controller to be proposed. The results obtained in this work indicate that the proposed controller obtained better results in most of the comparisons made and that there are still other possibilities that should be considered in future implementations Há uma crescente demanda por sistemas de controle automático para veículos aéreos não tripulados devido ao grande número de aplicações civis e militares. Um sistema de piloto automático em uma aeronave busca melhorar os mecanismos de direção e pilotagem de um avião, e é composto por controladores complexos e sofisticados. Este trabalho contribui com o avanço no desenvolvimento desses sistemas, e têm como objetivo geral projetar um piloto automático com controladores avançados para o avião Cessna 172/182. A técnica de controle clássica, que usa controladores PID, é a mais utilizada por ser eficiente e facilmente desenvolvida, porém possui limitações. Variações não previstas na aeronave e perturbações durante o voo podem não ser compensadas pelo sistema de controle. Por isso o uso de técnicas de controle avançado se justifica para melhorar a eficiência e a confiabilidade do sistema. Neste trabalho também são propostos procedimentos de otimização dos ganhos dos controladores PID projetados a partir de funções de transferência simuladas no software Matlab/Simulink, estabelecendo um sistema model-in-the-loop, e então com a integração do software Matlab/Simulink e o simulador de voo X-Plane, formando um sistema software-in-the-loop. A implementação dos controladores projetados foi feita em uma placa Arduino, que foi acoplada ao simulador de voo, constituindo um sistema hardware-in-the-loop. Neste contexto, resultados de simulações são adquiridos para permitir verificar a efetividade do uso das propostas de otimização feitas neste trabalho. Várias opções de controladores avançados como alternativas ao controlador PID foram usadas, o que permitiu propor o controlador ISA-PID-EG-Fuzzy. Os resultados obtidos neste trabalho apontam que o controlador proposto obteve melhores resultados na maioria das comparações feitas e que ainda existem outras possibilidades que devem ser consideradas em futuras implementações 162 f.