Made available in DSpace on 2015-05-08T14:59:41Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 2002299 bytes, checksum: 8157401052d865ab5779e6f1b23383d8 (MD5) Previous issue date: 2012-04-27 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / This work presents the position control of a robotic manipulator with two degrees of freedom. Such control is accomplished by applying a multilayer neural network, emulating a PD2 controller. The choice of the number of neurons in the hidden layer is made with the aid of a Genetic Algorithm, whose role is to generate populations where individuals will be the number of neurons in the hidden layer and evaluate the performance of the control system when subjected to different references signals. The two best individuals of each generation will give origin to the population of the next iteration, noting the probabilities of crossover and mutation, using the criterion of elitism as a warranty of optimization. The evaluation of the overall performance of the control system, in turn, is based on trajectory following response (sinusoidal reference signals) and on position response (step reference signals). / No presente trabalho trata-se do controle de posicionamento de um manipulador robótico com dois graus de liberdade. Tal controle é realizado por meio da aplicação de uma rede neural multicamadas, emulando um controlador do tipo PD2. A escolha do número de neurônios na camada oculta é feita com auxílio de um Algoritmo Genético, cujo papel é gerar populações em que os indivíduos serão o número de neurônios na camada oculta e avaliar o desempenho do sistema de controle quando submetido a diferentes referências. Os dois melhores indivíduos de cada geração darão origem a população da iteração seguinte, observando as probabilidades de cruzamento e mutação, utilizando assim o critério do elitismo como garantia de otimização. A avaliação do desempenho geral do sistema de controle, por sua vez, é feita com base na resposta ao acompanhamento de trajetória (sinais senoidais) e a resposta de posicionamento (sinais do tipo degrau).

Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-20T01:57:26Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-22T14:06:58Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-22T18:09:13Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-22T18:12:23Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-22T19:44:21Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-23T11:57:14Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-23T12:57:56Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-23T13:16:32Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-23T13:34:44Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-23T17:24:55Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-23T17:29:02Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-24T12:05:24Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-24T12:39:44Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-24T16:47:38Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-24T17:31:22Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-27T11:40:50Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-27T12:31:51Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-27T13:03:15Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Submitted by Jeferson Jose de Lima null (jefersonjl82@gmail.com) on 2017-11-27T18:08:07Z No. of bitstreams: 1 PPGEE_UNESP_JEFERSON.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Approved for entry into archive by Maria Marlene Zaniboni null (zaniboni@bauru.unesp.br) on 2017-11-28T11:31:03Z (GMT) No. of bitstreams: 1 lima_jj_dr_bauru.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) / Made available in DSpace on 2017-11-28T11:31:03Z (GMT). No. of bitstreams: 1 lima_jj_dr_bauru.pdf: 2168304 bytes, checksum: 65aa625d79b7b8de002c02599c5f3983 (MD5) Previous issue date: 2017-09-29 / Manipuladores robóticos leves trazem diversas vantagens quanto ao custo de produção e eficiência na relação carga útil e peso do robô. No entanto a utilização de materiais leves tende a aumentar a flexibilidade estrutural, principalmente na transmissão do torque e nos elos. As propostas de manipuladores apresentadas neste trabalho possuem requisitos conflitantes, pois deseja-se a redução do peso dos mecanismos e aumentar o desempenho, surgem então alguns desafios de engenharia. Desta forma, esta tese trata da modelagem mecânica, análise dinâ- mica e controle híbridos, utilizando atuadores inteligentes, para manipuladores robóticos com características flexíveis. Dois principais modelos de manipuladores robóticos com características flexíveis serão considerados neste trabalho: um para carregamento de carga conectadas a um cabo e outro para manuseio de ferramenta rotativa, ambos com interação não-ideal do elemento manipulado. É possível verificar comportamento caótico ao adicionar a carga aos manipuladores, trazendo assim, maiores desafios a proposta de controle. Na estratégia de controle são considerados como atuadores os motores CC (Corrente Contínua) e atuadores classificados como materiais inteligentes como a Liga de Memória de Forma (LMF), atuando nos elos flexí- veis, e freio Magneto-Reológico (MR-Brake), atuando nas juntas flexíveis. Utilizou-se da rede neural RBFNN para estimativa das variáveis de controle dos atuadores LMF e MR-Brake. O controle DSDRE (Discrete State Dependent Ricatti Equation) é utilizado como a lei de controle. Os resultados numéricos mostram que a adição de atuadores híbridos trazem um ganho considerável no controle de vibração e posicionamento dos manipuladores. / Light-weight robotic manipulators have advantages over the cost of production and efficiency in relation to payload and weight of the robot. However, the use of light-weight materials tends to increase structural flexibility in torque transmission and in the links of the robot. The manipulator proposals presented in this work have conflicting requirements since it is desired to reduce the weight of the mechanisms and increase the performance, it makes some engineering challenges. Thus, this thesis deals with mechanical modeling, dynamic analysis and hybrid control, using intelligent actuators, for robotic manipulators with flexible characteristics. Two models of robotic manipulators with flexible characteristics will be considered in this work: one for payload connected to a cable and another one for rotary tool, both with non-ideal interaction of the manipulated element. It is possible to verify chaotic behavior by adding the load to the manipulators, becoming a great challenger to the proposal control. DC motors and actuators classified as intelligent materials such as the shape memory alloy (SMA), acting on the flexible links, and Magneto-Rheological Brake (MR-Brake), acting on the flexible joints, are used in the strategy control. The neural network RBF was used to estimate the control variables of the SMA and MR-Brake actuators. The DSDRE (Discrete State Dependent Ricatti Equation) control is used as the control law. The numerical results show that the addition of hybrid actuators possibly have a considerable gain in the control of vibration and positioning of the manipulators.