No abstract

Modo de acesso: World Wide Web Inclui bibliografia 1. Gestão da Produção 2. Engenharia de Produção. I. Título CDD-658 O conteúdo dos artigos e seus dados em sua forma, correção e confiabilidade são de responsabilidade exclusiva dos seus respectivos autores.

No abstract

The present work focuses on the development of a pneumatic gecko robot capable of moving on surfaces with different inclinations, using linear actuators. The main applications are inspections, cleaning and repairs to buildings, ship hulls and large solar panel structures. The work relies on the design of vacuum claws using mechanical and pneumatic concepts to escape the high expense of compressed air provided by the common vacuum components on the market. In addition, the present work applies the neural network algorithm called backpropagation with tests on the prototype to obtain a computational learning of the robot's operation, after observing the behavior of the actuators through simulations with a kinematic model.

-The main goal of this paper is to propose procedures for modelling and control of nonlinear systems by using neuro-fuzzy topologies. For the modelling of a nonlinear system, its input space is initially divided into a number of fuzzy operating regions, within which reduced order models represent the system's behaviour. The complete system modelling -the global model -is obtained through the conjunction of the local models by using a neuro-fuzzy network. A neuro-fuzzy adaptive network, based on a hybrid learning algorithm (self-organised learning and supervised learning) and called FALCON-H, is used in the control of a nonlinear plant modelled as described above.