Omar Lengerke

Movement persuit control of an offshore automated platform via a RAM-based neural network

The reproduction of the movements of a ship by automated platforms, without the use of sensors providing exact data related to the numeric variables involved, is a non-trivial matter. The creation of an artificial vision system that can follow the cadence of said ship, in six axes of freedom, is the goal of this research. Considering that a real time response is a requisite in this case, it was decided to adopt a Boolean artificial neural network system that could identify and follow arbitrary interest points that could define, as a group, a model of the movement of an observed vessel. This paper describes the development of a prototype based on the Boolean perceptron model WiSARD (Wilkie, Stonham and Aleksanders Recognition Device), that is being implemented in the C programming language on a desktop computer using a regular webcam as input.

Motion planning on Mobile Robots using Differential Flatness

One solution for the motion planning in a nonholonomic vehicle, described as mobile robot, is made in this paper. Using the boundary conditions, the desired trajectory is parameterized in a polynomial by means of a point to point steering algorithm. The system is drove trough the trajectory, using the Differential Flatness properties, calculating the input values in order to perform the movement. Simulations and results of the study are presented.

Comparison of Defuzzification Methods: Automatic Control of Temperature and Flow inHeat Exchanger

The objective of this work is to analyze the behavior of the traditional control and the fuzzy control, applying them in the flow and temperature control to the load of current of a heat exchanger, as well as the analysis of different methods of defuzzification, utilized just as itself this carrying out the fuzzy control. Acting on the structure of the fuzzy controller some changes of form are carried out such that this tune in to be able to obtain the answer but optimum. In the same way proceeds on the traditional controller, and in this way comparisons on these two types of controls are established. Inside the changes that are carried out on the fuzzy controller this form of defuzzification the information, that is to say the methods are exchanged defuzzification in order then to realize comparisons on the behavior of each one of these.

Automated Guided Vehicles (AGV): Searching a Path in the Flexible Manufacturing Systems

Automated Guided Vehicles (AGV): Searching a Path in the Flexible Manufacturing Systems Manufacturing systems are undergoing a noticeable evolution due to an intense technological progress in industrial robotics. Serial production has evolved into the concept of Flexible Manufacturing Systems (FMS), which encapsulate processes in automatic equipment that are capable of executing different operations, that before be performed in several stages and diverse equipments. Automated Guided Vehicle (AGV) systems have been frequently used as material handling equipment in manufacturing systems since the last two decades. Particularly, AGVs with trailers are, and will continue to be, the backbone of the material transport industry. The use of these systems has taken the attention of experts and researchers. They are numerous studies concerning AGV with trailers systems in literature; few of them deal with the adaptation of these systems into FMS. In this paper, a study of the trajectories and a simulation model of a hypothetical system, which included a FMS environment, were developed. In addition, a potential fields method was explored in order to improve the ability of detecting obstacles in AGVs with trailers moving through stations. Pojazdy Kierowane Automatycznie (AGV): Poszukiwanie Drogi w Elastycznych Systemach Wytwarzania Produkcja seryjna wyewoluowała w kierunku koncepcji Elastycznych Systemów Wytwarzania (FMS), która obejmuje procesy technologiczne wykonywane przy zastosowaniu urządzeń automatyki. Od dwóch dekad do transportu i podawania materiałów w systemach wytwarzania stosuje się często układy Pojazdów Kierowanych Automatycznie (AGV). W szczególności, takie pojazdy z przyczepami są i w dalszym ciągu będą szkieletem systemów do transportu materiałów produkcyjnych. W niniejszym artykule przedstawiono badania nad trajektoriami (trasami przejazdów) i modelem symulacyjnym takiego hipotetycznego systemu, który został opracowany jako część środowiska Elastycznych Systemów Wytwarzania (FMS). Dodatkowo została zbadana potencjalna metoda badań w terenie pozwalająca na poprawę wykrywalności przeszkód utrudniających ruch Pojazdom Kierowanym Automatycznie z przyczepami przejeżdżającymi przez stacje.

Identification and modeling for non-linear dynamic system using neural networks type MLP

In control systems, the model dynamics of linear systems is the principal and most important phase of a project, but when working with dynamic of non-linear systems obtain the model becomes a very complex task can be used techniques of system identification. This article show the use of one technique for identification and modeling of dynamic linear systems and nonlinear systems using dynamics neural networks type multilayer perceptron, obtaining approximate results in the identification of non-linear system.