<p>U tezi je analizirana opravdanost primene FPGA tehnologije za razvoj upravljačkog sistema za linearne aktuatore. Realizovan je upravljački sistem za servo upravljanje linearnim pneumatskim aktuatorom, čiji rad je eksperimentalno proveren. Razvijeni su i algoritmi za detekciju opterećenosti aktuatora, kao i za detekciju prepreke na nepoznatoj poziciji korišćenjem metode analize promene pritiska u komorama pneumatskog cilindra.</p> / <p>This thesis discusses the possibilities of FPGA technology application in<br />the development of a control system for linear actuators. A control system<br />for servo control of linear pneumatic actuators was realized, and<br />experimentally tested. Furthermore, algorithms were developed for<br />detection of actuator load, as well as for detection of an obstacle in<br />unknown position, by analysing pressure change in the pneumatic<br />cylinder chambers.</p>

The extraction and analysis of human gait characteristics using image sequences are an important area of research. Recently, the focus of this research area has turned to computer vision as an unobtrusive way to analyze human motions. The applications for such a system are wide ranging in many disciplines. For example, it has been shown that visual systems can be used to identify people by their gait, estimate a subject's kinematic configuration and identify abnormal motion. The focus of this thesis is a system that accurately classifies observed motions without the use of an explicit spatial or temporal model. The visual detection of hidden loads through passive visual analysis of gait is presented as a test of the system. The major contributions of this thesis are in two areas. The first is a neural network based scheme that classifies walking styles based on simple image metrics obtained from a single, monocular gray scale image sequence. The powerful neural network classifier utilized in this system provides an efficient, robust and highly accurate classification using these image metrics. This eliminates the need for more complex and difficult to obtain measures that are required by many of the currently human visual analysis systems. This system uses computer vision and pattern recognition techniques combined with physiological knowledge of human gait to estimate an observed subject's hip angle. The hip angle is then used to calculate a normality index of the gait. The hip angle estimate and normality index are then used as inputs to a neural network. It is shown through experiment that this system provides an accurate classification of four different walking styles observed by a single camera. Secondly, a computer vision based approach is presented that provides an accurate pose estimate without the use of an explicit spatial or temporal model. A hybrid fuzzy neural network is used to assign contour points of a silhouette to kinematically relevant groups. These labeled points are used to estimate the joint locations of the subject. The joint angles are shown to be good estimates as compared to ground truth angles provided by a motion capture system. The effectiveness of the system to distinguish between subtle gait differences is demonstrated by detecting the presence of hidden loads when carried by walking people. / Ph. D.

Nesta dissertação apresentaremos um m´método para detecção automática da quantidade de carga adicionada em uma lavadora de roupas para que esta possa adequar o seu nível de água e ciclo de lavagem. A máquina na qual este algoritmo foi desenvolvido é uma máquina de eixo vertical (abertura na parte de cima) e utiliza um motor síncrono trapezoidal (BPM do inglês Brushless Permanent Magnet). O algoritmo que será descrito aqui utiliza uma rede neural para inferir a quantidade de carga baseado em informações disponíveis nesta m´máquina como, corrente do motor, velocidade do cesto e tensão de alimentação, entre outros, essas informações estão disponíveis na maioria dos modelos de máquinas de lavar roupas que utilizam esse tipo de motor. A utilização de um algoritmo para detectar automaticamente e de forma precisa a quantidade de roupas é muito importante, pois dessa forma evita-se o desperdício de insumos e, principalmente, água no processo de lavagem. Além disso apresentaremos os resultados que mostram a diferença entre o uso da rede neural e o método linear chamado planejamento de experimento (DOE do inglês Design of Experiments). / In this dissertation a method for automatic load size detection will be presented, so the water level and the washing cycles can be chosen by a washing machine. The machine where this algorithm was developed is a top load washing machine that uses a brushless permanent magnet motor (BPM motor). The algorithm that is going to be described here uses a neural network to deduce the load size based on information available on this machine such as, motor current, basket speed, power supply voltage and others. These signals are available on most washing machines that uses this kind of motor. The use of an algorithm that detects automatically and precisely the load amount is very important in order to avoid the waste of soap, bleach and softner and, more importantly, water during the wash task. Moreover the use of the neural network will be compared with a linear methods called DOE (design of experiment). Finally, results showing the difference between both methods are presented.

Nesta dissertação apresentaremos um m´método para detecção automática da quantidade de carga adicionada em uma lavadora de roupas para que esta possa adequar o seu nível de água e ciclo de lavagem. A máquina na qual este algoritmo foi desenvolvido é uma máquina de eixo vertical (abertura na parte de cima) e utiliza um motor síncrono trapezoidal (BPM do inglês Brushless Permanent Magnet). O algoritmo que será descrito aqui utiliza uma rede neural para inferir a quantidade de carga baseado em informações disponíveis nesta m´máquina como, corrente do motor, velocidade do cesto e tensão de alimentação, entre outros, essas informações estão disponíveis na maioria dos modelos de máquinas de lavar roupas que utilizam esse tipo de motor. A utilização de um algoritmo para detectar automaticamente e de forma precisa a quantidade de roupas é muito importante, pois dessa forma evita-se o desperdício de insumos e, principalmente, água no processo de lavagem. Além disso apresentaremos os resultados que mostram a diferença entre o uso da rede neural e o método linear chamado planejamento de experimento (DOE do inglês Design of Experiments). / In this dissertation a method for automatic load size detection will be presented, so the water level and the washing cycles can be chosen by a washing machine. The machine where this algorithm was developed is a top load washing machine that uses a brushless permanent magnet motor (BPM motor). The algorithm that is going to be described here uses a neural network to deduce the load size based on information available on this machine such as, motor current, basket speed, power supply voltage and others. These signals are available on most washing machines that uses this kind of motor. The use of an algorithm that detects automatically and precisely the load amount is very important in order to avoid the waste of soap, bleach and softner and, more importantly, water during the wash task. Moreover the use of the neural network will be compared with a linear methods called DOE (design of experiment). Finally, results showing the difference between both methods are presented.

For positioning of linear stages in absolute coordinates, there is a general need to find a reference position since the initial one is unknown. This is commonly called homing. To reduce costs and facilitate assembly, homing can be performed without additional sensors, known as sensorless homing. This thesis delves into sensorless homing, specifically with respect to stepper motors, and develops a graphical application for control of them. The commercial technology StallGuard is applied inconjunction with exploration into how it – and sensorless load detectionin general – functions. The resulting graphical application can be used to configure the stepper motors, perform homing using StallGuard, and automatically tune StallGuard to work despite varying conditions. In addition, rudimentary sensorless load detection independent from StallGuard is developed, demonstrating how it could work in practice. Testing shows homing with StallGuard resulting in a position within a ±5μm window in 94% of cases, less than 1/7 the width of an average strand of human hair. Additionally, homing is easily performed with a single button press from the graphical interface, with optional additional configuration available.