Neste trabalho estuda-se a aplicação de métodos estatísticos multivariáveis para a classificação de gasolinas comerciais em conformidade à legislação vigente. Atualmente, a ANP baseia a classificação em limites máximos e mínimos para uma série de diferentes propriedades físico-químicas. O objetivo do trabalho é propor uma metodologia para fazer uma triagem das amostras coletadas durante o Programa de Monitoramento da Qualidade dos Combustíveis através de um método de classificação. Ela utiliza a espectroscopia NIR, que é uma técnica rápida e não destrutiva, como método analítico. Com isto será possível reduzir o número de ensaios físico-químicos que não necessariamente seriam realizados sistematicamente em todas as amostras, reduzindo-se os custos e aumentando-se a quantidade de postos monitorados. As análises NIR produzem grandes quantidades de dados, o que leva à utilização de técnicas estatísticas multivariáveis para estabelecer as metodologias de classificação. Neste trabalho utilizam-se técnicas já consagradas, como a PCA e a PLS para a compressão dos dados e a LDA e QDA para a classificação das amostras. Os dados analisados correspondem às propriedades físico-químicas e aos espectros NIR de um conjunto de 216 amostras de gasolinas comerciais, utilizado para a concepção dos modelos de classificação, e de outro de 50 amostras, utilizado para a validação dos modelos. Os modelos testados no trabalho foram as combinações da PCA-LDA, PCA-QDA, PLS-LDA, PLS-QDA, PLS (regressão) e a análise dos gráficos de scores (biplot). Os melhores desempenhos foram obtidos pelos gráficos dos scores, em seguida pela regressão PLS, PLS-QDA, PCA-QDA e PLS-QDA. Existem ainda algumas etapas a serem alcançadas para tornar prática a utilização da classificação de gasolinas comerciais através de NIR, no entanto, a contribuição deste estudo é importante pois permitiu demonstrar a sua viabilidade técnica. / In this work, the application of multivariable statistical methods for the classification of commercial gasoline in accordance to applicable laws in Brazil is studied. In the present, the ANP bases the classification of gasoline on lower and upper bounds defined for a number of physico-chemical properties. The objective of this work is to propose an alternative analysis methodology, that is adequate for making a pre-sorting of the samples collected by the Fuel Quality Monitoring Program through a classification method. This method is based on NIR spectroscopy, that is a fast and non-destructive technique, as the analytical method. In this way, it would be possible to reduce the number of physico-chemical analyses, as it would be possible not to perform them on every sample, reducing costs and increasing the quantity and frequency of gas stations that could be monitored. NIR analyses produce a great quantity of data, that makes the use of multivariable statistical techniques necessary in order to set up classification methodologies. In this work the well-known PCA and PLS techniques are used for data compression, and LDA and QDA analyses for sample classification. The data studied correspond to the physico-chemical properties and NIR spectra of a total of 216 commercial gasoline samples, used for model design, and of a 50 samples, used for validation. The classification methods that are tested are combinations of PCA-LDA, PCA-QDA, PLS-LDA, PLS-QDA, PLS (regression) and data compression scores graphical analysis (biplot). Best performance was obtained with compression scores graphical analysis, followed by PLS regression, PLS-QDA, PCA-QDA and PLS-QDA. There are still some steps to be fulfilled before the usage of commercial gasoline classification through NIR could be practical. However, this study has shown that this methodology is technically feasible.

A utilização de controladores preditivos multivariáveis na indústria de processos cresceu significativamente nos últimos anos principalmente devido à versatilidade e a confiabilidade que essa ferramenta proporciona em termos de controle avançado. No entanto, aspectos relacionados à aplicação prática do que vem sendo desenvolvido no meio acadêmico possui pouca difusão na indústria devido às configurações clássicas adotadas, como sistemas quadrados (com o mesmo número de variáveis controladas e manipuladas), modelos lineares, utilização de setpoint e etc. diferindo daquilo que está disponível e é amplamente utilizado industrialmente: sistemas não-quadrados (geralmente com mais variáveis controladas do que manipuladas), modelos não-lineares e utilização de soft-constraints. Esse trabalho propõe uma metodologia para ajuste dos parâmetros presentes em um controlador preditivo, atento à variedade de algoritmos presentes na indústria de processos. Essa metodologia se baseia na obtenção do melhor desempenho alcançável para cada cenário de um modelo global do processo, atendendo as restrições de Número de Desempenho Robusto relativo (rRPN), Máxima Sensibilidade e restrições nas ações de controle. Baseado em um desempenho que é alcançável, o modelo linear global é escalonado (assim como a planta não-linear) e os pesos que levam o sistema para a melhor condição operacional são estimados. Essa técnica abrange controladores operando em faixas e/ou setpoint e configurações não-quadradas, i.e., com mais variáveis controladas do que manipuladas. A abordagem proposta foi testada em uma planta de quatro tanques esféricos com aquecimento apresentando resultados coerentes, corroborando seu potencial de aplicação industrial. / Due to their versatility and reliability, Model Predictive Controllers (MPCs) are the standard solution for advanced process control in the process industry. However, there is a gap between the academic developments and the actual industrial applications, since the most academic studies focus on systems working with set-points and same number of manipulated and controlled variables, whereas the industrial application cope with non-squared configuration usually with several controlled variables in ranging and a reduced number of manipulated variables. This work proposes a tuning methodology for the countable parameters presents in a typical industrial predictive controller, considering the variety of the algorithms presents commercially in the process industry. This methodology is based on the estimation of the best attainable performance for each scenario of the global model of the process, constrained by the relative Robust Performance Number (rRPN), Maximal Sensitivity and restrictions in the control actions. Based on a performance that is attainable, the linear global model is scaled (and the non-linear) and the weights that lead the system to the best operational condition are estimated. This technique covers controllers operating in zones of control and/or set-point tracking and non-square configurations, i.e., with more controlled variables than manipulated. The proposed approach was tested in a Quadruple-Spherical tanks heating system presenting coherent results indicating its potential for industrial applications.

A escolha do modelo de referência é a principal tarefa a ser executada pelo projetista em um projeto de controle por modelo de referência. Uma má escolha do modelo de referência pode resultar em um desempenho de malha fechada que tem pouca semelhança com o especificado e a malha fechada pode até ser instável. Neste trabalho, esse problema será discutido no controle de plantas multivariáveis. O resultado experimental em uma planta de controle de nível de três tanques mostra uma aparentemente correta, ainda que ingênua, escolha do modelo de referência levando a um desempenho muito pobre em malha fechada. O problema é, então, analisado, expondo a ingenuidade do exemplo. Começa-se por reconhecer as restrições fundamentais impostas pelo sistema e, em seguida, deriva-se diretrizes gerais que respeitam essas restrições, para uma escolha eficaz do modelo de referência em sistemas multivariáveis. Também é proporcionada uma nova formulação para calcular o grau relativo mínimo de cada elemento do modelo de referência sem a necessidade de um modelo completo da planta. A aplicação destas orientações em simulações e na planta de três tanques ilustra sua eficácia. / The choice of the reference model is the main task to be performed by the designer in a model reference control design. A poor choice of the reference model may result in a closed-loop performance that bears no resemblance to the specifications and the closedloop may even be unstable. In this work we discuss this issue in the control of multivariable plants. Experimental results in a three tank level control plant show a seemingly correct, yet naive, choice of reference model leading to very poor closed-loop performance. The problem is then analyzed, exposing the naivete of the design example. We start by recognizing the fundamental constraints imposed by the system and then deriving general guidelines respecting these contraints for the effective choice of the reference model in multivariable systems. We also provide a novel formulation to compute the minimal relative degree of each element of the reference model without needing a complete model of the plant. The application of these guidelines to simulations and the three tank plant illustrates their effectiveness.

O escopo desta dissertação é o desenvolvimento de um método para detectar os modelos da matriz dinâmica que estejam degradando o desempenho de controladores preditivos baseados em modelos. O método proposto se baseia na análise de correlação cruzada entre o erro nominal do controlador em malha fechada e a uma estimativa da contribuição de cada canal para o cálculo da saída, filtrada pela função de sensibilidade do controlador. Esse método pode ser empregado na auditoria de controladores com variáveis controladas em setpoints e/ou com variáveis que operem entre faixas, como é usual de se encontrar na indústria. Esta dissertação apresenta os resultados da aplicação bem sucedida do método no sistema de quatro tanques (JOHANSSON, 2000), para o qual três cenários foram avaliados. No primeiro cenário, o método localizou corretamente discrepâncias de ganho e de dinâmica de modelos de um controlador preditivo baseado em modelos (Model-based Predictive Controller, ou controlador MPC). No segundo, o método foi utilizado para avaliar a influência de uma variável externa para melhorar o desempenho de um controlador afetado por distúrbios não medidos. No terceiro cenário, o método localizou canais com modelos nulos que deveriam ser incluídos na matriz de controle de um controlador MPC de estrutura descentralizada. Os resultados deste estudo de caso foram comparados com aqueles obtidos pelo método proposto por BADWE, GUDI e PATWARDHAN (2009), constatando-se que o método proposto é mais robusto que o método usado na comparação, não demandando ajustes de parâmetros por parte do usuário para fornecer bons resultados. A dissertação inclui também um estudo de caso da aplicação industrial do método na auditoria de desempenho de um controlador preditivo linear de estrutura descentralizada, com doze variáveis controladas, oito manipuladas e quatro distúrbios não medidos, aplicado a um sistema de fracionamento de propeno e propano em uma indústria petroquímica. A auditoria permitiu reduzir o escopo de revisão do controlador a dezenove canais da matriz, sendo que quatorze destes correspondiam a canais com modelos nulos que deveriam ser incluídos na matriz. A eficácia do método foi comprovada repetindo-se a avaliação da qualidade de modelo para todas as variáveis controladas. / The scope of this dissertation is the development of a method to detect the models of the dynamic matrix that are affecting the performance of model-based predictive controllers. The proposed method is based on the cross correlation analysis between the nominal controller error and an estimate of the contribution of each channel to the controller output, filtered by the controller nominal sensitivity function. The method can be used in the performance assessment of controllers employing variables controlled at the setpoint and/or those controlled within ranges. This dissertation presents the results of the successful application of the method to the quadruple-tank process (JOHANSSON, 2000), for which three scenarios were evaluated. In the first scenario, the method correctly located gain and dynamic mismatches on a model-based predictive controller (MPC controller). In the second one, the method was used to evaluate the influence of an external variable to improve the performance of a controller affected by unmeasured disturbances. In the third scenario, the method located null models that should be included in the dynamic matrix of a decentralized MPC controller. The results of the three scenarios were compared with the ones obtained through the method proposed by BADWE, GUDI e PATWARDHAN (2009). The proposed method was considered more robust than the reference one for not requiring parameters estimation performed by the user to provide good results. This dissertation also includes a case study about the application of the method on the performance assessment of an industrial linear predictive controller of decentralized structure. The controller has twelve controlled variables, eight manipulated variables, and four unmeasured disturbances and is applied to a propylene-propane fractionation system of a petrochemical industry. The performance assessment allowed reducing the scope of the controller revision to nineteen channels of the models matrix, fourteen of which were null models that should be included in the controller. The efficacy of the proposed method was confirmed by repeating the model quality evaluation for all the controlled variables.

Les travaux de thèse exposés dans ce mémoire ont pour thèmes la modélisation physique et la commande multivariable d'un système thermo-pneumatique complexe dans un contexte automobile. Ils ont été menés dans le cadre d'une collaboration industrielle entre le Département d'Automatique de Supélec et la Direction de la Recherche de Renault, et ont pour application principale le système d'alimentation en air d'un véhicule à pile à combustible avec reformeur de carburant embarqué. Il faut préciser que la conception et la commande d'un tel système déterminent de manière significative les caractéristiques et les performances d'un véhicule électrique intégrant une pile à combustible, la complexité augmentant lorsque la production d'hydrogène à bord du véhicule par reformage remplace le stockage d'hydrogène comprimé à haute pression.<br /><br />Les différentes étapes de la thèse ont d'abord abouti au développement de modèles dynamiques représentatifs des non-linéarités et des couplages inhérents aux phénomènes acoustiques dans les fluides compressibles, et à l'identification des modèles des différents actionneurs et capteurs retenus pour cette application. Un modèle réduit et conditionné du système à commander a alors été dérivé du modèle non-linéaire global du système d'air, puis utilisé comme support de l'analyse et de la synthèse de stratégies de commande multivariables. L'approche multivariable se justifie clairement par l'action de découplage des effets produits par les divers actionneurs, et par la capacité à respecter les spécifications dynamiques du cahier des charges.<br /><br />Enfin, une part importante du travail a été consacrée à la réalisation d'un banc d'essai expérimental reconstituant le système d'alimentation en air, et prenant en compte les exigences futures d'intégration à bord d'un véhicule. L'exploitation de ce moyen d'essai a permis de tester les divers composants devant intégrer à terme le système "pile à combustible" du projet RESPIRE (Réduction des Émissions avec Système PIle à combustible et Reformeur Essence), mais aussi de valider les modèles et lois de commande du système d'air développés au cours de la thèse.

<p>The goal of this Master thesis has on the one hand been to create a simulation environment for robots, where not only the simulations in this work can be performed, but also similar robot simulations, and on the other hand to study regulators that can increase the possibilities of rejecting disturbances on an industrial robot. The robot model used has three degrees of freedom, corresponding to the three main links on ABB:s IRB7600. </p><p>The simulation environment is created using Matlab, Simulink, and Robotics Toolbox. It is constructed in a general way and can be used for simulations of other robot objects created in Robotics Toolbox. </p><p>A gain scheduling is added to the LQ-regulator, where the feedback matrix is varied depending on the arm position in the workspace. The gain scheduling is implemented along a reference path in the workspace, around which the simulations and frequency analyses are performed. </p><p>The regulators that have been tested are a PID-regulator, a gain scheduled LQ-regulator, a gain scheduled LQ-regulator with reconstructed states, and finally a fix LQ-regulator with reconstructed states. Results from the tests show that the gain scheduling LQ-regulator is the one that yields the best rejection of disturbances, but the corresponding regulator with reconstructed states, which is more realistic, performs nearly as well. The model based regulators are, however, significantly better when it comes to rejecting disturbances than the PID-regulator.</p>

This thesis examined the factors correlated with rapid and benign progression of disease in a group of 1452 Parkinsons disease (PD) patients. The data were collected in a movement disorders clinic at the Royal University Hospital, University of Saskatchewan run by Dr. Alex Rajput and Dr. Ali Rajput. This data is a clinical dataset of PD patients collected from 1970 through to February, 2005. This was a retrospective cases-only study, with anticipated analytical follow-up if any correlations were detected between progression type of PD and the many independent variables available in the dataset. <p>Rapid progression was defined as those subjects who reached Hoehn and Yahr stage 3 within three years or H&Y stage 4 or 5 within five years. Subjects who remained in Hoehn and Yahr stage 1 or 2, ten years after onset of disease, were defined as having benign progression. The study analyzed demographic and clinical findings at first visit to this clinic associated with rapid and benign progression of PD. <p> Analysis revealed that, at first clinic visit, benign progression was positively associated with disease duration (OR=1.41; 95% CI 1.27, 1.57), male sex (OR=3.23; 95% CI 1.70, 6.16), and current smoking habit (OR=2.33; 95% CI 0.67, 8.11). Benign progression was negatively associated with older age of onset (OR=0.36; 95% CI 0.25, 0.50), past history of smoking (OR=0.46; 95% CI 0.24, 0.89), current or past use of levodopa (OR=0.45; 95% CI 0.21, 0.98), and mild to severe rigidity (OR=0.43; 95% CI 0.23, 0.80). <p>Analysis also revealed that, at first clinic visit, rapid progression was positively associated with older age of onset (OR=2.45; 95% CI 1.80, 3.33) and mild to severe rigidity (OR=1.73; 95% CI 1.02, 2.94). Rapid progression was negatively associated with disease duration (OR=0.52; 95% CI 0.44, 0.62), male sex (OR=0.58; CI 0.35, 0.95), and mild to severe resting tremor (OR=0.47; CI 0.28, 0.77). <p>The results of this study indicate that age of onset, disease duration, male sex, and rigidity are good potential predictors of disease progression in PD because they have opposite associations with rapid and benign progression. History of levodopa use was negatively associated with benign progression and as such may be good indicator of non-benign progression. Although previous studies found no predictive value for smoking history, the current study reported a unique association between smoking history and benign progression. Past smoking history was negatively associated with benign progression. While there was a positive association with current smoking history, the result was not statistically significant. Resting tremor was negatively associated with rapid progression and as such may be a good indicator of non-rapid progression. <p> Disease characteristics collected at first clinic visit are useful in predicting the course of progression of PD. With more rapid progression of PD closer and more frequent follow-up of patients may be necessary.

The goal of this Master thesis has on the one hand been to create a simulation environment for robots, where not only the simulations in this work can be performed, but also similar robot simulations, and on the other hand to study regulators that can increase the possibilities of rejecting disturbances on an industrial robot. The robot model used has three degrees of freedom, corresponding to the three main links on ABB:s IRB7600. The simulation environment is created using Matlab, Simulink, and Robotics Toolbox. It is constructed in a general way and can be used for simulations of other robot objects created in Robotics Toolbox. A gain scheduling is added to the LQ-regulator, where the feedback matrix is varied depending on the arm position in the workspace. The gain scheduling is implemented along a reference path in the workspace, around which the simulations and frequency analyses are performed. The regulators that have been tested are a PID-regulator, a gain scheduled LQ-regulator, a gain scheduled LQ-regulator with reconstructed states, and finally a fix LQ-regulator with reconstructed states. Results from the tests show that the gain scheduling LQ-regulator is the one that yields the best rejection of disturbances, but the corresponding regulator with reconstructed states, which is more realistic, performs nearly as well. The model based regulators are, however, significantly better when it comes to rejecting disturbances than the PID-regulator.

This thesis examined the factors correlated with rapid and benign progression of disease in a group of 1452 Parkinsons disease (PD) patients. The data were collected in a movement disorders clinic at the Royal University Hospital, University of Saskatchewan run by Dr. Alex Rajput and Dr. Ali Rajput. This data is a clinical dataset of PD patients collected from 1970 through to February, 2005. This was a retrospective cases-only study, with anticipated analytical follow-up if any correlations were detected between progression type of PD and the many independent variables available in the dataset. <p>Rapid progression was defined as those subjects who reached Hoehn and Yahr stage 3 within three years or H&Y stage 4 or 5 within five years. Subjects who remained in Hoehn and Yahr stage 1 or 2, ten years after onset of disease, were defined as having benign progression. The study analyzed demographic and clinical findings at first visit to this clinic associated with rapid and benign progression of PD. <p> Analysis revealed that, at first clinic visit, benign progression was positively associated with disease duration (OR=1.41; 95% CI 1.27, 1.57), male sex (OR=3.23; 95% CI 1.70, 6.16), and current smoking habit (OR=2.33; 95% CI 0.67, 8.11). Benign progression was negatively associated with older age of onset (OR=0.36; 95% CI 0.25, 0.50), past history of smoking (OR=0.46; 95% CI 0.24, 0.89), current or past use of levodopa (OR=0.45; 95% CI 0.21, 0.98), and mild to severe rigidity (OR=0.43; 95% CI 0.23, 0.80). <p>Analysis also revealed that, at first clinic visit, rapid progression was positively associated with older age of onset (OR=2.45; 95% CI 1.80, 3.33) and mild to severe rigidity (OR=1.73; 95% CI 1.02, 2.94). Rapid progression was negatively associated with disease duration (OR=0.52; 95% CI 0.44, 0.62), male sex (OR=0.58; CI 0.35, 0.95), and mild to severe resting tremor (OR=0.47; CI 0.28, 0.77). <p>The results of this study indicate that age of onset, disease duration, male sex, and rigidity are good potential predictors of disease progression in PD because they have opposite associations with rapid and benign progression. History of levodopa use was negatively associated with benign progression and as such may be good indicator of non-benign progression. Although previous studies found no predictive value for smoking history, the current study reported a unique association between smoking history and benign progression. Past smoking history was negatively associated with benign progression. While there was a positive association with current smoking history, the result was not statistically significant. Resting tremor was negatively associated with rapid progression and as such may be a good indicator of non-rapid progression. <p> Disease characteristics collected at first clinic visit are useful in predicting the course of progression of PD. With more rapid progression of PD closer and more frequent follow-up of patients may be necessary.

In the past, a lot of studies about the comparison of exchange rate forecasting models have been carried out. Most of these studies have a similar result which is the random walk model has the best forecasting performance. In this thesis, I want to find a model to beat the random walk model in forecasting the exchange rate. In my study, the vector autoregressive model (VAR), restricted vector autoregressive model (RVAR), vector error correction model (VEC), Bayesian vector autoregressive model are employed in the analysis. These multivariable time series models are compared with the random walk model by evaluating the forecasting accuracy of the exchange rate for three North European countries both in short-term and long-term. For short-term, it can be concluded that the random walk model has the best forecasting accuracy. However, for long-term, the random walk model is beaten. The equal accuracy test proves this phenomenon really exists.