Modeling and Model Predictive Control of an Industrial Hydraulic System

This thesis aims to illustrate the construction of a mathematical model of a hydraulic system, oriented to the design of a model predictive control (MPC) algorithm. The modeling procedure starts with the basic formulation of a piston-servovalve system. The latter is a complex non linear system with some unknown and not measurable effects that constitute a challenging problem for the modeling procedure. The first level of approximation for system parameters is obtained basing on datasheet informations, provided workbench tests and other data from the company. Then, to validate and refine the model, open-loop simulations have been made for data matching with the characteristics obtained from real acquisitions. The final developed set of ODEs captures all the main peculiarities of the system despite some characteristics due to highly varying and unknown hydraulic effects, like the unmodeled resistive elements of the pipes. After an accurate analysis, since the model presents many internal complexities, a simplified version is presented. The latter is used to linearize and discretize correctly the non linear model. Basing on that, a MPC algorithm for reference tracking with linear constraints is implemented. The results obtained show the potential of MPC in this kind of industrial applications, thus a high quality tracking performances while satisfying state and input constraints. The increased robustness and flexibility are evident with respect to the standard control techniques, such as PID controllers, adopted for these systems. The simulations for model validation and the controlled system have been carried out in a Python code environment.

The use of principal components and univariate charts to control multivariate processes

In this article, we evaluate the performance of the T2 chart based on the principal components (PC chart) and the simultaneous univariate control charts based on the original variables (SU X̄ charts) or based on the principal components (SUPC charts). The main reason to consider the PC chart lies on the dimensionality reduction. However, depending on the disturbance and on the way the original variables are related, the chart is very slow in signaling, except when all variables are negatively correlated and the principal component is wisely selected. Comparing the SU X̄, the SUPC and the T 2 charts we conclude that the SU X̄ charts (SUPC charts) have a better overall performance when the variables are positively (negatively) correlated. We also develop the expression to obtain the power of two S 2 charts designed for monitoring the covariance matrix. These joint S2 charts are, in the majority of the cases, more efficient than the generalized variance |S| chart.

Comparison between conventional and stochastic pinning control

Theoretical developments on pinning control of complex dynamical networks have mainly focused on the deterministic versions of the model dynamics. However, the dynamical behavior of most real networks is often affected by stochastic noise components. In this paper the pinning control of a stochastic version of the coupled map lattice network with spatiotemporal characteristics is studied. The control of these complex dynamical networks have functional uncertainty which should be considered when calculating stabilizing control signals. Two feedback control methods are considered: the conventional feedback control and modified stochastic feedback control. It is shown that the typically-used conventional control method suffers from the ignorance of model uncertainty leading to a reduction and potentially a collapse in the control efficiency. Numerical verification of the main result is provided for a chaotic coupled map lattice network. © 2011 IEEE.

Supervisory control of wastewater treatment plants by combining principal component analysis and fuzzy c-means clustering

In this paper a methodology for integrated multivariate monitoring and control of biological wastewater treatment plants during extreme events is presented. To monitor the process, on-line dynamic principal component analysis (PCA) is performed on the process data to extract the principal components that represent the underlying mechanisms of the process. Fuzzy c-means (FCM) clustering is used to classify the operational state. Performing clustering on scores from PCA solves computational problems as well as increases robustness due to noise attenuation. The class-membership information from FCM is used to derive adequate control set points for the local control loops. The methodology is illustrated by a simulation study of a biological wastewater treatment plant, on which disturbances of various types are imposed. The results show that the methodology can be used to determine and co-ordinate control actions in order to shift the control objective and improve the effluent quality.

Social and medical vulnerability factors of frequent users at the emergency department: a case-control study

BACKGROUND: Up to 5% of patients presenting to the emergency department (ED) four or more times within a 12 month period represent 21% of total ED visits. In this study we sought to characterize social and medical vulnerability factors of ED frequent users (FUs) and to explore if these factors hold simultaneously. METHODS: We performed a case-control study at Lausanne University Hospital, Switzerland. Patients over 18 years presenting to the ED at least once within the study period (April 2008 toMarch 2009) were included. FUs were defined as patients with four or more ED visits within the previous 12 months. Outcome data were extracted from medical records of the first ED attendance within the study period. Outcomes included basic demographics and social variables, ED admission diagnosis, somatic and psychiatric days hospitalized over 12 months, and having a primary care physician.We calculated the percentage of FUs and non-FUs having at least one social and one medical vulnerability factor. The four chosen social factors included: unemployed and/or dependence on government welfare, institutionalized and/or without fixed residence, either separated, divorced or widowed, and under guardianship. The fourmedical vulnerability factors were: ≥6 somatic days hospitalized, ≥1 psychiatric days hospitalized, ≥5 clinical departments used (all three factors measured over 12 months), and ED admission diagnosis of alcohol and/or drug abuse. Univariate and multivariate logistical regression analyses allowed comparison of two JGIM ABSTRACTS S391 random samples of 354 FUs and 354 non-FUs (statistical power 0.9, alpha 0.05 for all outcomes except gender, country of birth, and insurance type). RESULTS: FUs accounted for 7.7% of ED patients and 24.9% of ED visits. Univariate logistic regression showed that FUs were older (mean age 49.8 vs. 45.2 yrs, p=0.003),more often separated and/or divorced (17.5%vs. 13.9%, p=0.029) or widowed (13.8% vs. 8.8%, p=0.029), and either unemployed or dependent on government welfare (31.3% vs. 13.3%, p<0.001), compared to non-FUs. FUs cumulated more days hospitalized over 12 months (mean number of somatic days per patient 1.0 vs. 0.3, p<0.001; mean number of psychiatric days per patient 0.12 vs. 0.03, p<0.001). The two groups were similar regarding gender distribution (females 51.7% vs. 48.3%). The multivariate linear regression model was based on the six most significant factors identified by univariate analysis The model showed that FUs had more social problems, as they were more likely to be institutionalized or not have a fixed residence (OR 4.62; 95% CI, 1.65 to 12.93), and to be unemployed or dependent on government welfare (OR 2.03; 95% CI, 1.31 to 3.14) compared to non-FUs. FUs were more likely to need medical care, as indicated by involvement of≥5 clinical departments over 12 months (OR 6.2; 95%CI, 3.74 to 10.15), having an ED admission diagnosis of substance abuse (OR 3.23; 95% CI, 1.23 to 8.46) and having a primary care physician (OR 1.70;95%CI, 1.13 to 2.56); however, they were less likely to present with an admission diagnosis of injury (OR 0.64; 95% CI, 0.40 to 1.00) compared to non-FUs. FUs were more likely to combine at least one social with one medical vulnerability factor (38.4% vs. 12.1%, OR 7.74; 95% CI 5.03 to 11.93). CONCLUSIONS: FUs were more likely than non-FUs to have social and medical vulnerability factors and to have multiple factors in combination.

Estimation of State Space Models and Stochastic Volatility

Ma thèse est composée de trois chapitres reliés à l'estimation des modèles espace-état et volatilité stochastique. Dans le première article, nous développons une procédure de lissage de l'état, avec efficacité computationnelle, dans un modèle espace-état linéaire et gaussien. Nous montrons comment exploiter la structure particulière des modèles espace-état pour tirer les états latents efficacement. Nous analysons l'efficacité computationnelle des méthodes basées sur le filtre de Kalman, l'algorithme facteur de Cholesky et notre nouvelle méthode utilisant le compte d'opérations et d'expériences de calcul. Nous montrons que pour de nombreux cas importants, notre méthode est plus efficace. Les gains sont particulièrement grands pour les cas où la dimension des variables observées est grande ou dans les cas où il faut faire des tirages répétés des états pour les mêmes valeurs de paramètres. Comme application, on considère un modèle multivarié de Poisson avec le temps des intensités variables, lequel est utilisé pour analyser le compte de données des transactions sur les marchés financières. Dans le deuxième chapitre, nous proposons une nouvelle technique pour analyser des modèles multivariés à volatilité stochastique. La méthode proposée est basée sur le tirage efficace de la volatilité de son densité conditionnelle sachant les paramètres et les données. Notre méthodologie s'applique aux modèles avec plusieurs types de dépendance dans la coupe transversale. Nous pouvons modeler des matrices de corrélation conditionnelles variant dans le temps en incorporant des facteurs dans l'équation de rendements, où les facteurs sont des processus de volatilité stochastique indépendants. Nous pouvons incorporer des copules pour permettre la dépendance conditionnelle des rendements sachant la volatilité, permettant avoir différent lois marginaux de Student avec des degrés de liberté spécifiques pour capturer l'hétérogénéité des rendements. On tire la volatilité comme un bloc dans la dimension du temps et un à la fois dans la dimension de la coupe transversale. Nous appliquons la méthode introduite par McCausland (2012) pour obtenir une bonne approximation de la distribution conditionnelle à posteriori de la volatilité d'un rendement sachant les volatilités d'autres rendements, les paramètres et les corrélations dynamiques. Le modèle est évalué en utilisant des données réelles pour dix taux de change. Nous rapportons des résultats pour des modèles univariés de volatilité stochastique et deux modèles multivariés. Dans le troisième chapitre, nous évaluons l'information contribuée par des variations de volatilite réalisée à l'évaluation et prévision de la volatilité quand des prix sont mesurés avec et sans erreur. Nous utilisons de modèles de volatilité stochastique. Nous considérons le point de vue d'un investisseur pour qui la volatilité est une variable latent inconnu et la volatilité réalisée est une quantité d'échantillon qui contient des informations sur lui. Nous employons des méthodes bayésiennes de Monte Carlo par chaîne de Markov pour estimer les modèles, qui permettent la formulation, non seulement des densités a posteriori de la volatilité, mais aussi les densités prédictives de la volatilité future. Nous comparons les prévisions de volatilité et les taux de succès des prévisions qui emploient et n'emploient pas l'information contenue dans la volatilité réalisée. Cette approche se distingue de celles existantes dans la littérature empirique en ce sens que ces dernières se limitent le plus souvent à documenter la capacité de la volatilité réalisée à se prévoir à elle-même. Nous présentons des applications empiriques en utilisant les rendements journaliers des indices et de taux de change. Les différents modèles concurrents sont appliqués à la seconde moitié de 2008, une période marquante dans la récente crise financière.

Simulation-based smoothing and filtering in factor stochastic volatility models : two econometric applications

In this article we use factor models to describe a certain class of covariance structure for financiaI time series models. More specifical1y, we concentrate on situations where the factor variances are modeled by a multivariate stochastic volatility structure. We build on previous work by allowing the factor loadings, in the factor mo deI structure, to have a time-varying structure and to capture changes in asset weights over time motivated by applications with multi pIe time series of daily exchange rates. We explore and discuss potential extensions to the models exposed here in the prediction area. This discussion leads to open issues on real time implementation and natural model comparisons.

Simulation -based smoothing and filtering in factor stochastic volatility models : two econometric applications (July-2001)

The past decade has wítenessed a series of (well accepted and defined) financial crises periods in the world economy. Most of these events aI,"e country specific and eventually spreaded out across neighbor countries, with the concept of vicinity extrapolating the geographic maps and entering the contagion maps. Unfortunately, what contagion represents and how to measure it are still unanswered questions. In this article we measure the transmission of shocks by cross-market correlation\ coefficients following Forbes and Rigobon's (2000) notion of shift-contagion,. Our main contribution relies upon the use of traditional factor model techniques combined with stochastic volatility mo deIs to study the dependence among Latin American stock price indexes and the North American indexo More specifically, we concentrate on situations where the factor variances are modeled by a multivariate stochastic volatility structure. From a theoretical perspective, we improve currently available methodology by allowing the factor loadings, in the factor model structure, to have a time-varying structure and to capture changes in the series' weights over time. By doing this, we believe that changes and interventions experienced by those five countries are well accommodated by our models which learns and adapts reasonably fast to those economic and idiosyncratic shocks. We empirically show that the time varying covariance structure can be modeled by one or two common factors and that some sort of contagion is present in most of the series' covariances during periods of economical instability, or crisis. Open issues on real time implementation and natural model comparisons are thoroughly discussed.

Stochastic dynamics of Musca domestica (Diptera: Muscidae) and Chrysomya putoria (Diptera: Calliphoridae)

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Strategy and model building in the fourth dimension: a null model for genotype × age interaction as a Gaussian stationary stochastic process

Abstract Background Using univariate and multivariate variance components linkage analysis methods, we studied possible genotype × age interaction in cardiovascular phenotypes related to the aging process from the Framingham Heart Study. Results We found evidence for genotype × age interaction for fasting glucose and systolic blood pressure. Conclusions There is polygenic genotype × age interaction for fasting glucose and systolic blood pressure and quantitative trait locus × age interaction for a linkage signal for systolic blood pressure phenotypes located on chromosome 17 at 67 cM.

A case-control study of hepatitis C virus and its interaction with hepatitis B virus on the development of hepatocellular carcinoma in the USA

Objective. The aim of this study was to assess the independent risk of hepatitis C virus (HCV) infection in the development of hepatocellular carcinoma (HCC). The independent risk of hepatitis B virus (HBV), its interaction with hepatitis C virus and the association with other risk factors were examined.^ Methods. A hospital-based case-control study was conducted between January 1994 and December 1995. We enrolled 115 pathologically confirmed HCC patients and 230 nonliver cancer controls, who were matched by age ($\pm$5 years), gender, and year of diagnosis. Both cases and controls were recruited from The University of Texas M. D. Anderson Cancer Center at Houston. The risk factors were collected through personal interviews and blood samples were tested for HCV and HBV markers. Univariate and multivariate analyses were performed through conditional logistic regression.^ The prevalence of anti-HCV positive is 25.2% in HCC cases compared to 3.0% in controls. The univariate analysis showed that anti-HCV, HBsAg, alcohol drinking and cigarette smoking were significantly associated with HCC, however, family history of cancer, occupational chemical exposure, and use of oral contraceptive were not. Multivariate analysis revealed a matched odds ratio (OR) of 10.1 (95% CI 3.7-27.4) for anti-HCV, and an OR of 11.9 (95% CI 2.5-57.5) for HBsAg. However, dual infection of HCV and HBV had only a thirteen times increase in the risk of HCC, OR = 13.9 (95% CI 1.3-150.6). The estimated population attributable risk percent was 23.4% for HCV, 12.6% for HBV, and 5.3% for both viruses. Ever alcohol drinkers was positively associated with HCC, especially among daily drinkers, matched OR was 5.7 (95% CI 2.1-15.6). However, there was no significant increase in the risk of HCC among smokers as compared to nonsmokers. The mean age of HCC patients was significantly younger among the HBV(+) group and among the HCV(+)/HBV(+) group, when compared to the group of HCC patients with no viral markers. The association between past histories of blood transfusion, acupuncture, tattoo and IVDU was highly significant among the HCV(+) group and the HBV(+)/HCV(+) group, as compared to HCC patients with no viral markers. Forty percent of the HCC patients were pathologically or clinically diagnosed with liver cirrhosis. Anti-HCV(+) (OR = 3.6 95% CI 1.5-8.9) and alcohol drinking (OR = 2.7 95% CI 1.1-6.7), but not HBsAg, are the major risk factors for liver cirrhosis in HCC patients.^ Conclusion. Both hepatitis B virus and hepatitis C virus were independent risk factors for HCC. There was not enough evidence to determine the interaction between both viruses. Only daily alcoholic drinkers showed increasing risk for HCC development, as compared to nondrinkers. ^

Improved robust control of nonlinear stochastic systems using uncertain models

We introduce a technique for quantifying and then exploiting uncertainty in nonlinear stochastic control systems. The approach is suboptimal though robust and relies upon the approximation of the forward and inverse plant models by neural networks, which also estimate the intrinsic uncertainty. Sampling from the resulting Gaussian distributions of the inversion based neurocontroller allows us to introduce a control law which is demonstrably more robust than traditional adaptive controllers.

A mixture density network approach to modelling and exploiting uncertainty in nonlinear control problems

In nonlinear and stochastic control problems, learning an efficient feed-forward controller is not amenable to conventional neurocontrol methods. For these approaches, estimating and then incorporating uncertainty in the controller and feed-forward models can produce more robust control results. Here, we introduce a novel inversion-based neurocontroller for solving control problems involving uncertain nonlinear systems which could also compensate for multi-valued systems. The approach uses recent developments in neural networks, especially in the context of modelling statistical distributions, which are applied to forward and inverse plant models. Provided that certain conditions are met, an estimate of the intrinsic uncertainty for the outputs of neural networks can be obtained using the statistical properties of networks. More generally, multicomponent distributions can be modelled by the mixture density network. Based on importance sampling from these distributions a novel robust inverse control approach is obtained. This importance sampling provides a structured and principled approach to constrain the complexity of the search space for the ideal control law. The developed methodology circumvents the dynamic programming problem by using the predicted neural network uncertainty to localise the possible control solutions to consider. A nonlinear multi-variable system with different delays between the input-output pairs is used to demonstrate the successful application of the developed control algorithm. The proposed method is suitable for redundant control systems and allows us to model strongly non-Gaussian distributions of control signal as well as processes with hysteresis. © 2004 Elsevier Ltd. All rights reserved.

Efficient Control in Multistage Stochastic Optimization Problem

AMS subject classification: 90C31, 90A09, 49K15, 49L20.

Optimal investment under stochastic volatility and power type utility function

2000 Mathematics Subject Classification: 37F21, 70H20, 37L40, 37C40, 91G80, 93E20.