This book determines adjustable parameters in mathematical models that describe steady state or dynamic systems, presenting the most important optimization methods used for parameter estimation. It focuses on the Gauss-Newton method and its modifications for systems and processes represented by algebraic or differential equation models.

Optimal State Estimation for Process Monitoring, Fault Diagnosis and Control presents various mechanistic model based state estimators and data-driven model based state estimators with a special emphasis on their development and applications to process monitoring, fault diagnosis and control. The design and analysis of different state estimators are highlighted with a number of applications and case studies concerning to various real chemical and biochemical processes. The book starts with the introduction of basic concepts, extending to classical methods and successively leading to advances in this field. Design and implementation of various classical and advanced state estimation methods to solve a wide variety of problems makes this book immensely useful for the audience working in different disciplines in academics, research and industry in areas concerning to process monitoring, fault diagnosis, control and related disciplines. - Describes various classical and advanced versions of mechanistic model based state estimation algorithms - Describes various data-driven model based state estimation techniques - Highlights a number of real applications of mechanistic model based and data-driven model based state estimators/soft sensors - Beneficial to those associated with process monitoring, fault diagnosis, online optimization, control and related areas

A rigorous introduction to the theory and applications of state estimation and association, an important area in aerospace, electronics, and defense industries. Applied state estimation and association is an important area for practicing engineers in aerospace, electronics, and defense industries, used in such tasks as signal processing, tracking, and navigation. This book offers a rigorous introduction to both theory and application of state estimation and association. It takes a unified approach to problem formulation and solution development that helps students and junior engineers build a sound theoretical foundation for their work and develop skills and tools for practical applications. Chapters 1 through 6 focus on solving the problem of estimation with a single sensor observing a single object, and cover such topics as parameter estimation, state estimation for linear and nonlinear systems, and multiple model estimation algorithms. Chapters 7 through 10 expand the discussion to consider multiple sensors and multiple objects. The book can be used in a first-year graduate course in control or system engineering or as a reference for professionals. Each chapter ends with problems that will help readers to develop derivation skills that can be applied to new problems and to build computer models that offer a useful set of tools for problem solving. Readers must be familiar with state-variable representation of systems and basic probability theory including random and stochastic processes.

Model-based control and process optimization technologies are becoming more commonly used by chemical engineers. These algorithms rely on fundamental or empirical models that are frequently described by systems of differential equations with unknown parameters. It is, therefore, very important for modellers of chemical engineering processes to have access to reliable and efficient tools for parameter estimation in dynamic models. The purpose of this thesis is to develop an efficient and easy-to-use parameter estimation algorithm that can address difficulties that frequently arise when estimating parameters in nonlinear continuous-time dynamic models of industrial processes. The proposed algorithm has desirable numerical stability properties that stem from using piece-wise polynomial discretization schemes to transform the model differential equations into a set of algebraic equations. Consequently, parameters can be estimated by solving a nonlinear programming problem without requiring repeated numerical integration of the differential equations. Possible modelling discrepancies and process disturbances are accounted for in the proposed algorithm, and estimates of the process disturbance intensities can be obtained along with estimates of model parameters and states. Theoretical approximate confidence interval expressions for the parameters are developed. Through a practical two-phase nylon reactor example, as well as several simulation studies using stirred tank reactors, it is shown that the proposed parameter estimation algorithm can address difficulties such as: different types of measured responses with different levels of measurement noise, measurements taken at irregularly-spaced sampling times, unknown initial conditions for some state variables, unmeasured state variables, and unknown disturbances that enter the process and influence its future behaviour.

State Estimation for Dynamic Systems presents the state of the art in this field and discusses a new method of state estimation. The method makes it possible to obtain optimal two-sided ellipsoidal bounds for reachable sets of linear and nonlinear control systems with discrete and continuous time. The practical stability of dynamic systems subjected to disturbances can be analyzed, and two-sided estimates in optimal control and differential games can be obtained. The method described in the book also permits guaranteed state estimation (filtering) for dynamic systems in the presence of external disturbances and observation errors. Numerical algorithms for state estimation and optimal control, as well as a number of applications and examples, are presented. The book will be an excellent reference for researchers and engineers working in applied mathematics, control theory, and system analysis. It will also appeal to pure and applied mathematicians, control engineers, and computer programmers.

The application of modern methods in numerical mathematics on problems in chemical engineering is essential for designing, analyzing and running chemical processes and even entire plants. Scientific Computing in Chemical Engineering II gives the state of the art from the point of view of numerical mathematicians as well as that of engineers. The present volume as part of a two-volume edition covers topics such as computer-aided process design, combustion and flame, image processing, optimization, control, and neural networks. The volume is aimed at scientists, practitioners and graduate students in chemical engineering, industrial engineering and numerical mathematics.