Data Driven Modeling Filtering And Control

Research in the field of system identification and control has been shifting from traditional model-based to data-driven or evidence-based theories. The latter methods enable better designs based on more direct and accurate data-based information and verifiable data. In the era of big data, IoT, and cyber-physical systems, this subject is of growing importance, as data-driven approaches are key enablers to solve problems that could not be addressed by previous standard approaches. This book presents a number of innovative data-driven methodologies, complemented by significant application examples to show the potential offered by the most recent advances in the field.

Using important examples, this book showcases the potential of the latest data-based and data-driven methodologies for filter and control design. It discusses the most important classes of dynamic systems, along with the statistical and set membership analysis and design frameworks.

This book provides a new perspective on modeling cyber-physical systems (CPS), using a data-driven approach. The authors cover the use of state-of-the-art machine learning and artificial intelligence algorithms for modeling various aspect of the CPS. This book provides insight on how a data-driven modeling approach can be utilized to take advantage of the relation between the cyber and the physical domain of the CPS to aid the first-principle approach in capturing the stochastic phenomena affecting the CPS. The authors provide practical use cases of the data-driven modeling approach for securing the CPS, presenting novel attack models, building and maintaining the digital twin of the physical system. The book also presents novel, data-driven algorithms to handle non- Euclidean data. In summary, this book presents a novel perspective for modeling the CPS.

A typical design procedure for model predictive control or control performance monitoring consists of: 1. identification of a parametric or nonparametric model; 2. derivation of the output predictor from the model; 3. design of the control law or calculation of performance indices according to the predictor. Both design problems need an explicit model form and both require this three-step design procedure. Can this design procedure be simplified? Can an explicit model be avoided? With these questions in mind, the authors eliminate the first and second step of the above design procedure, a “data-driven” approach in the sense that no traditional parametric models are used; hence, the intermediate subspace matrices, which are obtained from the process data and otherwise identified as a first step in the subspace identification methods, are used directly for the designs. Without using an explicit model, the design procedure is simplified and the modelling error caused by parameterization is eliminated.

This book provides a thorough and fresh treatment of the control of innovative variable-geometry vehicle suspension systems. A deep survey on the topic, which covers the varying types of existing variable-geometry suspension solutions, introduces the study. The book discusses three important aspects of the subject: • robust control design; • nonlinear system analysis; and • integration of learning and control methods. The importance of variable-geometry suspensions and the effectiveness of design methods implemented in the autonomous functionalities of electric vehicles—functionalities like independent steering and torque vectoring—are illustrated. The authors detail the theoretical background of modeling, control design, and analysis for each functionality. The theoretical results achieved through simulation examples and hardware-in-the-loop scenarios are confirmed. The book highlights emerging ideas of applying machine-learning-based methods in the control system with guarantees on safety performance. The authors propose novel control methods, based on the theory of robust linear parameter-varying systems, with examples for various suspension systems. Academic researchers interested in automotive systems and their counterparts involved in industrial research and development will find much to interest them in the eleven chapters of Control of Variable-Geometry Vehicle Suspensions.

This book is a comprehensive exposition of the theory, algorithms, and applications of structured low-rank approximation. Local optimization methods and effective suboptimal convex relaxations for Toeplitz, Hankel, and Sylvester structured problems are presented. A major part of the text is devoted to application of the theory with a range of applications from systems and control theory to psychometrics being described. Special knowledge of the application fields is not required. The second edition of /Low-Rank Approximation/ is a thoroughly edited and extensively rewritten revision. It contains new chapters and sections that introduce the topics of: • variable projection for structured low-rank approximation;• missing data estimation;• data-driven filtering and control;• stochastic model representation and identification;• identification of polynomial time-invariant systems; and• blind identification with deterministic input model. The book is complemented by a software implementation of the methods presented, which makes the theory directly applicable in practice. In particular, all numerical examples in the book are included in demonstration files and can be reproduced by the reader. This gives hands-on experience with the theory and methods detailed. In addition, exercises and MATLAB^® /Octave examples will assist the reader quickly to assimilate the theory on a chapter-by-chapter basis. “Each chapter is completed with a new section of exercises to which complete solutions are provided.” Low-Rank Approximation (second edition) is a broad survey of the Low-Rank Approximation theory and applications of its field which will be of direct interest to researchers in system identification, control and systems theory, numerical linear algebra and optimization. The supplementary problems and solutions render it suitable for use in teaching graduate courses in those subjects as well.

Combining scientific computing methods and algorithms with modern data analysis techniques, including basic applications of compressive sensing and machine learning, this book develops techniques that allow for the integration of the dynamics of complex systems and big data. MATLAB is used throughout for mathematical solution strategies.