Item description for Robust Estimation and Failure Detection: A Concise Treatment (Advances in Industrial Control) by Rami S. Mangoubi...
This work presents a concise treatment of robust estimation, with a thorough presentation of Kalman filtering. The robust game theoretic/ H? filtering theory is developed, making it possible to design estimators that are more general than Kalman filters and are robust to model uncertainties and rapid model variations. It also reviews the likelihood ratio method for failure detection and demonstrates how robust filters can enhance such methods by enabling the design of failure detectors that are sensitive to failures but insensitive to model uncertainties and/or rapid model variations. Robust Estimation and Failure Detection is of particular value to students, researchers and engineers with an interest in filtering or failure detection, offering classical and advanced theories and design methods and allowing them to benefit from the robust control theoretic developments of the last fifteen years. Control researchers and engineers will also find it relevant, as it demonstrates how development in their discipline affects these two neighbouring fields.
Promise Angels is dedicated to bringing you great books at great prices. Whether you read for entertainment, to learn, or for literacy - you will find what you want at promiseangels.com!
Est. Packaging Dimensions: Length: 9.48" Width: 6.33" Height: 0.71" Weight: 0.96 lbs.
Release Date Sep 18, 1998
ISBN 3540762515 ISBN13 9783540762515
Reviews - What do customers think about Robust Estimation and Failure Detection: A Concise Treatment (Advances in Industrial Control)?
An Excellent Book May 18, 2001
Many books on recursive estimation or filtering were published over the last 4 decades. This one is unique for several reasons. The book has a lucid formulation of not only the Kalman filter, but a large family of filtering problems as well. It explains the relationship between these problems and the properties of the solutions in both the deterministic and stochastic context. As such, the book opens a new era in the subject of recursive filtering: It goes beyond the Kalman filter, which is also well covered.
The book treats the subject of detection in dynamic systems as well. As the author himself notes in the preface, there are many books in signal detection and estimation, and he is introducing one that ties the two subjects for those interested in dynamic systems.
Though the book does not have exercises, it contains good examples and an application chapter where algorithms in the book are compared. When discussing the applications, the author is also honest about the limitations of the new filters and detectors, and shows where the designer has to part with the theory. But this is a difficulty with robust control design too.
I also enjoyed reading the historical introduction to the subjects of filtering and detecion. The new additions that are not found in other books are well motivated.
An original, clear work on two subjects Apr 29, 2001
The book formulates the problem of optimal and robust fault detection in dynamic systems in a very logical and comprehensive way. It also provides a deterministic and stochastic interpretation of his formulation, and uses the two as needed in a very astute way.
Though originally a thesis, the chapters on robust estimation, the clear writing, and the added appendix on the Kalman filter, together qualify the monograph as a broad and excellent, though at times brief, book on detection and estimation in dynamic systems. The book assumes familiarity with probability, estimation and dynamic systems, and the writing is dense at certain points, but as a reader new to the subject, the engaging tone kept me from being intimidated. This is a welcome addition to the books available on these subjects.
A unique book that has depth and is a pleasure to read Feb 12, 2001
This is a unique monograph. It is probably one of the few books on model based and recursive estimation that covers more than Kalman filtering. It is of value to those familiar with Kalman filtering, and those who would like to be familiar with it. It starts with a historic introduction that clearly motivates the Wiener and Kalman filters as well as the more advanced minmax, risk sensitive or game theoretic filters that are robust to noise and system model uncertainties. In addition, the book connects these filter to classical and robust model based detection theory. For those new to Kalman filtering, an extensive appendix of thirty-some pages covers the subject a lot better than many books.
The relationships between all the topics is explained beautifully and the reader understands why he is being taught what he reads. The treatment of steady state filtering should be longer, though, but the author probably felt that detection is a transient phenomenon and chose to focus on that. The chapter on risk sensitivity could be developed further, however. Originally a thesis whose breakthrough contribution is the the use of robust filters in failure detection, the book is indeed serious and concise, sometimes too concise, but the writing is so eloquent that it never ceases to be a pleaure to read.