Robust Estimation and Failure Detection: A Concise Treatment

ISBN-13: 9781447115885 / Angielski / Miękka / 2012 / 222 str.

Rami S. Mangoubi

Opis

The series Advances in Industrial Control aims to report and encourage technology transfer in control engineering. The rapid development of control technology impacts all areas of the control discipline. New theory, new controllers, actuators, sensors, new industrial processes, computer methods, new applications, new philosophies ..., new challenges. Much of this development work resides in industrial reports, feasibility study papers and the reports of advanced collaborative projects. The series offers an opportunity for researchers to present an extended exposition of such new work in all aspects of industrial control for wider and rapid dissemination. This monograph brings together two of the most exciting areas of advanced signal processing and control. The first involves the development of optimal estimators for uncertain signal and noise models. The second is the subject of failure detection and isolation, which has considerable potential in a range of applications. The text provides a gradual build-up of ideas moving from traditional Wiener and Kalman fIltering to risk sensitive control and estimation problems.

Recenzje

From the reviews:
"The book provides a novel solution of a class of robust estimation problems and includes convincing application studies. ... The material presented in the book is accessible to the novice in both filtering and detection theory. ... The chapters of the book are very well- structured, presented with clarity, and the reader's understanding is helped with some examples. ... I strongly recommend it to researchers and practitioners in the field of estimation and failure detection, who will certainly find this book an important reference." (Theodor- Dan Popescu, Studies in Informatics and Control, Vol. 8 (2), 1999)

Spis treści

1 Introduction.- 2 Estimation and Failure Detection: An Overview.- 2.1 Introduction.- 2.2 Ever Since Wiener.- 2.2.1 Wiener and Kalman Filters.- 2.2.2 Beyond Linear Least Squares Estimation.- 2.2.3 Kalman Filter and Model Uncertainties.- 2.2.4 Robust Estimation and the Small Gain Theorem.- 2.2.5 Robust Stability and Robust Performance for Estimation.- 2.2.6 Further Discussion on Robust Estimation and Control.- 2.2.7 Risk Sensitive Control and Estimation.- 2.3 Failure Detection and Isolation.- 2.3.1 Kalman Filters in FDI Algorithms: The GLUT.- 2.3.2 Nonadditive Failures.- 2.3.3 Modeling Uncertainties and FDI Algorithms.- 2.3.4 Robust Failure Detection and Isolation.- 2.4 Summary.- 3 Discrete-Time Robust Estimation.- 3.1 Introduction.- 3.2 Plants with an Uncertain Noise Model.- 3.2.1 Problem Formulation.- 3.2.2 Derivation of the Estimator.- 3.2.3 Estimator Properties.- 3.2.4 Estimator Equations and Discussion.- 3.3 Plants with Uncertain Dynamics and Noise Model.- 3.3.1 Problem Formulation.- 3.3.2 Derivation of the Estimator.- 3.3.3 Robust Estimator Equations and Discussion.- 3.4 Extension to Steady State.- 3.5 Robust Fixed-Interval Smoothing.- 3.6 Numerical Examples.- 3.6.1 A Two-State System.- 3.6.2 Attitude Determination.- 3.7 Related Work.- 4 Stochastic Interpretation of Robust Estimation: Risk Sensitivity.- 4.1 Introduction.- 4.2 The Risk Sensitive Optimal Estimation Problem.- 4.2.1 Problem Formulation.- 4.2.2 Equivalence to Game Theoretic Estimation.- 4.3 Extension to Systems with Modeling Uncertainty.- 4.4 Numerical Comparison of Error Density Functions.- 4.5 Summary.- 5 Robust Failure Detection and Isolation.- 5.1 Introduction.- 5.2 Problem Description.- 5.2.1 General Discussion and Notation.- 5.2.2 Problem Formulation.- 5.2.3 The Failure Model.- 5.3 A Likelihood Ratio Test with Robustness Properties.- 5.4 Likelihood Ratio Tests and Plant Uncertainties.- 5.4.1 Examples: Underwater Vehicle with Model Uncertainty.- 5.5 FDI with Robustness to Failure Mode, Noise and Plant Uncertainties.- 5.5.1 The Decision Function.- 5.5.2 Robust Estimator Design.- 5.5.3 Summary of the Algorithm.- 5.6 Summary.- 6 Two Applications.- 6.1 Introduction.- 6.2 Application to an Underwater Vehicle.- 6.2.1 Straight and Level Cruise.- 6.2.2 Maneuvers.- 6.3 Application to Reentry Vehicle attitude Control Systems.- 6.3.1 Problem Description.- 6.3.2 Robust FDI Filter Architecture.- 6.3.3 Results.- 6.3.4 Summary.- A The Kalman Filter.- A.1 Problem Description.- A.2 The One-Step Predictor.- A.3 Measurement Update and the Filtered Estimate.- A.4 Gaussian Disturbance.- A.5 The Innovation Process.- A.6 Linear Time-Invariant Systems.- A.7 The Wiener Filter.- A.8 Smoothing.- A.8.1 Fixed-Interval Smoothing.- A.8.2 Fixed-Point and Fixed-Lag Smoothing.- A.9 The Extended Kaiman Filter (EKF).- A.10 Summary of Equations and Additional Remarks.- B Outputs of Linear Systems and Their Quadratic Forms.- B.1 Moments of Linear Systems Outputs.- B.2 Probability Density Functions of Gaussian Quadratic Forms.- C Continuous-Time Robust Estimation.- C.1 Introduction.- C.2 Problem Formulation.- C.3 Derivation of the Estimator.- C.4 Related Work.- D Application Data.- D.1 Underwater Vehicle Application.- D.1.1 The Plant.- D.1.2 Description of Robust Filter Design.- D.2 Reentry Vehicle Application.- D.2.1 The Plant.- D.2.2 The Filters.