Process control system fault diagnosis : a Bayesian approach / Ruben Gonzalez, Fei Qi, Biao Huang
- Author
- Gonzalez, Ruben, 1985-
- Published
- Chichester, West Sussex, United Kingdom : John Wiley & Sons, 2016.
- Edition
- First edition.
- Physical Description
- 1 online resource
- Additional Creators
- Huang, Biao, 1962- and Qi, Fei, 1983-
Access Online
- Contents
- Machine generated contents note: 1.Introduction -- 1.1.Motivational Illustrations -- 1.2.Previous Work -- 1.2.1.Diagnosis Techniques -- 1.2.2.Monitoring Techniques -- 1.3.Book Outline -- 1.3.1.Problem Overview and Illustrative Example -- 1.3.2.Overview of Proposed Work -- References -- 2.Prerequisite Fundamentals -- 2.1.Introduction -- 2.2.Bayesian Inference and Parameter Estimation -- 2.2.1.Tutorial on Bayesian Inference -- 2.2.2.Tutorial on Bayesian Inference with Time Dependency -- 2.2.3.Bayesian Inference vs. Direct Inference -- 2.2.4.Tutorial on Bayesian Parameter Estimation -- 2.3.The EM Algorithm -- 2.4.Techniques for Ambiguous Modes -- 2.4.1.Tutorial on Θ Parameters in the Presence of Ambiguous Modes -- 2.4.2.Tutorial on Probabilities Using Θ Parameters -- 2.4.3.Dempster[—]Shafer Theory -- 2.5.Kernel Density Estimation -- 2.5.1.From Histograms to Kernel Density Estimates -- 2.5.2.Bandwidth Selection -- 2.5.3.Kernel Density Estimation Tutorial -- 2.6.Bootstrapping -- 2.6.1.Bootstrapping Tutorial -- 2.6.2.Smoothed Bootstrapping Tutorial -- 2.7.Notes and References -- References -- 3.Bayesian Diagnosis -- 3.1.Introduction -- 3.2.Bayesian Approach for Control Loop Diagnosis -- 3.2.1.Mode M -- 3.2.2.Evidence E -- 3.2.3.Historical Dataset D -- 3.3.Likelihood Estimation -- 3.4.Notes and References -- References -- 4.Accounting for Autodependent Modes and Evidence -- 4.1.Introduction -- 4.2.Temporally Dependent Evidence -- 4.2.1.Evidence Dependence -- 4.2.2.Estimation of Evidence-transition Probability -- 4.2.3.Issues in Estimating Dependence in Evidence -- 4.3.Temporally Dependent Modes -- 4.3.1.Mode Dependence -- 4.3.2.Estimating Mode Transition Probabilities -- 4.4.Dependent Modes and Evidence -- 4.5.Notes and References -- References -- 5.Accounting for Incomplete Discrete Evidence -- 5.1.Introduction -- 5.2.The Incomplete Evidence Problem -- 5.3.Diagnosis with Incomplete Evidence -- 5.3.1.Single Missing Pattern Problem -- 5.3.2.Multiple Missing Pattern Problem -- 5.3.3.Limitations of the Single and Multiple Missing Pattern Solutions -- 5.4.Notes and References -- References -- 6.Accounting for Ambiguous Modes: A Bayesian Approach -- 6.1.Introduction -- 6.2.Parametrization of Likelihood Given Ambiguous Modes -- 6.2.1.Interpretation of Proportion Parameters -- 6.2.2.Parametrizing Likelihoods -- 6.2.3.Informed Estimates of Likelihoods -- 6.3.Fagin[—]Halpern Combination -- 6.4.Second-order Approximation -- 6.4.1.Consistency of Θ Parameters -- 6.4.2.Obtaining a Second-order Approximation -- 6.4.3.The Second-order Bayesian Combination Rule -- 6.5.Brief Comparison of Combination Methods -- 6.6.Applying the Second-order Rule Dynamically -- 6.6.1.Unambiguous Dynamic Solution -- 6.6.2.The Second-order Dynamic Solution -- 6.7.Making a Diagnosis -- 6.7.1.Simple Diagnosis -- 6.7.2.Ranged Diagnosis -- 6.7.3.Expected Value Diagnosis -- 6.8.Notes and References -- References -- 7.Accounting for Ambiguous Modes: A Dempster[—]Shafer Approach -- 7.1.Introduction -- 7.2.Dempster[—]Shafer Theory -- 7.2.1.Basic Belief Assignments -- 7.2.2.Probability Boundaries -- 7.2.3.Dempster's Rule of Combination -- 7.2.4.Short-cut Combination for Unambiguous Priors -- 7.3.Generalizing Dempster[—]Shafer Theory -- 7.3.1.Motivation: Difficulties with BBAs -- 7.3.2.Generalizing the BBA -- 7.3.3.Generalizing Dempster's Rule -- 7.3.4.Short-cut Combination for Unambiguous Priors -- 7.4.Notes and References -- References -- 8.Making Use of Continuous Evidence Through Kernel Density Estimation -- 8.1.Introduction -- 8.2.Performance: Continuous vs. Discrete Methods -- 8.2.1.Average False Negative Diagnosis Criterion -- 8.2.2.Performance of Discrete and Continuous Methods -- 8.3.Kernel Density Estimation -- 8.3.1.From Histograms to Kernel Density Estimates -- 8.3.2.Defining a Kernel Density Estimate -- 8.3.3.Bandwidth Selection Criterion -- 8.3.4.Bandwidth Selection Techniques -- 8.4.Dimension Reduction -- 8.4.1.Independence Assumptions -- 8.4.2.Principal and Independent Component Analysis -- 8.5.Missing Values -- 8.5.1.Kernel Density Regression -- 8.5.2.Applying Kernel Density Regression for a Solution -- 8.6.Dynamic Evidence -- 8.7.Notes and References -- References -- 9.Accounting for Sparse Data Within a Mode -- 9.1.Introduction -- 9.2.Analytical Estimation of the Monitor Output Distribution Function -- 9.2.1.Control Performance Monitor -- 9.2.2.Process Model Monitor -- 9.2.3.Sensor Bias Monitor -- 9.3.Bootstrap Approach to Estimating Monitor Output Distribution Function -- 9.3.1.Valve Stiction Identification -- 9.3.2.The Bootstrap Method -- 9.3.3.Illustrative Example -- 9.3.4.Applications -- 9.4.Experimental Example -- 9.4.1.Process Description -- 9.4.2.Diagnostic Settings and Results -- 9.5.Notes and References -- References -- 10.Accounting for Sparse Modes Within the Data -- 10.1.Introduction -- 10.2.Approaches and Algorithms -- 10.2.1.Approach for Component Diagnosis -- 10.2.2.Approach for Bootstrapping New Modes -- 10.3.Illustration -- 10.3.1.Component-based Diagnosis -- 10.3.2.Bootstrapping for Additional Modes -- 10.4.Application -- 10.4.1.Monitor Selection -- 10.4.2.Component Diagnosis -- 10.5.Notes and References -- References -- 11.Introduction to Testbed Systems -- 11.1.Simulated System -- 11.1.1.Monitor Design -- 11.2.Bench-scale System -- 11.3.Industrial Scale System -- References -- 12.Bayesian Diagnosis with Discrete Data -- 12.1.Introduction -- 12.2.Algorithm -- 12.3.Tutorial -- 12.4.Simulated Case -- 12.5.Bench-scale Case -- 12.6.Industrial-scale Case -- 12.7.Notes and References -- References -- 13.Accounting for Autodependent Modes and Evidence -- 13.1.Introduction -- 13.2.Algorithms -- 13.2.1.Evidence Transition Probability -- 13.2.2.Mode Transition Probability -- 13.3.Tutorial -- 13.4.Notes and References -- References -- 14.Accounting for Incomplete Discrete Evidence -- 14.1.Introduction -- 14.2.Algorithm -- 14.2.1.Single Missing Pattern Problem -- 14.2.2.Multiple Missing Pattern Problem -- 14.3.Tutorial -- 14.4.Simulated Case -- 14.5.Bench-scale Case -- 14.6.Industrial-scale Case -- 14.7.Notes and References -- References -- 15.Accounting for Ambiguous Modes in Historical Data: A Bayesian Approach -- 15.1.Introduction -- 15.2.Algorithm -- 15.2.1.Formulating the Problem -- 15.2.2.Second-order Taylor Series Approximation of p(E and Contents note continued: 18.7.Industrial-scale Case -- 18.8.Notes and References -- References.
- Summary
- Process Control System Fault Diagnosis: A Bayesian Approach Ruben T. Gonzalez, University of Alberta, Canada Fei Qi, Suncor Energy Inc., Canada Biao Huang, University of Alberta, Canada Data-driven Inferential Solutions for Control System Fault Diagnosis A typical modern process system consists of hundreds or even thousands of control loops, which are overwhelming for plant personnel to monitor. The main objectives of this book are to establish a new framework for control system fault diagnosis, to synthesize observations of different monitors with a prior knowledge, and to pinpoint possible abnormal sources on the basis of Bayesian theory. Process Control System Fault Diagnosis: A Bayesian Approach consolidates results developed by the authors, along with the fundamentals, and presents them in a systematic way. The book provides a comprehensive coverage of various Bayesian methods for control system fault diagnosis, along with a detailed tutorial. The book is useful for graduate students and researchers as a monograph and as a reference for state-of-the-art techniques in control system performance monitoring and fault diagnosis. Since several self-contained practical examples are included in the book, it also provides a place for practicing engineers to look for solutions to their daily monitoring and diagnosis problems. Key features: - A comprehensive coverage of Bayesian Inference for control system fault diagnosis. - Theory and applications are self-contained. - Provides detailed algorithms and sample Matlab codes. - Theory is illustrated through benchmark simulation examples, pilot-scale experiments and industrial application. Process Control System Fault Diagnosis: A Bayesian Approach is a comprehensive guide for graduate students, practicing engineers, and researchers who are interests in applying theory to practice.
- Subject(s)
- ISBN
- 1118770587 (electronic bk.)
1118770595 (epub)
9781118770580 (electronic bk.)
9781118770597 (epub)
1118770617
9781118770610 - Bibliography Note
- Includes bibliographical references and index.
View MARC record | catkey: 19515783