Update cookies preferences

E-book: Data-driven Design of Fault Diagnosis and Fault-tolerant Control Systems

4.00/5 (2 ratings by Goodreads)
Other books in subject:
  • Format - PDF+DRM
  • Price: 221,68 €*
  • * the price is final i.e. no additional discount will apply
  • Add to basket
  • Add to Wishlist
  • This ebook is for personal use only. E-Books are non-refundable.
Data-driven Design of Fault Diagnosis and Fault-tolerant Control SystemsLarger Image
Other books in subject:

DRM restrictions

  • Copying (copy/paste):

    not allowed

  • Printing:

    not allowed

  • Usage:

    Digital Rights Management (DRM)
    The publisher has supplied this book in encrypted form, which means that you need to install free software in order to unlock and read it.  To read this e-book you have to create Adobe ID More info here. Ebook can be read and downloaded up to 6 devices (single user with the same Adobe ID).

    Required software
    To read this ebook on a mobile device (phone or tablet) you'll need to install this free app: PocketBook Reader (iOS / Android)

    To download and read this eBook on a PC or Mac you need Adobe Digital Editions (This is a free app specially developed for eBooks. It's not the same as Adobe Reader, which you probably already have on your computer.)

    You can't read this ebook with Amazon Kindle

Data-driven Design of Fault Diagnosis and Fault-tolerant Control Systems presents basic statistical process monitoring, fault diagnosis, and control methods and introduces advanced data-driven schemes for the design of fault diagnosis and fault-tolerant control systems catering to the needs of dynamic industrial processes. With ever increasing demands for reliability, availability and safety in technical processes and assets, process monitoring and fault-tolerance have become important issues surrounding the design of automatic control systems. This text shows the reader how, thanks to the rapid development of information technology, key techniques of data-driven and statistical process monitoring and control can now become widely used in industrial practice to address these issues. To allow for self-contained study and facilitate implementation in real applications, important mathematical and control theoretical knowledge and tools are included in this book. Major schemes are presented in algorithm form and demonstrated on industrial case systems. Data-driven Design of Fault Diagnosis and Fault-tolerant Control Systems will be of interest to process and control engineers, engineering students and researchers with a control engineering background.
Part I Introduction, Basic Concepts and Preliminaries
1 Introduction
3(8)
1.1 Basic Concepts
3(2)
1.2 Motivation
5(2)
1.2.1 Data-Driven and Model-Based FDI
5(1)
1.2.2 Fault-Tolerant Control and Lifetime Management
5(1)
1.2.3 Information Infrastructure
6(1)
1.3 Outline of the Contents
7(2)
1.4 Notes and References
9(2)
References
10(1)
2 Case Study and Application Examples
11(12)
2.1 Three-Tank System
11(4)
2.1.1 Process Dynamics and Its Description
11(2)
2.1.2 Description of Typical Faults
13(1)
2.1.3 Closed-Loop Dynamics
14(1)
2.2 Continuous Stirred Tank Heater
15(2)
2.2.1 Plant Dynamics and Its Description
15(2)
2.2.2 Faults Under Consideration
17(1)
2.3 An Industrial Benchmark: Tennessee Eastman Process
17(4)
2.3.1 Process Description and Simulation
17(3)
2.3.2 Simulated Faults in TEP
20(1)
2.4 Notes and references
21(2)
References
21(2)
3 Basic Statistical Fault Detection Problems
23(26)
3.1 Some Elementary Concepts
23(3)
3.1.1 A Simple Detection Problem and Its Intuitive Solution
23(1)
3.1.2 Elementary Concepts in Fault Detection
24(2)
3.1.3 Problem Formulations
26(1)
3.2 Some Elementary Methods and Algorithms
26(5)
3.2.1 The Intuitive Solution
26(1)
3.2.2 T2 Test Statistic
27(1)
3.2.3 Likelihood Ratio and Generalized Likelihood Ratio
28(1)
3.2.4 Vector-Valued GLR
29(2)
3.3 The Data-Driven Solutions of the Detection Problem
31(5)
3.3.1 Fault Detection with a Sufficiently Large N
32(1)
3.3.2 Fault Detection Using Hotelling's T2 Test Statistic
33(2)
3.3.3 Fault Detection Using Q Statistic
35(1)
3.4 Case Example: Fault Detection in Three-Tank System
36(8)
3.4.1 System Setup and Simulation Parameters
36(1)
3.4.2 Training Results and Threshold Setting
37(2)
3.4.3 Fault Detection Results
39(5)
3.5 Variations of the Essential Fault Detection Problem
44(2)
3.5.1 Variation I
44(1)
3.5.2 Variation II
45(1)
3.6 Notes and References
46(3)
References
47(2)
4 Fault Detection in Processes with Deterministic Disturbances
49(24)
4.1 Problem Formulations and Some Elementary Concepts
49(4)
4.1.1 A Simple Detection Problem and Its Intuitive Solution
49(1)
4.1.2 Some Essential Concepts
50(2)
4.1.3 Problem Formulations
52(1)
4.2 Some Elementary Methods and Algorithms
53(7)
4.2.1 An Intuitive Strategy
53(1)
4.2.2 An Alternative Solution
54(2)
4.2.3 A Comparison Study
56(1)
4.2.4 Unknown Input Estimation Based Detection Scheme
57(1)
4.2.5 A General Solution
58(2)
4.3 A Data-Driven Solution of the Fault Detection Problem
60(2)
4.4 A Variation of the Essential Fault Detection Problem
62(2)
4.5 Case Study
64(4)
4.5.1 Case Study on Laboratory System CSTH
64(3)
4.5.2 Case Study on Three-Tank System
67(1)
4.6 Notes and References
68(5)
References
70(3)
Part II Application of Multivariate Analysis Methods to Fault Diagnosis in Static Processes
5 Application of Principal Component Analysis to Fault Diagnosis
73(22)
5.1 The Basic Application Form of PCA to Fault Detection
73(4)
5.1.1 Algorithms
74(1)
5.1.2 Basic Ideas and Properties
75(2)
5.2 The Modified Form of SPE: Hawkin's T2H Statistic
77(1)
5.3 Fault Sensitivity Analysis
78(3)
5.3.1 Sensitivity to the Off-set Faults
79(1)
5.3.2 Sensitivity to the Scaling Faults
80(1)
5.4 Multiple Statistical Indices and Combined Indices
81(3)
5.5 Dynamic PCA
84(1)
5.6 Fault Identification
84(3)
5.6.1 Identification of Off-set Faults
84(1)
5.6.2 Identification of Scaling Faults
85(1)
5.6.3 A Fault Identification Procedure
86(1)
5.7 Application to TEP
87(6)
5.7.1 Case Study on Fault Scenario 4
87(2)
5.7.2 Case Study Results for the Other Fault Scenarios
89(1)
5.7.3 Comparison of Multiple Indices with Combined Indices
90(3)
5.8 Notes and References
93(2)
References
93(2)
6 Application of Partial Least Squares Regression to Fault Diagnosis
95(22)
6.1 Partial Least Squares Algorithms
95(3)
6.2 On the PLS Regression Algorithms
98(5)
6.2.1 Basic Ideas and Properties
98(3)
6.2.2 Application to Fault Detection and Process Monitoring
101(2)
6.3 Relations Between LS and PLS
103(7)
6.3.1 LS Estimation
103(2)
6.3.2 LS Interpretation of the PLS Regression Algorithm
105(5)
6.4 Remarks on PLS Based Fault Diagnosis
110(1)
6.5 Case Study on TEP
111(5)
6.5.1 Test Setup
111(1)
6.5.2 Offline Training
111(1)
6.5.3 Online Running
111(5)
6.6 Notes and References
116(1)
References
116(1)
7 Canonical Variate Analysis Based Process Monitoring and Fault Diagnosis
117(18)
7.1 Introduction to CCA
117(2)
7.2 CVA-Based System Identification
119(4)
7.3 Applications to Process Monitoring and Fault Detection
123(3)
7.3.1 Process Monitoring
123(1)
7.3.2 Fault Detection Schemes
124(2)
7.4 Case Study: Application to TEP
126(2)
7.4.1 Test Setup and Training
126(1)
7.4.2 Test Results and a Comparison Study
127(1)
7.5 Notes and References
128(7)
References
131(4)
Part III Data-driven Design of Fault Diagnosis Systems for Dynamic Processes
8 Introduction, Preliminaries and I/O Data Set Models
135(18)
8.1 Introduction
135(1)
8.2 Preliminaries and Review of Model-Based FDI Schemes
136(12)
8.2.1 System Models
136(4)
8.2.2 Model-Based Residual Generation Schemes
140(8)
8.3 I/O Data Models
148(2)
8.4 Notes and References
150(3)
References
151(2)
9 Data-Driven Diagnosis Schemes
153(22)
9.1 Basic Concepts and Design Issues of Fault Diagnosis in Dynamic Processes
153(1)
9.2 Data-Driven Design Schemes of Residual Generators
154(8)
9.2.1 Scheme I
154(1)
9.2.2 Scheme II
155(2)
9.2.3 Scheme III
157(2)
9.2.4 A Numerically Reliable Realization Algorithm
159(2)
9.2.5 Comparison and Discussion
161(1)
9.3 Test Statistics, Threshold Settings and Fault Detection
162(1)
9.4 Fault Isolation and Identification Schemes
162(5)
9.4.1 Problem Formulation
163(2)
9.4.2 Fault Isolation Schemes
165(1)
9.4.3 Fault Identification Schemes
166(1)
9.5 Case Study: Fault Detection in Three-Tank System
167(5)
9.5.1 System and Test Setup
168(1)
9.5.2 Test Results
168(1)
9.5.3 Handling of Ill-Conditioning Σres
169(3)
9.6 Notes and References
172(3)
References
173(2)
10 Data-Driven Design of Observer-Based Fault Diagnosis Systems
175(28)
10.1 Motivation and Problem Formulation
175(1)
10.2 Parity Vectors Based Construction of Observer-Based Residual Generators
175(9)
10.2.1 Generation of a Scalar Residual Signal
176(2)
10.2.2 Generation of m-Dimensional Residual Vectors
178(4)
10.2.3 Data-Driven Design of Kalman Filter Based Residual Generators
182(2)
10.3 Fault Detection, Isolation and Identification
184(3)
10.3.1 On Fault Detection
184(1)
10.3.2 Fault Isolation Schemes
185(1)
10.3.3 A Fault Identification Scheme
186(1)
10.4 Observer-Based Process Monitoring
187(1)
10.5 Case Study on CSTH
188(6)
10.5.1 System Setup
188(1)
10.5.2 Towards the Kalman Filter-Based Residual Generator
189(1)
10.5.3 Towards the Generation of m-Dimensional Residual Vectors
190(4)
10.6 Case Study on TEP
194(3)
10.7 Remarks on the Application of the Data-Driven FDI Systems
197(1)
10.8 Notes and References
198(5)
References
199(4)
Part IV Adaptive and Iterative Optimization Techniques for Data-driven Fault Diagnosis
11 Adaptive Fault Diagnosis Schemes
203(20)
11.1 OI-based Recursive SVD Computation and Its Application
203(3)
11.1.1 Problem Formulation
204(1)
11.1.2 DPM: An Adaptive Algorithm
204(1)
11.1.3 Applications to Fault Detection
205(1)
11.2 An Adaptive SVD Algorithm and Its Applications
206(2)
11.2.1 The Adaptive SVD Algorithm
206(2)
11.2.2 Applications to Fault Detection
208(1)
11.3 Adaptive SKR Based Residual Generation Method
208(7)
11.3.1 Problem Formulation
209(1)
11.3.2 The Adaptive Residual Generation Algorithm
210(1)
11.3.3 Stability and Exponential Convergence
211(3)
11.3.4 An Extension to the Adaptive State Observer
214(1)
11.4 Case Studies
215(6)
11.4.1 Application of Adaptive SVD Based RPCA Scheme to Three-Tank System
215(3)
11.4.2 Application of the Adaptive Observer-Based Residual Generation Scheme to the Three-Tank System
218(3)
11.5 Notes and References
221(2)
References
222(1)
12 Iterative Optimization of Process Monitoring and Fault Detection Systems
223(24)
12.1 Iterative Generalized Least Squares Estimation
223(2)
12.2 Iterative RLS Estimation
225(6)
12.2.1 The Basic Idea and Approach
225(2)
12.2.2 Algorithm, its Realization and Implementation
227(1)
12.2.3 An Example
227(4)
12.3 Iterative Optimization of Kalman Filters
231(6)
12.3.1 The Idea and Scheme
231(4)
12.3.2 Algorithm and Implementation
235(1)
12.3.3 An Example
236(1)
12.4 Case Study
237(4)
12.4.1 Case 1: Σv is Unknown While Σw is Given
239(1)
12.4.2 Case 2: Σw is Unknown While Σv is Given
240(1)
12.5 Notes and References
241(6)
References
243(4)
Part V Data-driven Design and Lifetime Management of Fault-tolerant Control Systems
13 Fault-Tolerant Control Architecture and Design Issues
247(16)
13.1 Preliminaries
247(3)
13.1.1 Image Representation and State Feedback Control
248(1)
13.1.2 Parametrization of Stabilizing Controllers
249(1)
13.2 Fault-Tolerant Control Architecture and Relevant Issues
250(11)
13.2.1 An Observer-Based Fault-Tolerant Control Architecture
250(2)
13.2.2 Design and Optimal Settings
252(3)
13.2.3 A Residual-Based Fault-Tolerant and Lifetime Management Structure
255(2)
13.2.4 System Dynamics and Design Parameters
257(4)
13.3 Notes and References
261(2)
References
262(1)
14 Data-Driven Design of Observer-Based Control Systems
263(18)
14.1 Problem Formulation
263(1)
14.2 Data-Driven Realization Form of the Image Representation
264(2)
14.3 An Identification Scheme for the Image Representation
266(5)
14.3.1 A Brief Review of the I/O Data Set Model and Relevant Issues
266(1)
14.3.2 The Identification Scheme
266(5)
14.4 A data-Driven Design Scheme of Observer-Based Control Systems
271(3)
14.4.1 Data-Driven Design of Feed-Forward Controller
271(1)
14.4.2 Observer-Based State Feedback Controller Design
272(2)
14.5 Concluding Remarks
274(1)
14.6 Experimental Study on Laboratory CSTH System
275(2)
14.6.1 System Setup and Process Measurements
275(1)
14.6.2 Towards the Observer-Based Controller Design
275(1)
14.6.3 Towards the Fault-Tolerant Control Scheme
276(1)
14.7 Notes and References
277(4)
References
279(2)
15 Realization of Lifetime Management of Automatic Control Systems
281(18)
15.1 Adaptive Update of H-PRIO Parameters
281(6)
15.1.1 Problem Formulation
282(1)
15.1.2 Basic Idea
283(1)
15.1.3 The Adaptive Scheme
284(2)
15.1.4 Realization of the Adaptive Scheme
286(1)
15.2 Iterative Update of L-PRIO Parameters
287(3)
15.2.1 Problem Formulation
287(2)
15.2.2 Iterative Solution Algorithm
289(1)
15.3 Implementation of the Lifetime Management Strategy
290(6)
15.3.1 A General Description
290(1)
15.3.2 Case Study on Three-Tank System
291(5)
15.4 Notes and References
296(3)
References
297(2)
Index 299
In 1986, Steven X. Ding begun with the Ph D study/investigation on model-based FDI isusses. During his three years stay in industry, he had gained experiences with the applications of FDI techniques in real technical processes. In the last 17 years, he has been, as a university professor and institute head, involved in numerous national and international research grants and industrial projects in developing advanced FDI methods and their applications in different industrial sectors. He holds a lecture on fault diagnosis and fault-tolerant systems for master students and seminars on advanced FDI methods for PhD students at the University Duisburg-Essen and gives guest lectures/courses at other universities and research institutes. He has published more than 80 journal and 130 conference papers in this thematic area.
More information about ebooks More information about ebooks
Permanent link: https://www.kriso.ee/db/97814471641042e.html
Keywords: