Atjaunināt sīkdatņu piekrišanu

Equipment Health Monitoring in Complex Systems [Hardback]

5.00/5 (2 ratings by Goodreads)
, , ,
  • Formāts: Hardback, 250 pages
  • Izdošanas datums: 31-Oct-2017
  • Izdevniecība: Artech House Publishers
  • ISBN-10: 1608079724
  • ISBN-13: 9781608079728
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 147,05 €
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
Equipment Health Monitoring in Complex SystemsPalielināt
  • Formāts: Hardback, 250 pages
  • Izdošanas datums: 31-Oct-2017
  • Izdevniecība: Artech House Publishers
  • ISBN-10: 1608079724
  • ISBN-13: 9781608079728
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9781608079728.html
Keywords:
This book is a practical introduction to the safe operation and control of critical systems in defense, industrial, and healthcare applications. It highlights system engineering processes and presents an overview of the equipment health monitoring (EHM) functional architecture and algorithm design. The book also explores machine learning functions, such as feature extraction, data visualization and model boundaries.

The need for intelligent diagnostics and proposed health monitoring framework is increasingly important within sensing technology, big data analytics and grid capabilities. This resource, packed with case studies from industrial and healthcare settings, identifies key problems along with various techniques that address the current issues as well as future developments in the field. A MATLAB code is included to assist engineers with projects in the field.
Acknowledgments ix
1 Introduction
1(14)
1.1 Maintenance Strategies
1(5)
1.2 Overview of Health Monitoring
6(6)
1.3 Organization of Book Contents
12(3)
References
13(2)
2 Systems Engineering for EHM
15(56)
2.1 Introduction
15(1)
2.2 Introduction to Systems Engineering
16(7)
2.2.1 Systems Engineering Processes
17(3)
2.2.2 Overview of Systems Engineering for EHM Design
20(3)
2.2.3 Summary
23(1)
2.3 EHM Design Intent
23(15)
2.3.1 State the Problem: Failure Analysis and Management
23(3)
2.3.2 Model the System: Approaches for Failure Modeling
26(3)
2.3.3 Investigate Alternatives: Failure Models
29(5)
2.3.4 Assess Performance: Case Study
34(4)
2.4 EHM Functional Architecture Design
38(12)
2.4.1 State the Problem: EHM Functional Architecture Design
38(3)
2.4.2 Model the System: Function Modeling and Assessment
41(2)
2.4.3 Investigate Alternatives: Tools for Functional Architecture Design
43(5)
2.4.4 Assess Performance: Gas Turbine EHM Architecture Optimization
48(2)
2.5 EHM Algorithm Design
50(17)
2.5.1 State the Problem: Monitoring Algorithm Design Process
51(2)
2.5.2 Model the System: Detailed Fault Mode Modeling
53(4)
2.5.3 Investigate Alternatives: Development Approaches
57(6)
2.5.4 Assess Performance: Algorithm Design Case Study
63(4)
2.6 Conclusion
67(4)
References
68(3)
3 The Need for Intelligent Diagnostics
71(22)
3.1 Introduction
71(3)
3.2 The Need for Intelligent Diagnostics
74(4)
3.3 Overview of Machine Learning Capability
78(2)
3.4 Proposed Health Monitoring Framework
80(13)
3.4.1 Feature Extraction
81(2)
3.4.2 Data Visualization
83(6)
3.4.3 Model Construction
89(1)
3.4.4 Definition of Model Boundaries
90(1)
3.4.5 Verification of Model Performance
91(1)
References
91(2)
4 Machine Learning for Health Monitoring
93(32)
4.1 Introduction
93(1)
4.2 Feature Extraction
94(1)
4.3 Data Visualization
95(9)
4.3.1 Principal Component Analysis
96(2)
4.3.2 Kohonen Network
98(2)
4.3.3 Sammon's Mapping
100(3)
4.3.4 NeuroScale
103(1)
4.4 Model Construction
104(8)
4.5 Definition of Model Boundaries
112(3)
4.6 Verification of Model Performance
115(10)
4.6.1 Verification of Regression Models
115(2)
4.6.2 Verification of Classification Models
117(5)
References
122(3)
5 Case Studies of Medical Monitoring Systems
125(24)
5.1 Introduction
125(1)
5.2 Kernel Density Estimates
126(5)
5.3 Extreme Value Statistics
131(11)
5.3.1 Type-I EVT
132(4)
5.3.2 Type-II EVT
136(2)
5.3.3 Gaussian Processes
138(4)
5.4 Advanced Methods
142(7)
References
6 Monitoring Aircraft Engines
149(28)
6.1 Introduction
149(3)
6.1.1 Aircraft Engines
149(2)
6.1.2 Model-Based Monitoring Systems
151(1)
6.2 Case Study
152(4)
6.2.1 Aircraft Engine Air System Event Detection
152(1)
6.2.2 Data and the Detection Problem
153(3)
6.3 Kalman Filter-Based Detection
156(9)
6.3.1 Kalman Filter Estimation
156(3)
6.3.2 Kalman Filter Parameter Design
159(4)
6.3.3 Change Detection and Threshold Selection
163(2)
6.4 Multiple Model-Based Detection
165(6)
6.4.1 Hypothesis Testing and Change Detection
165(2)
6.4.2 Multiple Model Change Detection
167(4)
6.5 Change Detection with Additional Signals
171(3)
6.6 Summary
174(3)
References
174(3)
7 Future Directions in Health Monitoring
177(26)
7.1 Introduction
177(2)
7.2 Emerging Developments Within Sensing Technology
179(7)
7.2.1 Low-Cost and Ubiquitous Sensing
180(4)
7.2.2 Ultra-Minaturization---Nano and Quantum
184(1)
7.2.3 Bio-Inspired
185(1)
7.2.4 Summary
186(1)
7.3 Sensor Informatics for Medical Monitoring
186(4)
7.3.1 Deep Learning for Patient Monitoring
188(2)
7.4 Big Data Analytics and Health Monitoring
190(1)
7.5 Growth in Use of Digital Storage
190(13)
7.5.1 Example Health Monitoring Application Utilizing Grid Capability
192(6)
7.5.2 Cloud Alternatives
198(3)
References
201(2)
About the Authors 203(2)
Index 205
Stephen King is an engineering associate fellow and equipment health management specialist at Rolls-Royce Digital Business. He is also a visiting professor at Cranfield University. He received his Ph.D. in Mathematics and Computer Science from Lancaster University. Andrew Mills is a senior research fellow and program manager for the Rolls-Royce University Technology Center. He received his Ph.D. and M.Eng. in control system engineering from the University of Sheffield. Visakan Kadirkamanathan is a professor of signal and information processing at Cambridge University. He is also the director of the Rolls-Royce University Technology Center for Control and Monitoring Systems Engineering at Sheffield University. He received his Ph.D. in information engineering and his B.A. in electrical and information sciences at Cambridge University. Dave Clifton is an associate professor in the Department of Engineering Science at the University of Oxford and a governing body fellow of Balliol College, Oxford. He is a research fello of the Royal Academy of Engineering and leads the Computational Health Informatics (CHI) laboratory. He received his Ph.D. in information engineering at the University of Oxford