Artificial Intelligence Methods for Fault Diagnosis in Centrifugal Pumps

Cover
Half Title
Title Page
Copyright Page
Preface
Nomenclature
Acronyms
Table of Contents
Chapter 1: Technical Background on Centrifugal Pumps
	1.1 MOTIVATION
	1.2 AREAS OF LITERATURE REVIEW
	1.3 RESEARCH GAPS AND OBJECTIVES
	1.4 METHODOLOGY
	1.5 NOVEL CONTRIBUTIONS AND APPROACHES
	1.6 CONCLUSION
	REFERENCES
Chapter 2: Condition Monitoring and Pumps
	2.1 INTRODUCTION
	2.2 CONDITION MONITORING AND FAULT DIAGNOSIS
	2.3 PUMPS AND CENTRIFUGAL PUMPS
	2.4 CONVENTIONAL FAULT DETECTION TECHNIQUES
	2.5 ROTATING MACHINERY FAULT DETECTION
	2.6 CENTRIFUGAL PUMP FAULT DETECTION
	2.7 SIGNAL PROCESSING METHODS
	2.8 CONCLUSION
	TUTORIAL
	REFERENCES
Chapter 3: Artificial Intelligence Systems
	3.1 FEATURE EXTRACTION
	3.2 ARTIFICIAL INTELLIGENCE SCHEMES
	3.3 MULTILAYER PERCEPTRON WITH BACK PROPAGATION ARTIFICIAL NEURAL NETWORK
	3.4 RADIAL BASIS FUNCTION
	3.5 SUPPORT VECTOR MACHINE
	3.6 PROBABILISTIC NEURAL NETWORK
	3.7 APPLICATION OF ARTIFICIAL INTELLIGENCE SYSTEMS IN ROTATING MACHINERY FAULTS DIAGNOSIS
	3.8 APPLICATIONS OF ARTIFICIAL INTELLIGENCE IN FAULT DIAGNOSIS OF CENTRIFUGAL PUMP
	3.9 CONCLUSION
	TUTORIAL
	REFERENCES
Chapter 4: Genetic Algorithm
	4.1 BASIC CONCEPT OF GENETIC ALGORITHM
	4.2 GA AND GABP-ANN TRAINING METHODS
	4.3 APPLICATION AND COMPARISON OF GENETIC ALGORITHM SCHEMES
	4.4 CONCLUSION
	TUTORIAL
	REFERENCES
Chapter 5: Centrifugal Pump Vibration Measurement and Acquisition
	5.1 INTRODUCTION
	5.2 CENTRIFUGAL PUMP VIBRATION TEST AND ACQUISITION
	5.3 CENTRIFUGAL PUMP TEST SETUP INSTALLATION
	5.4 PUMP CONDITIONS (FAULT)
	5.5 VIBRATION MEASUREMENT AND ACQUISITION
	5.6 HEALTHY CONDITION
	5.7 MISALIGNMENT
	5.8 MECHANICAL LOOSENESS
	5.9 IMBALANCE
	5.10 IMPELLER DAMAGE
	5.11 BEARING FAULT
	5.12 CAVITATION
	5.13 CONCLUSION
	TUTORIAL
	REFERENCES
Chapter 6: Wavelet and Feature Extraction
	6.1 INTRODUCTION
	6.2 FEATURE NORMALIZATION
	6.3 FEATURE EXTRACTION USING CONTINUOUS WAVELET TRANSFORM (CWT)
	6.4 FEATURE EXTRACTION USING DISCRETE WAVELET TRANSFORM (DWT)
	6.5 FEATURE EXTRACTION USING WAVELET PACKET TRANSFORM (WPT)
	6.6 CONCLUSION
	TUTORIAL
	REFERENCES
Chapter 7: Centrifugal Pump Fault Diagnosis Using MLP and GA
	7.1 INTRODUCTION
	7.2 CLASSIFICATION METHOD
	7.3 CLASSIFICATION RESULTS
	7.4 CONCLUSION
	REFERENCES
Chapter 8: Centrifugal Pump Fault Detection Using SVM
	8.1 INTRODUCTION
	8.2 CLASSIFICATION METHODS
	8.3 CLASSIFICATION RESULTS
	8.4 CONCLUSION
	REFERENCES
Chapter 9: Fault Diagnosis Using MLP and SVM with DWT Based Feature Extraction
	9.1 INTRODUCTION
	9.2 GENETIC ALGORITHM TRAINING AND OPTIMIZATION ARCHITECTURE PARAMETERS
	9.3 EXPERIMENTAL SETUP FOR THE STUDY
	9.4 FEATURE EXTRACTION
	9.5 CLASSIFICATION METHODS
	9.6 PERFORMANCE OF THE SYSTEM
	9.7 CONCLUSION
	REFERENCES
Chapter 10: MLP-GABP and SVM with WPT Based Feature Extraction
	10.1 INTRODUCTION
	10.2 ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL SYSTEM
	10.3 EXPERIMENTAL SETUP
	10.4 FEATURE EXTRACTION
	10.5 CLASSIFICATION METHODS
	10.6 THE SYSTEM PERFORMANCE
	10.7 CONCLUSION
	REFERENCES
Chapter 11: Comparative Analysis of the Artificial Intelligence Schemes
	11.1 INTRODUCTION
	11.2 CLASSIFICATION BASED ON CWT
	11.3 CLASSIFICATION BASED ON DWT
	11.4 CLASSIFICATION BASED ON WPT
	11.5 CONCLUSION
	REFERENCES
Chapter 12: Applications of Neural Network in Rotor Misalignment and Unbalance Detection
	12.1 INTRODUCTION
	12.2 THEORY
	12.3 FEED-FORWARD MULTILAYER PERCEPTRON NETWORK
	12.4 EXPERIMENTAL SETUP
	12.5 RESULTS AND DISCUSSIONS
	12.6 CONCLUSIONS
	REFERENCES
Perspective
Appendix A
	Appendix B
Appendix C (Chapter 7 Figures)
Index