Intro
Preface
Acknowledgements
Contents
1 Background and Health Problems of Pipelines
1.1 Introduction
1.2 Pipeline Classification and Construction Status
1.3 Pipeline Health Status Globally
1.4 Pipeline Inspection Technology System
1.5 Technical System of Pipeline Health Monitoring
1.6 Global Pipeline Inspection and Monitoring Standards and Specifications
References
2 Pipeline Inspection Technology
2.1 Introduction
2.2 Visual Inspection Technology
2.3 Electromagnetic Inspection Technology
2.3.1 Magnetic Flux Leakage

2.3.2 Remote Field Eddy Current
2.3.3 Broadband Electromagnetic
2.3.4 Pulsed Eddy Current System
2.3.5 Ground Penetrating Radar
2.4 Acoustic Inspection Technology
2.4.1 Acoustic Emission Method
2.4.2 Ultrasonic Method
2.4.3 Ultrasonic Guided Wave Method
2.4.4 Echo Impact
2.4.5 SmartBall
2.4.6 Sonar System Method
2.4.7 Leakfinder
2.4.8 Sahara
2.5 Optical Inspection Technology
2.5.1 Lidar System
2.5.2 Diode Laser Absorption Method
2.5.3 Thermal Imaging
2.5.4 Spectral Imaging Method
2.6 Chemical Composition Analysis-Based Method

2.6.1 Sniffer Method
2.6.2 Vapor Sampling Method
2.7 Technology Selection Considerations
References
3 Pipeline Health Monitoring Technology
3.1 Introduction
3.2 Optical Fiber Sensing
3.2.1 Optical Time Domain Reflection (OTDR)
3.2.2 Fiber Bragg Grating (FBG)
3.2.3 Interferometric Optical Fiber Sensor
3.3 Signal-Based Method
3.3.1 Volume/Mass Balance Method
3.3.2 Negative Pressure Wave Method
3.3.3 GPS Time Label Method
3.3.4 Pressure Point Analysis Method
3.3.5 Cross Correlation Analysis
3.3.6 Transient Test-Based Technique

3.3.7 State Estimation Method
3.4 Technology Selection Considerations
References
4 Health Monitoring Technology Based on Artificial Intelligence
4.1 Introduction
4.2 Classic Models
4.2.1 Linear Regression
4.2.2 Naive Bayes
4.2.3 Artificial Neural Network
4.2.4 Kernel-Based Model
4.2.5 Decision Tree Method
4.2.6 Deep Learning
4.3 Optimizers
4.3.1 Fruit Fly Optimizer
4.3.2 Grey Wolf Optimizer
4.3.3 Whale Optimization Algorithm
4.3.4 Nondominated Sorting Genetic Algorithm II
4.3.5 Multi-objective Grey Wolf Optimizer

4.3.6 Multi-objective Salp Swarm Algorithm
4.4 Application Scenarios
4.4.1 Fault Diagnosis
4.4.2 Risk Prediction
4.4.3 Condition-Related Parameter Prediction
4.4.4 Visual Defect Recognition
4.5 Application Summary
4.5.1 Model Category
4.5.2 Model Framework
4.5.3 Data Size and Data Division
4.5.4 Input Variable
4.5.5 Error (Accuracy) Indicator
4.5.6 Real-World Applications
4.6 Specific Applications
4.6.1 Burst Pressure Prediction [236]
4.6.2 Pullback Force Prediction [229]
References
5 Data Preprocessing Technology in Pipeline Health Monitoring