On-Board Design Models and Algorithm for Communication Based Train Control and Tracking System

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Acknowledgments
Authors
1 Vision of Intelligent Control and Tracking Rail System: Global Evident Data
	1.1 Introduction
	1.2 History of Train Control System Development
	1.3 Advanced Train Control System
		1.3.1 Positive Train Control System
		1.3.2 Communication-Based Train Control System (CBTCS)
		1.3.3 European Train Control System (ETCS)
		1.3.4 Chinese Train Control System (CTCS)
	1.4 Indian Train Tracking and Control System Scenario
		1.4.1 Auxiliary Warning System (AWS)
		1.4.2 Anti Collision Device (ACD)
		1.4.3 Train Collision Avoidance System (TCAS)
	1.5 Challenges in Current Train Tracking Model
2 Train Navigation Control and Information Management System
	2.1 Introduction
	2.2 Advance Train Control Solution
	2.3 GPS and Differential GPS-Based Tracking System
	2.4 Wireless Sensor-Based Tracking System
	2.5 Designing of Tracking Control Model and Data Information Algorithms
	2.6 Tracking Control Model Using Multi-Sensor Data Fusion
3 Hybrid System for Train Tracking and Monitoring Model
	3.1 GPS-Based Train Tracking Solution
	3.2 DGPS-Based Train Tracking Solution
		3.2.1 Selection Factor for DGPS-Based Tracking Solution
	3.3 Intelligent Railway Safety System with Radio Frequency Identification
		3.3.1 Advantages and Application of RFID
		3.3.2 Train Detection and Data Exchanging System
	3.4 Future with Wireless Sensor Network
		3.4.1 Real-Time Application Based WSN
		3.4.2 Mobile WSN Based Train Tracking Solution
	3.5 Positioning Rail Accurate Communication Highway Identification Model
4 Locomotive Tracking in Satellite Visible and Low Satellite Visible Area
	4.1 Introduction
	4.2 Kinematics Update State Hypotheses Information Surveillance Model
	4.3 Many Tracking Algorithms One Filter- The Future with Kalman Filter
		4.3.1 Why We Prefer Kalman Filter for Our Designing
		4.3.2 Designing Tree of DKF
		4.3.3 Theoretical Testing of Kalman Filter
	4.4 Modeling Assumption for DGPS Measurements Using Kalman Filter
		4.4.1 Kinematic Tracking State Model
		4.4.2 Parameter Measurement Coordinate Model
	4.5 Adopted Algorithm for Kalman Filter Model Testing
	4.6 Test Route Case Study
		4.6.1 Case 1: Position Identification of Moving Train Using Kalman Filter
		4.6.2 Case 2: Velocity Measurement of Moving Locomotive Using Kalman Filter
	4.7 WSN-RFID Based Tunnel Surveillance Integration Model
	4.8 Sensor Matching Control Algorithm for Di-Sensor Model
	4.9 Methodology to Analysis Sensor Matching Control Design for Train Tracking
	4.10 Train Tracking Problem Formulation
	4.11 Decision Logic for PI and Tracking Accuracy
	4.12 Quadratic Performance Control Problem Analysis Using Liapunov Method
		4.12.1 Case 1: For Optimal Control Input U (K) = -0.7913, Performance Index J = 0.5
		4.12.2 Case 2: For Optimal Control Input U (K) = -0.2087, Performance Index J = 1.8
		4.12.3 Train Tracking with Velocity and Position Error Estimation
5 Train Trajectory Optimization Based on Di-Filter Theory
	5.1 Introduction
	5.2 Optimal Differential Correction Solution for Standalone GPS
	5.3 Interacting Multiple Model (IMM) Algorithm for Di-Filter Model
	5.4 Stability Check Analysis for Di-Filter Model
	5.5 IMM Algorithm-Based Decision Logic Tree of Di-filter
		5.5.1 Case 1: Trajectory of Train Journey
		5.5.2 Case 2: Tracking Accuracy Estimation
		5.5.3 Case 3: Tracking Train Journey Probability Model Concept
		5.5.4 Case 4: Train Trajectory Errors Estimation
6 Heterogeneous Sensor Data Fusion DGPS-WSN-RFID-Based Train Tracking Model
	6.1 Introduction
	6.2 Research Road Map to Multi-Sensor Data Fusion Technology
	6.3 Architecture and Methodology Using Data Fusion Technique
	6.4 Architecture for DGPS-WSN-Based Data Fusion and Modeling Assumptions
	6.5 Decision Level Data Fusion Using Information Filter
7 Wireless Locomotive Real-Time Surveillance Model
	7.1 Introduction
	7.2 Probabilistic Detection Sensor Data Fusion Identification Model
	7.3 Bayes Theorem-Based Algorithm for Data Fusion
	7.4 Performance Analysis of DGPS-WSN-RFID-Based Model
		7.4.1 Case 1: R1 = r1 and r2 = r1 r2 r3
		7.4.2 Case 2: r1 = r2 and r2 = r1 r2 r3
		7.4.2 Case 3: r1 = r3 and r2 = r1 r2 r3
8 Predictive Analysis of Intelligent Rail Trip Detection Service Using Machine Learning
	8.1 Introduction
	8.2 Neural Networks Architecture
	8.3 Machine Learning Methods
		8.3.1 Supervised Learning
		8.3.2 Classification
		8.3.3 Line Regression
		8.3.4 Unsupervised Learning
		8.3.5 Clustering
	8.4 Processing of Data and Analysis
	8.5 Analysis of Data Set Using Recurrent Neural Network
Further Readings
Index