Application of Signal Processing Tools and Artificial Neural Network in Diagnosis of Power System Faults

Cover
Half Title
Title Page
Copyright Page
Table of Contents
Authors
Introduction
	References
Chapter 1: Power System Faults
	1.1 Introduction
	1.2 Types of Faults and Their Analysis Using Conventional Techniques
	1.3 Application of Soft Computing in Fault Analysis
	1.4 Comparison of Conventional Techniques with Soft Computing
	1.5 Summary
	References
Chapter 2: Wavelet Transform
	2.1 Introduction
	2.2 Brief Survey of Literature
	2.3 Application of FT and STFT in Stationary and Non-Stationary Signals
	2.4 Continuous Wavelet Transform (CWT)
		2.4.1 Evolution of CWT from STFT
	2.5 Application of CWT in Signal Processing Using MATLAB
	2.6 Discrete Wavelet Transform (DWT)
	2.7 Conclusion
	References
Chapter 3: Stockwell Transform
	3.1 Introduction
	3.2 Fast Fourier Transform (FFT), STFT, and WT
		3.2.1 FFT and STFT
		3.2.2 Wavelet Transform (WT)
	3.3 Theory of Stockwell Transform (ST)
		3.3.1 Derivation of ST from Modification of STFT
		3.3.2 Derivation of ST from Modification of CWT
	3.4 Discrete S-Transform (DST)
	3.5 Properties of ST
	3.6 Comparison of ST with CWT
	3.7 Summary
	References
Chapter 4: Application of ST for Time Frequency Representations (TFRs) of Different Electrical Signals
	4.1 Introduction
	4.2 Signal Extraction from a Time Series
		4.2.1 Non-Sinusoidal Waveform Whose Equation Is Known
		4.2.2 Harmonic Analysis of the Inrush Current Waveform of a Saturated Transformer
	4.3 Comparison among FFT, DWT, and DST
		4.3.1 Stationary Signal
		4.3.2 Non-Stationary Signal
	4.4 Effect of Noise
		4.4.1 Effect of Noise on a Pure Non-Sinusoidal Stationary Signal
		4.4.2 Effect of Noise on a Pure Non-Stationary Signal
	4.5 Conclusion
	References
Chapter 5: Neural Network
	5.1 Introduction
	5.2 Mathematical Model of a Neuron
	5.3 Network Architectures
	5.4 Learning Processes
	5.5 Back Propagation Algorithm
		5.5.1 Learning Process
		5.5.2 Training Algorithms
	5.6 Probabilistic Neural Network
	5.7 Conclusion
	References
Chapter 6: Fault Analysis in Single-Circuit Transmission Line Using S-Transform and Neural Network
	6.1 Introduction
	6.2 Feature Extraction by S-Transform
	6.3 Power System under Study
	6.4 PNN-Based Fault Classification
	6.5 Results of Simulation and PNN Classifier
	6.6 Effect of Noise on Fault Diagnosis
	6.7 Fault Location Estimation by BPNN
	6.8 Conclusion
	6.9 Future Work for Implementation
	References
Chapter 7: Fault Analysis in an Unbalanced and a Multiterminal System Using ST and Neural Network
	7.1 Introduction
	7.2 Feature Extraction by S-Transform
	7.3 Fault Classification in an Unbalanced Power System Network
		7.3.1 Simulation of Unbalanced System
		7.3.2 PNN Based Fault Classification
		7.3.3 Results of Simulation and PNN Classifier
		7.3.4 Effect of Noise
		7.3.5 Fault Location Estimation by BPNN
	7.4 Application of the Proposed Method in a Practical System
		7.4.1 Identification of Faulty Line Segment
		7.4.2 Determination of Exact Fault Location
	7.5 Conclusion
	References
Chapter 8: Application of ST for Fault Analysis in a HVDC System
	8.1 Introduction
	8.2 Simulation of the HVDC System and Faults for the Study
	8.3 Fault Classification and Determination of Fault Location
		8.3.1 Effect of Noise in Fault Analysis
	8.4 Conclusion
	References
Chapter 9: Conclusion and Extension of Future Research Work
	9.1 Conclusion
	9.2 Future Work
Index
	A
	B
	C
	D
	E
	F
	G
	H
	I
	L
	M
	N
	P
	R
	S
	T
	U
	W