Get Thesis Now !

PROJECT TOPIC: FAULT DETECTION ON POWER DISTRIBUTION LINE USING ARTIFICIAL NEURAL NETWORK AND FUZZY LOGIC (A CASE STUDY OF BORI DISTRIBUTION NETWORK)
Department: Electrical Electronics
AMOUNT: 20,000
FORMAT: MS WORD
PAGES: -

Get Complete Work

Abstract Preview

ABSTRACT

This study, ‘Fault location on power distribution lines using artificial neural network and Fuzzy Logic was carried out on Bori distribution network system to predict, classify and estimate the fault distance from a given feeder. Fault detection, fault classification and fault location have been achieved by using artificial neural networks and Fuzzy Logic. Feedforward networks have been applied along with backpropagation algorithm for each of the three phases in the Fault location process. Analysis on neural networks with varying number of hidden layers and neurons per hidden layer has been provided to validate the choice of the neural networks in each step. Simulation results have been provided to demonstrate that artificial neural network based methods are efficient in locating faults on power distribution lines and achieve satisfactory performances. The different faults are simulated with different parameters to check the versatility of the method. The various simulations and analysis of signals are done in the MATLAB/SIMULINK environment. In another development, to cope with this uncertainty in decision making, a fault diagnosis method based on fuzzy logic is proposed. The proposed method aims to ease the burden of decision making on the part of the system operator by presenting a fast and accurate fault diagnosis method to classify and identify the type of fault which occurs on an overhead radial power distribution network. This method eased the burden of decision making on the part of the system operator by presenting a fast and accurate fault diagnosis method to detect, classify and locate the type of fault which occurs on an overhead radial power distribution network. This work, if implemented, will serve as a viable tool in fault detection, classification and location for distribution network system.

TABLE OF CONTENTS

PAGES

Title Page i

Abstract ii

Declaration iii

Certification iv

Dedication v

Acknowledgements vi

Table of Contents viii

List of Tables x

List of Figures xi

List of Plates xiii

CHAPTER 1: INTRODUCTION 1

1.1 Background of Study 1

1.2 Statement of the Problem 4

1.3 Objectives of the Study 5

1.4 Significance of the Study 6

1.5 Scope of the Study 6

CHAPTER 2: LITERATURE REVIEW 7

2.1 Elements of Power Systems 7

2.2 Power Generation System 9

2.3 power transmission system 10

2.4 power distribution systems 10

2.4.1 History Power Distribution System 11

2.4.2 Primary Distribution 12

2.4.3 Network Configurations 12

2.4.4 Rural Services 13

2.4.5 Secondary Distribution 13

2.5 Fault Location Methods for Distribution Systems. 14

2.6 Distribution line Fault Location Methods 16

2.6.1 Impedance Based Method 16

2.6.2 Simple Reactance Method 16

2.6.3 Travelling Wave Based Method 16

2.6.4 Neural Network Based Method 17

2.7 Neural Networks and their Application Distribution line fault Location 17

2.8 Model of a Neuron 19

2.9 Feedforward Networks 22

2.10 Learning Strategies 23

CHAPTER 3: MATERIALS AND METHODS 29

3.1 Types of and Sources of Data 29

3.2 Fault Detection, Classification and Location in Bori Power

Distribution System 29

3.3 Description of Power Distribution System in Bori 29

3.4 Modelling of the Studied Power Distribution System 31

3.5 Outline of the Proposed Scheme 32

3.6 Data Pre-processing 35

3.7 Fault Generated Data 36

3.8 Overview of the Training Process 37

3.9 Overview of the Testing Process 39

3.9 The fault Detection Using Neural Network 40

CHAPTER 4: RESULTS AND DISCUSSION 41

4.1 Fault Detection 41

4.1.1 Training the Fault Detection Neural Network 41

4.1.2 Testing the Fault Detection Neural Network 45

4.2 Fault Classification 48

4.2.1 Training the Fault Classifier Neural Network 48

4.2.2 Test with New Sets of Data Receiver Operating

Characteristics Curve 56

4.2.4 Test with New Sets of Data Fault Location 58

4.3.1 Single line – Ground Faults 58

CHAPTER 5: CONCLUSION AND RECOMMENDATIONS 63

5.1 Conclusions 63

5.2 Contributions to Knowledge 65

5.3 Recommendations 65

References 67

Appendices 73

LIST OF TABLES

Table PAGES

3.1: Description of bus-bars where faults were created in MatLab 35

3.2 Sample of Inputs to the neural network for various fault cases. 37

4.1 Fault classifier ANN outputs for various faults. 49

4.2: S-G –L Fault Output against Target 59

4.3: S-G –L Fault Output against Target 60

4.4: L-L Fault Output against Target 61

4.5: D-L G Fault Output against Target 62

LIST OF FIGURES

2.1 Typical electric power generation, transmission, and distribution system 9

2.2: A basic three-layer architecture of a feedforward ANN. 18

2.3: Typical model of a neuron. 19

2.4 Step activation function 20

2.5 Piece wise linear activation function. 21

2.6 Sigmoid unipolar activation function. 21

2.7 Bipolar activation function. 21

2.8 Structure of a two-layered feedforward network. 23

2.9 Scheme of supervised learning. 24

2.10 Structure of back-error-propagation algorithm 27

3.1 Transformers and their co-ordinates on Out-going Feeder 1(TTC) 30

3.2 Transformers and their co-ordinates on Out-going Feeder 2(LGA’S Lodge) 31

3.3 Symbols and Description of the Model 32

3.4 Mean-square error performance of the network (6-40-20-1) 34

4.1 Mean-square error performance of the network (6-40-20-10-1). 42

4.2 Mean-square error performance of the network (6-40-20-10-4-1) 43

4.3 Regression fit of the outputs vs. targets for the network (6-40-20-10-4-1) 44

4.4 Confusion matrices for Training, Testing and Validation Phases. 45

4.5 Overview of the ANN (6-40-20-10-1) chosen for fault detection 46

4.6 Mean-square error performance of the network with configuration (6-5-5-31-4) 47

4.7 Mean-square error performance of the network with configuration (6-5-31-4) 50

4.8 Mean-square error performance of the network with configuration (6-5-4) 51

4.9 Mean-square error performance of the network with configuration (6-10-4) 52

4.10 Mean-square error performance of the network with configuration (6-20-4) 53

4.11 Mean-square error performance of the network with configuration (6-35-4) 54

4.12 Gradient and Validation performance of the ANN (6-40-30-20-4) 55

4.13 Regression fit of the outputs vs. targets for the network (6-40-30-20-4) 56

CHAPTER 1 INTRODUCTION

1.1 BACKGROUND OF STUDY

Electrical power system comprises of generation, transmission and distribution of electrical energy. Distribution and utilization of electrical energy is the final stage in electricity delivery to end users (Uhunmwangho, R. and Omorogiuwa, E. 2014). In Nigerian Power System network, operating voltage of 11KV is distributed from 33KV Substation and is further stepped down to 0.145KV at the consumer’s end by transformers. These lines are exposed to faults as a result of lightning, short circuits, faulty equipment, wrong operations, human errors, overload, aging, etc. Many electrical faults manifest in mechanical damages, which must be repaired before returning the line to service. The restoration can be expedited if the fault location is known. Electrical system faults are the greatest threat to the continuity of electricity supply. Faults on electric power systems are an unavoidable problem and can cause short to long term power outages for customers and may lead to significant losses, especially for the manufacturing industry. Fast detecting, isolating, locating and repairing of these faults are critical in maintaining a reliable power system operation. When fault occurs on a distribution line, the voltages and currents at the point of fault suddenly reduces or increases to values that were not anticipated. Fault location is thus a very important issue in power system engineering and if done with higher accuracy, would aid in the quick restoration of power supply with minimum interruption. This is necessary for the health of power equipment and satisfaction of customer. Moreover, the introduction of new reform in Nigerian Power sector has increased the need for reliable and uninterrupted supply of electric power to the end users who are very sensitive to power outages. One of the most important factors that hinder the continuous supply of electricity and power is the presence of fault in the power system. Any abnormal flow of current in a power system’s components is called a fault in the power system. These faults cannot be completely avoided since a portion of these faults also occur due to natural reasons which are beyond the control of power engineers. Hence, it is very important to have a well-coordinated protection system that detects any kind of abnormal flow of current in the power system. This protection is expected to identify the type of fault and then accurately locates the position of the fault in the power system. The faults are usually taken care of by devices that detect the occurrence of a fault and eventually isolate the faulted section from the rest of the power system. Faults can be of various types namely transient, persistent, symmetric or asymmetric faults and the fault detection process for each of these faults is distinctly unique in the sense that there is no one universal fault location technique for all these kinds of faults. The overhead distribution Lines that distributes power from the substations are more prone to the occurrence of a fault because there is no insulation around the line cables, thus increasing the frequency of fault short circuit faults and ground faults. The reasons for the occurrence of a fault on a distribution line are due to several reasons such as a momentary tree contact, a bird or an animal contact (Das and Novosel, 2000) or due to other natural reasons such as thunderstorms or lightning. Most of the research done in the field of protective relaying of power systems concentrates on transmission line fault protection due to the fact that transmission lines are relatively very long and can run through various geographical terrain and hence it can take anything from a few minutes to several hours to physically check the line for faults (Eriksson, Saha and Rockefeller, 1985).In the past, several methods have been used for estimating fault location with different techniques such as line impedance based numerical method, travelling wave methods and Fourier analysis.

The automatic location of faults can greatly enhance the systems reliability because the faster we restore power, the more money and valuable time we save. Hence, many utilities are implementing fault locating devices in their power quality monitoring systems (IEEE guide for determining fault location on AC transmission and distribution lines, 2005) that are equipped with Global Information Systems for easy location of these faults. Fault location techniques can be broadly classified into the following categories (Saha, Izykowski and Rosolowski, 2010):

· Impedance measurement based methods

· Travelling-wave phenomenon based methods

· High-frequency components of currents and voltages generated by faults based methods

· Intelligence based method

In recent years, intelligent based methods are being used in the process of fault detection and location. Three major artificial intelligence based techniques that have been widely used in the power and automation industry according to Magnago and Abur, 1999 to classify faults are:

· Expert System Techniques

· Artificial Neural Network

· Fuzzy Logic Systems

Among these available techniques, Artificial Neural Network (ANN) has been used extensively in this research work for fault location on electric power distribution lines. This ANN method does not require an intense knowledge base for the location of faults unlike the other artificial intelligence based methods (Tang, Wang, Aggarwa et al., 2000). This research, therefore, presents a method for detection and identification of the faults and its location on the line using Artificial Neural Network (ANN) which were studied and simulated. Fault Voltages, currents and location distances of the lines are observed to perform this task.

1.2 STATEMENT OF PROBLEMS

The distribution system is a very important component of an electric power system which also consists of the generation and transmission systems. “The subject of fault location has been of considerable interest to electric power utility engineers and researchers for over twenty years”. Fault occurs due to failure of insulation of the distribution system, bridging of energized phase conductors by objects, grounding of power lines, short circuit etc. These events affect the value of the voltage and current on the distribution system and sometimes the entire power system. Considering the fact that most distribution systems are run overhead and have a radial topology, the need for accurate and reliable fault detection system becomes expedient. In recent times, researchers are more interested in finding solutions to the problem of vagueness, incomplete fault information, error in fault data and information redundancy.

The primitive method of fault location using visual inspection is time consuming and costly as requires extra maintenance staff to patrol outage areas. With the advent of digital relaying, several fault location methods for distribution systems have been proposed in the past couple of decades. Although some of these methods have acceptable accuracy for the application in conventional distribution systems, very few have addressed the fault location problem in the presence of distribution generation (DG).

In Bori Distribution Network, fault location is done by lines-men, usually as a follow up to recurrent tripping of the relay feeder. This is usually done without the aid of sensors and computers. Information supplied by customer(s) may also help the lines-men to localize such faults. Protective relay trips the 11KV outgoing circuit breaker tied to the line and the faulty section is identified and then isolated for maintenance operation. These challenges are summarized below:

· Uncertainty and discrepancy in predicting fault location in distribution network.

· Conventional fault location techniques subject Power equipment to stress and cause so much delay in fault diagnosis.

To reduce the outage time and enhance service reliability, it is essential for dispatchers to locate fault sections in a power system as soon as possible. Currently, heuristic rules from dispatchers’ past experiences are extensively used in fault diagnosis. The important role of such experience has motivated extensive recent work on the application of expert system in this field. A few papers have described and dealt with uncertainties involving the fault location and other information available. These uncertainties occur due to failures of protective relays and breakers, errors of local acquisition and transmission, and inaccurate occurrence time, etc. An effective approach is thus necessary to deal with uncertainties in these expert systems. Fault diagnosis in electric power system is a facet operation. Every signal and step contains some uncertainties, which can be modeled by the use of Artificial Neural Network and Fuzzy Logic. ANN and Fuzzy set theory is used to determine the most likely fault sections in the approach presented here. In this research, the combination of these methods helps to appropriately diagnosis the fault with minimum error function. Both are manipulated during inference based on rules concerning fault sections.

1.3 OBJECTIVES OF THE STUDY

1.3.1 Main Objective

The main objective of this research is to develop and design a functional faults locator that can detect, classify and locate faults in power distribution lines through the application of Artificial Neural Network (ANN) and Fuzzy Logic in order to reduce the outage time and enhance service reliability.

1.3.2 Specific Objectives

The specific objectives include the following;

i. To develop an Artificial neural network (ANN) based technique for diagnosing and prediction of Faults location;

ii. To develop an Artificial neural network (ANN) based technique for fault classification;

iii. To design an artificial neural network (ANN) based technique that can locate the approximate distance where faults occur along the distribution line;

iv. To develop a Fuzzy Logic based technique for diagnosing and predicting Fault location;

v. To develop a Fuzzy Logic based technique for fault classification.

Download

Hot Line :+2347075301759,08038736720