Analysis and Comparison of Machine Learning Approaches for Transmission Line Fault Prediction in Power Systems (original) (raw)
Related papers
Journal of Research in Engineering and Applied Sciences, 2021
The transmission lines suffer from various faults subjected to numerous natural as well as manmade causes. This paper presents a proposed MATLAB-SIMULINK model for generation of such random disturbances. The output of the system is input to another python-based model in order to detect and predict the exact nature of disturbances using various artificial neural networks with their respective accuracy scores. This paper provides a brief comparison between Decision Tree Classifier, Random Forest Classifier, Support Vector Machines, K-Nearest Neighbors and Multi-Layer Perceptron methodologies for detection of line to ground fault, as an example in this model-based approach.
Using machine learning algorithms for classifying transmission line faults
DÜMF Mühendislik Dergisi
The faults in transmission lines should be identified for attaining high quality energy in electrical power systems. Savings can be made in both time and energy if the transmission line faults are classified accurately. The present study examined phase-ground, phase-phase-ground, phase-phase, phase-phase-phase and no fault cases. Support Vector Machine (SVM), K-Nearest Neighbours Algorithm (KNN), Decision Tree (DT), Ensemble, Linear discriminant analysis (LDA) classifiers were used for classifying the transmission line faults. These algorithms were compared with regard to parameters such as accuracy, error rate, prediction speed and training time. The accuracy and minimum error of SVM and KNN classifiers were 99.7 % and 0.0011 respectively. DT classifier is faster than the other classifiers with a predicted speed of 29000 obs/sec. Whereas LDA had the shortest training time of 0.76992 sec. The results have indicated that SVM, KNN classifiers have similar performances. In addition, th...
2021
The recent developments in the technology made by organizations have led to a quicker, simpler and a very accurate data analysis. The use of machine learning techniques have been exponentially increasing in the analysis of data in different fields ranging from medicine to defense, education, finance and energy applications. The machine learning techniques reduce further meaningful information processed by data mining. These significant and meaningful information help organizations to establish their future policies to get more advantages in terms of time and cost. In this paper the author has tried to present the best classification method by having a comparative analysis on various methods such as Logistic Regression, Support Vector Machine, Naive Bayes and K-Nearest Neighbors etc. for a particular use case i.e. prediction and classification of transmission line faults. The author has made this analysis by utilizing both Python and MATLAB Simulink. This will surely help the researc...
Machine Learning Approaches for Power Transmission Lines Fault Classification: A Systematic Review
Journal of Advanced Research in Artificial Intelligence & It's Applications, 2024
The era of computational intelligent power systems has resulted in a proliferation of great number of techniques, technologies and products for the power industry. This may be attributed to the unique ability of computationally intelligent systems to demystify the hidden truths in large volumes of power systems data. In this paper, a succinct systematic review of power transmission line fault classification based on ML approaches is presented. The review accounts for the different Machine Learning (ML) approaches in terms of their nature of classification such as the single or multi-class, the nature of the ML such as the use of purely mathematical or AI, and the nature of the hybridization such as the use of dual or multi-hybridizations and for a period of 2006 to 2020. Specifically, the review studies the aspect of power systems classification that deals with the detection and localization of faults on transmission lines. From the reviews conducted, the most prominent classifiers were found to be the conventional Artificial Neural Networks (ANN) for the detection and localization of power system faults. This shows that the researchers will prefer the predictive ML approaches that are based on the simple intelligent operations that occur in mammalian brains i.e. the conventional Back-Propagation Neural Networks (BPNNs). However, it will be desirous if researchers equally investigate other potential but less popular neural ML model schemes.
Transmission Line Fault Location and Classification Using Machine Learning Technique
Zenodo (CERN European Organization for Nuclear Research), 2022
The fault types and location in a power transmission line are detected based on the voltage and current wave forms. Fault types and location varies slightly depending on the location of the accident, which is not easy to grasp with the human eye. Therefore, many sensors are needed to diagnose faults, and it is very difficult for an administrator to determine the type and location of fault using voltage and current waveforms. The traditional systems adopted for fault classification result in complexity, lack of economy, nonhomogeneity and sometimes even cause unacceptable classification errors. The detection of fault in transmission line is done by using magnetic field sensors. The k-Nearest-Neighbour (kNN) algorithm and linear regression Machine Learning Technique can be used to locate and classify fault. This will reduce the computation techniques and will help in improving the power transmission system protection. It will also reduce the time necessary to clear the faults, especially for a long transmission line.
The Characterisation and Automatic Classification of Transmission Line Faults: PhD Thesis
A country‘s ability to sustain and grow its industrial and commercial activities is highly dependent on a reliable electricity supply. Electrical faults on transmission lines are a cause of both interruptions to supply and voltage dips. These are the most common events impacting electricity users and also have the largest financial impact on them. This research focuses on understanding the causes of transmission line faults and developing methods to automatically identify these causes. Records of faults occurring on the South African power transmission system over a 16-year period have been collected and analysed to find statistical relationships between local climate, key design parameters of the overhead lines and the main causes of power system faults. The results characterize the performance of the South African transmission system on a probabilistic basis and illustrate differences in fault cause statistics for the summer and winter rainfall areas of South Africa and for different times of the year and day. This analysis lays a foundation for reliability analysis and fault pattern recognition taking environmental features such as local geography, climate and power system parameters into account. A key aspect of using pattern recognition techniques is selecting appropriate classifying features. Transmission line fault waveforms are characterised by instantaneous symmetrical component analysis to describe the transient and steady state fault conditions. The waveform and environmental features are used to develop single nearest neighbour classifiers to identify the underlying cause of transmission line faults. A classification accuracy of 86% is achieved using a single nearest neighbour classifier. This classification performance is found to be superior to that of decision tree, artificial neural network and naïve Bayes classifiers. The results achieved demonstrate that transmission line faults can be automatically classified according to cause.
Improving fault identification in smart transmission line using machine learning technique
International Journal of Applied Power Engineering (IJAPE), 2023
In this work inevitable for power transmission boards such as Tamil Nadu Generation and Distribution Corporation Limited (TANGEDCO) to look for a low-cost communication system with low power usage and to improve supply reliability, to transmit reliable fault information back to the control centre in real time. This work aims to design an automated and effective fault identification and position system for all overhead power transmission network networks using all current fault indicator technologies, machine learning methods, and commercially tested communication technology to easily and reliably pin a transmission system's flawed point parts. This will help to people avoid touching the electrical wire and prevent electrical shocks and current wastage as well. Smart transmission lines have played a decisive role in developing human protection and preventing current wastage. The transmission line is opened and the state of the line is evaluated, and the information goes to electrical board (EB) office. The system monitors the data by sending the alert message to the person responsible for the GPS location, either via SMS or BUZZER, or by displaying the alert message lives. Transmission line distribution is broad and most of them are spread around the geographical environment.
A NEURAL NETWORK BASED APPROACH FOR TRANSMISSION LINE FAULTS
In this study, a neural network based methodology is proposed for power transmission line faults. The proposed method uses Probabilistic Neural Network (PNN) for classifying fault types and Resilient Propagation algorithm (RPROP) for detecting fault locations. Wavelet Transform is also proposed for feature selection and analysis. The hybrid system proposed in this study is tested using a simulation and a prototype power system.
2018
Electric power Transmission lines are characterized by very lengthy transmission lines and thus are more exposed to the environment. Consequently, transmission lines are more prone to faults, which hinder the continuity of electric power supplied, increases the loss of electric power generated and loss of economy. Quick detection and classification of a fault hastens its Clearance and reduces system downtime thus, improving the security and efficiency of the network. Thus, this paper focuses on developing a single artificial neural network to detect and classify a fault on Nigeria 33-kV electric power transmission lines. This study employs feedforward artificial neural networks with backpropagation algorithm in developing the fault detector- classifier. The transmission lines were modeled using SimPowerSystems toolbox in Simulink and simulation is done in MATLAB environment. The instantaneous voltages and currents values are extracted and used to train the fault detector-classifier....
Artificial Intelligence Based Fault detection and classification in Transmission Lines
Iconic Research And Engineering Journals, 2018
Artificial neural networks and wavelet transform have been used to achieve fault Identification and classification on electric power transmission lines. This work proposed an improved solution based on wavelet transform and neural network back-propagation algorithm. The three-phase current and voltage waveforms measured during the occurrence of fault in the power transmission-line are pre-processed first and then decomposed using wavelet multi-resolution analysis to obtain the high frequency details and low frequency approximations. The patterns formed based on high frequency signal components are arranged as inputs of the neural network, whose task is to indicate the occurrence of a fault on the lines. The patterns formed using low frequency approximations are arranged as inputs of the second neural network, whose task is to indicate the exact fault type. The neural networks which can learn was trained to recognize patterns, classify data and forecast future events. Feed forward networks have been employed along with back propagation algorithm for each of the three phases in the Fault location process. An analysis of the learning and generalization characteristics of elements in power system was presented using Neural Network toolbox in MATLAB/SIMULINK environment. Simulation results obtained demonstrated that neural network pattern recognition and wavelet multi-resolution analysis approach are efficient in identifying and classifying faults on transmission lines as satisfactory performance was achieved especially when compared to the conventional methods such as impedance and travelling wave methods.