Survey on AI-Assisted Power Transmission Line Fault Detection

One of the most important components of power systems are power transmission lines. Different types of faults in power transmission lines may cause disruption of power transmission or damage power system equipment, as well as it can effect on the power quality of the entire network. Therefore accurate estimation of fault location in power transmission for restoring power transmission at the shortest possible time with the lowest disruption at power transmission is vital. On the other hand accurate estimation of type and location of faults in transmission lines can save time and maintenance cost of power system equipment. In this paper, EMTP software is used to simulate a real power grid model with 100 km transmission line for different fault locations and fault resistances. Then Discrete Wavelet Transform DWT, which is anadvance signal processing tool, is applied to acquire fundamental harmonics of three phase voltage and current signals at the end of transmission line. To classify type of faults and their locations, artificial neural network is utilizedat transmission line. The obtained results show that the error percentage in both location and fault typediagnosis is so low.

Power transmission lines are the key network that transmits energy from the generation side to load. The complexity and uncertainty in the power system increase continuously due to the evolution of the smart grid, which needs an effective and accurate protection system. The faults in transmission lines affect the whole power system and also the consumers’ side. Therefore, accurate and precise identification of faults in transmission lines minimizes the losses and maximizes the functionality and reliability of the power network. Due to the recent advances in digital technology, an online scheme is used to locate the fault in transmission lines. In this paper, machine learning-based discrete wavelet transform and double-channel extreme learning machine method are proposed to locate and classify the faults in transmission lines. Db4 wavelet is used as a mother wavelet in the discrete wavelet transform for feature extraction up to nine levels. The proposed method validated on real-time data which achieves higher classification accuracies and less fault detection time. Results show that high-impedance non-linear faults have no effect on the proposed technique.

Power transmission line is key equipment in secure and reliable power flow in each power system. To arise reliability and security of overhead power lines, different types of failures should be simulated to minimize their impact and to detect and resolve them as quickly as possible. The objective of this paper is to provide an accurate method for detection, classification and localization of faults occurring in power transmission lines using Artificial Neural Network (ANN). Power transmission system was modelled in DIgSILENT PowerFactory, simulating both normal and fault scenarios. Three types of faults were considered for simulation: single-phase-to-ground fault, two-phase short circuit, and three-phase short circuit. Each fault was simulated across the 110 kV power lines with a resolution of 5%. In addition to the fault scenarios, normal scenario was carried out using a load flow analysis, where the system’s load was varied. Voltage and current data from these simulations were utilized to train and test the ANN model. Principal Component Analysis (PCA) was applied for dimensionality reduction, improving the efficiency and performance of the ANN model. The proposed model achieved an accuracy of 100% in detecting fault types, a fault classification accuracy of 94% for identifying the fault line, and a mean absolute error (MAE) of 1.15 in pinpointing the exact fault position. These results demonstrate the model's effectiveness in accurately identifying and localizing faults in power transmission lines, significantly contributing to the reliability and stability of power grid operations.

This paper presents the progress of fault detection and classification analysis in transmission line using wavelet transform with high-speed protective digital relay. These techniques are applicable for real time data analysis. The MATLAB simulation model obtains the voltage and current signals that have been measured in both end of the transmission line. These signals are used in a discrete wavelet transform to extract the original signals and to measure the sharp variation of multi-resolution analysis (MRA). The analysis for various types of faults in transmission lines is detected and classified with the help of power protection techniques. In this paper, the wavelet transform technique is used for the detection of faults. This methodology delivers signals in the time and frequency domain. The wavelet transform will be examined to determine the effect of the detail coefficients db-3 and db-4 and provide an acquired time and frequency signal. The performance of wavelet transform will be more suitable, effective, and adequate for high impedance faults in high voltage transmission lines. The power transmission lines are interconnected with the generating station at 400 kv via consumer load through 300 km distance to obtain by MATLAB/Simulink.

Since 1945, electric power systems have been extremely important due to huge increase in the electric energy demand. As a result, power transmission lines have been rapidly developed in number and length. Any disturbance or the tripping of transmission line may lead to failure of supply in wide area. This requires the effective protection of these lines. The analysis of faults with different loads helps in the detection of transients which ultimately helps in the localization, detection and classification of power system faults to provide efficient protection system. This paper presents a discrete wavelet transform (DWT) based methodology for detection of transmission line faults. The investigated faults include line to ground fault, double line fault, double line to ground fault, and three phase faults. The detailed study of detection of faults has been carried out in MATLAB/Simulink environment.

Self attention convolutional neural network with time series imaging based feature extraction for transmission line fault detection and classification

Unexpected failures in the electrical power transmission line can occur for several different, unpredictable reasons. Power failures on transmission lines can destroy the present power grid if faults aren't quickly detected and corrected. For consistent performance, it is essential to have a system in place for identifying and categorizing power system faults. Several academics have developed automated approaches for fault identification and classification; however, typical fault detection techniques depend on human feature extraction with previous understanding. It is crucial to detect transmission line faults to guarantee safety. Preventing costly damage to the network is one of the key advantages of earlier fault detection in a transmission line. Autonomous and efficient fault diagnosis in the power system remains a major problem in the area of intelligent fault diagnosis. Recent years have seen a surge in interest in the development of intelligent fault diagnosis techniques that make use of Machine Learning (ML). Different ML techniques for fault classification are presented in this research. Kaggle data is used after being cleaned and integrated. Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF) are the ML models used. Using the metrics of evaluation, the optimal model is found. Results from experiments demonstrate that the NB will outperform other methods for fault detection in power transmission lines, with an accuracy rate of 97.77 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> , recall of 97.09 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> , the precision of 98.64%, and Fl-score of 97.86%.

Novel filter based ANN approach for short-circuit faults detection, classification and location in power transmission lines

In this article, the main problem under investigation is the detection and diagnosis of short-circuit faults in power transmission lines. The proposed fault detection (FDD) approach is mainly based on principal component analysis (PCA). The proposed fault diagnosis/identification (FAI) approach is mainly based on sliding-window versions of the discrete Fourier transform (DFT) and discrete Hilbert transform (DHT). The main contributions of this article are (a) a fault detection approach based on principal component analysis in the two-dimensional scores space; and (b) a rule-based fault identification approach based on human expert knowledge, combined with a probabilistic decision system, which detects variations in the amplitudes and frequencies of current and voltage signals, using DFT and DHT, respectively. Simulation results of power transmission lines in Portugal are presented in order to show the robust and high performance of the proposed FDD approach for different signal-to-noise ratios. The proposed FDD approach, implemented in Python, that can be executed online or offline, can be used to evaluate the stress to which circuit breakers (CBs) are subjected, providing information to supervision- and condition-based monitoring systems in order to improve predictive and preventive maintenance strategies, and it can be applied to high-/medium-voltage power transmission lines as well as to low-voltage electronic transmission systems.

Fast and accurate detection of faults in power transmission lines is of great importance for the safety and continuity of power systems. This study develops a predictive model using chirp-z transform and machine learning algorithms to locate single-phase-ground faults. During the study, 39 different fault locations were modelled, current and voltage signals of these locations were analysed and frequency spectra were obtained. The fault signals were decomposed into their components using the modal transformation matrix and then spectral analysis was performed using the Chirp-Z algorithm. The resulting spectra were used as input data for the prediction algorithms. Gradient Boosting Ensemble, Support Vector Regression and Random Forests algorithms were used for fault prediction and the performance of the models was compared. The accuracy of the models was evaluated using various metrics. The results show that the Gradient Boosting Ensemble model has the lowest error rates and the highest accuracy, which is important for early fault detection, maintenance and repair processes.

The transmission lines repeatedly face an aggregation of shunt-faults and its impact in the real time system increases the vulnerability, damage in load, and line restoration cost. Fault detection in power transmission lines have become significantly crucial due to a rapid increase in number and length. Any kind of interruption or tripping in transmission lines can result in a massive failure over a large area, which necessitates the need of effective protection. The diagnosis of faults help in detecting and classifying transients that eventually make the protection of transmission lines convenient. In this paper, we propose a deep learning-enabled technique for the detection and classification of transmission line faults. The faulty information are extracted using Discrete Wavelet Transform (DWT) and fed into the multilayer perceptron classification model. The results indicate that the proposed approach is capable of accurately classifying and detecting faults in transmission line with high precision.

One of the major problems in transmission lines is the occurrence of failures that affect the quality of the electric power supplied, as the exact localization of the fault must be known for correction. In order to streamline the work of maintenance teams and standardize services, this paper proposes a method of locating faults in power transmission lines by analyzing the voltage oscillographic signals extracted at the line monitoring terminals. The developed method relates time series models obtained specifically for each failure pattern. The parameters of the autoregressive integrated moving average (ARIMA) model are estimated in order to adjust the voltage curves and calculate the distance from the initial fault localization to the terminals. Simulations of the failures are performed through the ATPDraw ® (5.5) software and the analyses were completed using the RStudio ® (1.0.143) software. The results obtained with respect to the failures, which did not involve earth return, were satisfactory when compared with widely used techniques in the literature, particularly when the fault distance became larger in relation to the beginning of the transmission line.

A deep learning based intelligent approach in detection and classification of transmission line faults

In power transmission systems faults returning leaving them offline. This problem generates an economic impact on the interested parties, partly because in certain cases transmission lines protections act in a delayed manner or because the data processing generated by electrical protections tends to be a tedious. Artificial intelligence personnel have implemented a number of methods aimed to provide solutions for detection, classification and localization of said faults. In this work, a multilayer neural network capable of performing the process of classifying 11 types of faults in power transmission lines was implemented. As a result, a graphical interface allows users to intuitively visualize the faults.

Power transmission network is the most critical part of a power system due to its connectivity with generation and distribution stations. Though it is a riskier employment to carry out the routine inspections of the transmission lines manually, the task of inspection is imperative to the continuous operation of the power system. However, the new trend of transmission line inspection is based on extracted details of the lines by means of Remotely Operated Vehicles (ROVs) traversing through them. This paper proposes a method being tested by a prototype for traversing alone the transmission conductor, inspecting the line through real time video streaming, detecting faults and pinpointing them through Geo Tagging. Automated transmission line inspection and fault detection is proposed to carry out through image processing and sensory data acquisition. Radio Frequency (RF) technology is the main communication mechanism between the operator and the ROV. This technology will expand the remotely operating distance of the ROV. Furthermore, a mechanism was developed to enable the robot to cross over from one span to another in the transmission network which include suspension type insulators.