Locating Faults in Distribution Systems in the Presence of Distributed Generation using Machine Learning Techniques

This paper presents an artificial neural network (ANN) and support vector machine (SVM) approach for locating faults in radial distribution systems. Different from the traditional Fault Section Estimation methods, the proposed approach uses measurements available at the substation, circuit breaker and relay statuses. The data is analyzed using the principal component analysis (PCA) technique and the faults are classified according to the reactances of their path using a combination of support vector classifiers (SVCs) and feedforward neural networks (FFNNs). A practical 52 bus distribution system with loads is considered for studies, and the results presented show that the proposed approach of fault location gives accurate results in terms of the estimated fault location. Practical situations in distribution systems, such as protective devices placed only at the substation, all types of faults, and a wide range of varying short circuit levels, are considered for studies. The results demonstrate the feasibility of applying the proposed method in practical distribution system fault diagnosis.

ABSTRACTThis paper reviews the activity-travel behaviour literature that employs Machine Learning (ML) techniques for empirical analysis and modelling. Machine Learning algorithms, which attempt to build intelligence utilizing the availability of large amounts of data, have emerged as powerful tools in the fields of pattern recognition and big data analysis. These techniques have been applied in activity-travel behaviour studies since the early ’90s when Artificial Neural Networks (ANN) were employed to model mode choice decisions. AMOS, an activity-based modelling system developed in the mid-’90s, has ANN at its core to model and predict individual responses to travel demand management measures. In the dawn of 2000, ALBATROSS, a comprehensive activity-based travel demand modelling system, was proposed by Arentze and Timmermans using Decision Trees. Since then researchers have been exploring ML techniques like Support Vector Machines (SVM), Decision Trees (DT), Neural Networks (NN), Bayes Classifiers, and more recently, Ensemble Learners to model and predict activity-travel behaviour. A large number of publications over the years and an upward trend in the number of published articles over time indicate that Machine Learning is a promising tool for activity-travel behaviour analysis and prediction. This article, first of its kind in the literature, reviews these studies and explores the trends in activity-travel behaviour research that apply ML techniques. The review finds that mode choice decisions have received wide attention in the literature on ML applications. It was observed that most of the studies identify the lack of interpretability as a serious shortcoming in ML techniques. However, very few studies have attempted to improve the interpretability of the models. Further, some studies report the importance of feature engineering in ML-based studies, but very few studies adopt feature engineering before model development. Spatiotemporal transferability of models is another issue that has received minimal attention in the literature. In the end, the paper discusses possible directions for future research in the area of activity-travel behaviour modelling using ML techniques.

Prediction of fracture toughness of concrete using the machine learning approach

A machine learning approach for classifying healthy and infarcted patients using heart rate variabilities derived vector magnitude

Impact of pixel-based machine-learning techniques on automated frameworks for delineation of gross tumor volume regions for stereotactic body radiation therapy

This study aims to develop a real-time model for detecting and classifying various fault types in power distribution networks to enhance reliability and operational efficiency. A hybrid DWT–SVM approach is essential for accurately detecting and classifying faults in modern power distribution systems, especially under non-stationary and dynamic conditions. The proposed method addresses a range of fault scenarios, including single-phase-to-ground, line-to-line, double-line-to-ground, and three-phase faults, within a 33 kV distribution network. A hybrid approach combining Discrete Wavelet Transform (DWT) and Support Vector Machine (SVM) is introduced. Using the Debauchies-4 (Db4) wavelet, DWT effectively decomposes transient fault currents at the source terminal, capturing critical time-frequency domain features. Fault classification is performed using an SVM optimized with a Radial Basis Function (RBF) kernel and Particle Swarm Optimization (PSO), enabling precise mapping of data into higher-dimensional spaces for optimal separation. Validation conducted with MATLAB R2023b demonstrates a detection accuracy of 100% and a classification accuracy of 99%. Comparative analyses against models such as PSO-based Support Vector Machine (PSO-SVM), DWT-DNN and wavelet transform with artificial neural networks (WT-ANN) on the IEEE 13-bus system highlight the proposed method's superior performance. This innovative approach proves to be robust, adaptable, and highly effective across diverse fault scenarios, offering significant improvements in accuracy and reliability for fault detection and classification in power distribution networks. The method supports real-time operation by using high-speed simulation platforms MATLAB/Simulink to process signals and classify faults within milliseconds using a pre-trained SVM model.

A rule-based expert system designed to locate the faults in a distribution system is presented. Distribution system component data and network topology are stored in the database. A set of heuristic rules is compiled from the dispatcher's experience and imbedded in the rule base. To locate distribution system faults, an inference engine is developed to perform deductive reasoning on the rules in the knowledge base. The inference engine comprises three major parts: the dynamic searching method, the backtracking approach, and the set intersection operation. The expert system is implemented on a personal computer using the artificial intelligence language Prolog. To demonstrate the effectiveness of the proposed approach, the expert system has been used to locate faults in a real underground distribution system within the service area of the Taipei City District Office of the Taiwan Power Company. It is found that the expert system can identify fault location very efficiently. Therefore, it can serve as a valuable tool to help distribution system dispatchers determine fault locations.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

The potential benefits of direct current (DC) network in low‐voltage system promote smart grids and facilitate increasing penetration of distributed generation (DG). Correct identification of faulted section of a distribution network by an automation system reduces power outage time and improves reliability indices of such systems. With the onset of a fault in a DC distribution system, data recorded at an outage management system are used to identify the faulted section. With DG units active in a distribution system, there will be bidirectional power flow and faulted section identification becomes challenging. Using voltage and current data from consumer‐end smart meters and the substation, a method is proposed to identify the faulted section in DC distribution system. The Hadamard product of fault‐affected sections (obtained from network topology and voltage status matrices) is used to identify the faulted section correctly. Using power systems computer‐aided design/electro‐magnetic transient design and control simulation, the accuracy of the proposed method is verified for different fault situations including simultaneous faults, fault close to a bus and with rooftop photovoltaic integration to a DC distribution system. The method has the capability to provide information on the fault segment that connects feeder pillar to the consumer end also.

This study examines the use of machine learning (ML) techniques to optimize the basic machining parameters and protrusion dimensions that affect tool shape degeneration in die-sinking electric discharge machining (EDM). The primary objective is to decrease errors and enhance prediction and optimization effectiveness. This study introduces a completely novel tool geometry model aimed at minimizing tool shape degeneration, which, to our knowledge, has not been previously documented in the literature. Additionally, this research represents the first instance of employing ML techniques to generate data for addressing this specific type of problem, further advancing the field of die-sinking EDM. The pivotal machining parameters include discharge current, pulse time and machining depth. Three ML approaches are implemented in this investigation: Artificial Neural Network (ANN), Adaptive-Network-Based Fuzzy Inference System (ANFIS), and Support Vector Machine (SVM). In comparison with experimental outcomes, the ANN technique exhibited superior predictive ability with an coefficient of determination (R 2) of 0.99985 and an Mean Relative Error (MRE) of 0.854%. Four distinct EDM machining scenarios are presented and machining parameters and protrusion dimensions are optimized using the ANN technique to decrease tool shape degeneration. Optimizing the machining parameters and diagonal dimensions of the protrusion substantially reduced tool shape degeneration. This research demonstrates the effectiveness of ANN in optimizing machining parameters and improving tool performance in die-sinking EDM. A significant reduction in total wear area of 66.7% was achieved with a considerably lower time cost through the optimized ANN network. While the study demonstrates promising results, its reliance on specific datasets for training may limit the generalizability of the model to broader machining scenarios.

Gaining knowledge from health data may contribute to novel approaches or improved patient care plans. To intelligently acquire knowledge from the stroke data, machine learning (ML) technique is utilised and healthcare systems are used. Globally, security has become a major concern, and biometric technologies such as face detection and recognition technologies have been developed to solve security issues and security threats in the world. It has become possible because of developments in technology in the fields of automatic face analysis, machine learning, and pattern recognition. This chapter proposes a prototype to classify brain stroke and face recognition using ML techniques in the medical image. Face recognition and classification of stroke through ML technique like Decision Tree (DT), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Deep Learning with Convolution Neural Network (CNN) based on texture features and statistical features. A CNN model is experimentally used along with a collection of hyper-parameters for deep face recognition and stroke classification. Promising experimental results, with a total accuracy of 98.86% and 98.5%, are obtained, which demonstrates the effectiveness of deep face identification and stroke classification, respectively, in biometric systems.

Particulate matter (PM) emissions, including soot, pose a significant environmental concern. Traditional emission control approaches, such as engine calibration, often struggle to maintain consistent performance across varying driving conditions, engine speeds, and loads. This inconsistency leads to variations in pollutant output, making it challenging for internal combustion engines to comply with stringent emission standards under real-world driving conditions. Physics-based soot models, grounded in complex mathematical equations, have been developed to capture the mechanisms of soot formation. However, these models often face accuracy limitations and require substantial computational resources, rendering them impractical for real-time emission control. In contrast, Machine Learning (ML) techniques offer a more versatile and efficient approach to soot prediction. This paper introduces a machine learning methodology for predicting Soot Particle Numbers (PN). The approach integrates both physics-based and black-box strategies to create a grey-box model for predicting soot emissions from a 1600 cc Gasoline Direct Injection (GDI) engine across diverse load and speed conditions. The physical model is based on a validated 1D engine model in GT-SUITE, while the black-box model is formulated using multiple ML approaches exclusively on measured data. Ultimately, the grey-box model is developed through ML techniques based on measured data and combustion-related parameters obtained from the 1D engine physical model in GT-SUITE. The grey-box model’s results are compared with those of the black-box model. The ML techniques employed in this study include Gaussian Process Regression (GPR), Support Vector Machine (SVM), Artificial Neural Network (ANN), and an Ensemble of Regression Trees (ERT). The Minimum Redundancy Maximum Relevance (MRMR) and RreliefF feature selection methods are used to identify the most crucial features in soot PN prediction. The results indicate that the grey-box GPR exhibits superior performance for both single and multi-pulse injection strategies, achieving a coefficient of determination (R2) of 0.99.

Power system fault type classification and location prediction is critical in assessing the reliability of the power system, and later restoring it to a stable operating point followed by a fault. State of the art methods include sequence component, impedance measurement from the origin of the fault, and traveling wave based methods for fault type detection and classification problem. It is important to identify and classify the fault as quickly as possible for restoring power system stability to normal operation. Machine Learning and Deep Learning methods allow the analysis of large data of fault voltages and currents by using fast and efficient algorithms. These methods require large amount of data, however, with the recent advances in the field of power system, data acquisition using smart meters and Phasor Measurement Units (PMU), huge amount of system-wide data can be made available to analyze the problem of fault type classification and location prediction. This paper presents a comparative study of Stochastic Gradient Descent (SGD) based Deep Neural Network (DNN) and Machine Learning (ML) applied to power system fault type and location prediction problem. DNN architecture uses 10 hidden layers, each layer having 60 units with hyperbolic tangent as activation function, and a combination of Support Vector Machine (SVM) and Principal Component Analysis (PCA) method are considered. Comparative results in terms of time taken to run the algorithms, and accuracy of the results obtained are presented for a 3 machine 9 bus system. Results indicate that SVM method is an optimal choice for fault classification with high accuracy for location prediction and low computational requirements compared with DNN.

Ground fault location and isolating the fault location is very challenging in compensated distribution systems because of the fact that the fault current is very small to be measured. Considering that the massive intelligent electronic devices and Smart meter are installed in the distribution networks with the development of the “smart grid”, in this paper proposes a fault location method using the high voltage side smart metering unit recorded data. In the developed method uses the faulted negative sequence voltage and locates the faulted sections by applying the relationship between fault distance and measurement groups. The method is tested using three bus distribution systems and results give that it is suitable for system with both passive loads and distributed generations and it is not influenced by the system harmonic distortions, measurement noises and the loss of communication from one or even more of metering units. The proposed method uses the wide-area measured data but does not require any synchronization method. Accompanied with the less cost contactors, the method can locate and isolate the fault sections without interrupting the good system operations and makes it feasible for industry application.

The coronavirus is considered this century's most disruptive catastrophe and global concern. This disease has prompted extreme social, psychological and economic impacts affecting millions of people around the globe. COVID-19 is transmitted from one infected person's body to another through respiratory droplets. This virus proliferates when people breathe in air-contaminated space with droplets and microscopic airborne particles. This research aims to analyze automatic COVID-19 detection using machine learning techniques to build an intelligent web application. The dataset has been preprocessed by dropping null values, feature engineering, and synthetic oversampling (SMOTE) techniques. Next, we trained and evaluated different classifiers, i.e., logistic regression, random forest, decision tree, k-nearest neighbor, support vector machine (SVM), ensemble models (adaptive boosting and extreme gradient boosting) and deep learning (artificial neural network, convolutional neural network and long short-term memory) techniques. Explainable AI with the LIME framework has been applied to interpret the prediction results. The hybrid CNN-LSTM algorithm with the SMOTE approach performed better than the other models on the employed open-source dataset obtained from the Israeli Ministry of Health website, with 96.34% accuracy and a 0.98 F1 score. Finally, this model was chosen to deploy the proposed prediction system to a website, where users may acquire an instantaneous COVID-19 prognosis based on their symptoms.

Associations between persistent organic pollutants and endometriosis: A multipollutant assessment using machine learning algorithms