Search

Showing total 2 results
Start Over Topic electrical and electronic engineering Publication Year Range Last 3 years Language english Journal ieee transactions on industrial electronics
2 results

1. Recurrence Plots Based Method for Detecting Series Arc Faults in Photovoltaic Systems

Author

Teymoor Ghanbari, Haidar Samet, Ali Amiri, and Electrical Energy Systems

Subjects
Normal conditions, Series (mathematics), Computer science, Photovoltaic system, Circuit faults, Time series analysis, Signal, Plot (graphics), Arc (geometry), Time-domain analysis, Tools, Detection, Mathematical model, Series Arc Fault, Series arc fault (SAF), Control and Systems Engineering, Recurrence plots, SDG 7 - Affordable and Clean Energy, Electrical and Electronic Engineering, Time series, Algorithm, Photovoltaic systems, Switches, SDG 7 – Betaalbare en schone energie, Voltage
Abstract

Series Arc Faults (SAFs) are the most common faults in photovoltaic systems. If a SAF is not detected in time, it may lead to some catastrophic damages to the system. This paper presents a new method for detecting SAFs in photovoltaic systems based on determinism in the voltage signal. The determinism of the signal is derived using the recurrence plots method. The recurrence plots provide a two-dimensional plot of the signal, from which the degree of determinism in the signal is derived as a criterion for detection of SAFs. The performance of the method is evaluated using plenty of experiments carried out in different SAF and normal conditions. The results confirm the high accuracy, high speed, and low computational burden of the proposed method.

Published
2022

2. Fault Detection and Classification for Photovoltaic Systems Based on Hierarchical Classification and Machine Learning Technique

Author

Aref Eskandari, Jafar Milimonfared, Mohammadreza Aghaei, Group Reinders, and Energy Technology

Subjects
line-line (LL) and line-ground faults (LG), Monitoring, Computer science, Fault detection and classification, Feature extraction, 02 engineering and technology, Machine learning, computer.software_genre, Fault (power engineering), Fault detection and isolation, Data modeling, 0202 electrical engineering, electronic engineering, information engineering, SDG 7 - Affordable and Clean Energy, Electrical and Electronic Engineering, Normal conditions, Classification algorithms, business.industry, machine learning (ML), 020208 electrical & electronic engineering, Photovoltaic system, Photovoltaic monitoring, Process (computing), Circuit faults, Data models, Impedance, Hierarchical classification, Statistical classification, Control and Systems Engineering, Line-Line and Line-Ground faults, Artificial intelligence, hierarchical classification (HC), business, computer, Fault detection, SDG 7 – Betaalbare en schone energie
Abstract

Line-Line (LL) and Line-Ground (LG) faults may not be detected by common protection devices in PV arrays due to these faults are not detectable under high fault impedance and low mismatch level. In recent years, many efforts have been devoted to overcome these challenges using intelligent methods. However, these methods could not classify the type of faults and diagnose their severity. This paper proposes a novel and intelligent fault monitoring method to detect and classify LL and LG faults at the DC side of PV systems. For this purpose, the main features of Current-Voltage (I-V) curves under different fault events and normal conditions are extracted. The faults are categorized using the Hierarchical Classification (HC) platform. Later, the LL and LG faults are detected and classified by Machine Learning (ML) methods. The proposed method aims to reduce the amount of dataset which is required for the learning process and also obtain a higher accuracy in detecting and classifying the fault events at low mismatch levels and high fault impedance compared to other fault diagnostic methods. The experimental results verify that the proposed method precisely detects and classifies LL and LG faults on PV systems under the different conditions and severity with the accuracy of 96.66% and 91.66%, respectively.

Published
2021