Deployment of AI-based RBF network for photovoltaics fault detection procedure

Research output: Contribution to journalArticle

Abstract

In this paper, a fault detection algorithm for photovoltaic systems based on artificial neural networks (ANN) is proposed. Although, a rich amount of research is available in the field of PV fault detection using ANN, this paper presents a novel methodology based on only two inputs for the training, validating and testing of the Radial Basis Function (RBF) network achieving unprecedented detection accuracy of 98.1%. The proposed methodology goes beyond data normalisation and implements a ‘mapping of inputs’ approach to the data set before exposing it to the network for training. The accuracy of the proposed network is further endorsed through testing of the network in partial shading and overcast conditions.
Original languageEnglish
Pages (from-to)1-18
Number of pages18
JournalAIMS Electronics and Electrical Engineering
Volume4
Issue number1
DOIs
Publication statusAccepted/In press - 15 Nov 2019

Fingerprint

Radial basis function networks
Fault detection
Neural networks
Testing

Cite this

@article{61ca2267c5204129a76cc458b809183f,
title = "Deployment of AI-based RBF network for photovoltaics fault detection procedure",
abstract = "In this paper, a fault detection algorithm for photovoltaic systems based on artificial neural networks (ANN) is proposed. Although, a rich amount of research is available in the field of PV fault detection using ANN, this paper presents a novel methodology based on only two inputs for the training, validating and testing of the Radial Basis Function (RBF) network achieving unprecedented detection accuracy of 98.1{\%}. The proposed methodology goes beyond data normalisation and implements a ‘mapping of inputs’ approach to the data set before exposing it to the network for training. The accuracy of the proposed network is further endorsed through testing of the network in partial shading and overcast conditions.",
keywords = "Photovoltaic (PV), Artificial Intelligence, Machine learning, Fault detection, renewable energy, RBF network",
author = "Muhammad Hussain and Mahmoud Dhimish and Violeta Holmes and Peter Mather",
note = "Special Issues: Health Monitoring of Electrical Actuators and their supplies",
year = "2019",
month = "11",
day = "15",
doi = "10.3934/ElectrEng.2020.1.1",
language = "English",
volume = "4",
pages = "1--18",
journal = "AIMS Electronics and Electrical Engineering",
issn = "2578-1588",
publisher = "AIMS Press",
number = "1",

}

Deployment of AI-based RBF network for photovoltaics fault detection procedure. / Hussain, Muhammad; Dhimish, Mahmoud; Holmes, Violeta; Mather, Peter.

In: AIMS Electronics and Electrical Engineering, Vol. 4, No. 1, 26.12.2019, p. 1-18.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Deployment of AI-based RBF network for photovoltaics fault detection procedure

AU - Hussain, Muhammad

AU - Dhimish, Mahmoud

AU - Holmes, Violeta

AU - Mather, Peter

N1 - Special Issues: Health Monitoring of Electrical Actuators and their supplies

PY - 2019/11/15

Y1 - 2019/11/15

N2 - In this paper, a fault detection algorithm for photovoltaic systems based on artificial neural networks (ANN) is proposed. Although, a rich amount of research is available in the field of PV fault detection using ANN, this paper presents a novel methodology based on only two inputs for the training, validating and testing of the Radial Basis Function (RBF) network achieving unprecedented detection accuracy of 98.1%. The proposed methodology goes beyond data normalisation and implements a ‘mapping of inputs’ approach to the data set before exposing it to the network for training. The accuracy of the proposed network is further endorsed through testing of the network in partial shading and overcast conditions.

AB - In this paper, a fault detection algorithm for photovoltaic systems based on artificial neural networks (ANN) is proposed. Although, a rich amount of research is available in the field of PV fault detection using ANN, this paper presents a novel methodology based on only two inputs for the training, validating and testing of the Radial Basis Function (RBF) network achieving unprecedented detection accuracy of 98.1%. The proposed methodology goes beyond data normalisation and implements a ‘mapping of inputs’ approach to the data set before exposing it to the network for training. The accuracy of the proposed network is further endorsed through testing of the network in partial shading and overcast conditions.

KW - Photovoltaic (PV)

KW - Artificial Intelligence

KW - Machine learning

KW - Fault detection

KW - renewable energy

KW - RBF network

U2 - 10.3934/ElectrEng.2020.1.1

DO - 10.3934/ElectrEng.2020.1.1

M3 - Article

VL - 4

SP - 1

EP - 18

JO - AIMS Electronics and Electrical Engineering

JF - AIMS Electronics and Electrical Engineering

SN - 2578-1588

IS - 1

ER -