Detecting fault in photovoltaic system with a hybrid PDACNN-IDMOA methodology

PV system fault detection is essential since unidentified problems lead to energy loss, safety hazards and financial losses due to reduced power output and possible component damage. Early detection contributes to a sustainable and effective solar solution by ensuring optimal performance, minimizing...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Electrical engineering Ročník 107; číslo 4; s. 4393 - 4405
Hlavní autoři: Rashmi, G., Manjusha, M., Anish John Paul, M., Juliet Rose, D. B.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2025
Springer Nature B.V
Témata:
Accuracy
Alternative energy sources
Arrays
Artificial intelligence
Artificial neural networks
Back propagation networks
Classification
Damage detection
Deep learning
Economics and Management
Electrical Engineering
Electrical Machines and Networks
Energy Policy
Energy storage
Engineering
Fault detection
Genetic algorithms
Machine learning
Neural networks
Optimization techniques
Original Paper
Particle swarm optimization
Photovoltaic cells
Power Electronics
R&D
Radiation
Renewable resources
Research & development
Solar energy
Supervised learning
Support vector machines
Inverter
Fault detection
Battery
Grid
Converter
Filter and modelling of PV system
Photovoltaic panel
ISSN:0948-7921, 1432-0487
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:PV system fault detection is essential since unidentified problems lead to energy loss, safety hazards and financial losses due to reduced power output and possible component damage. Early detection contributes to a sustainable and effective solar solution by ensuring optimal performance, minimizing risks and maximizing financial benefits. Hence research on the detection of fault in photovoltaic (PV) systems is quite important. This paper proposes a hybrid technique for detecting the fault in PV systems. The proposed hybrid method is the combined performance of both the pyramidal dilation attention convolutional neural network (PDACNN) and improved dwarf mongoose optimization algorithm (IDMOA). Commonly it is referred as PDACNN-IDMOA technique. The major goal of the proposed method is to improve the detection of fault in PV system. In this manuscript, the hybrid PDACNN-IDMOA approach is suggested. The PDACNN approach is used for the fault detection in the PV system, and the IDMOA is used to optimize the weight parameter of the PDACNN. Moreover, the result of the system critic behaviour is researched, where the critic is a function of control fault. By then, the proposed framework has been integrated into the MATLAB/Simulink workspace, and existing methods are being used to compute its execution. The proposed method shows better outcomes than all existing methods like genetic algorithm–support vector machine (GA-SVM), backpropagation neural network–particle swarm optimization (BPNN-PSO) and salp swarm optimization–supervised machine learning (SSA-SML). The PV system breakdown can be found using the proposed method. The outcome indicates that, in comparison with existing methods, the proposed method's based RMSE value is 3.521* 10 - 4 is smaller than the existing approaches.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0948-7921
1432-0487
DOI:10.1007/s00202-024-02702-3