Optimised Neural Network Model for Wind Turbine DFIG Converter Fault Diagnosis

This research introduces an enhanced fault detection approach, variational mode decomposition (VMD), for identifying open-circuit IGBT faults in the grid-side converter (GSC) of a doubly fed induction generator (DFIG) wind turbine system. VMD has many advantages over other decomposition methods, not...

Full description

Saved in:
Bibliographic Details
Main Authors: Ramesh Kumar Behara, Akshay Kumar Saha
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/13/3409
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117909692547072
author Ramesh Kumar Behara
Akshay Kumar Saha
author_facet Ramesh Kumar Behara
Akshay Kumar Saha
author_sort Ramesh Kumar Behara
collection DOAJ
description This research introduces an enhanced fault detection approach, variational mode decomposition (VMD), for identifying open-circuit IGBT faults in the grid-side converter (GSC) of a doubly fed induction generator (DFIG) wind turbine system. VMD has many advantages over other decomposition methods, notably for non-stationary signals and noise. VMD’s robustness stems from its ability to decompose a signal into intrinsic mode functions (IMFs) with well-defined centre frequencies and bandwidths. The proposed methodology integrates VMD with a hybrid convolutional neural network–long short-term memory (CNN-LSTM) architecture to efficiently extract and learn distinctive temporal and spectral properties from three-phase current sources. Ten operational scenarios with a wind speed range of 5–16 m/s were simulated using a comprehensive MATLAB/Simulink version R2022b model, including one healthy condition and nine unique IGBT failure conditions. The obtained current signals were decomposed via VMD to extract essential frequency components, which were normalised and utilised as input sequences for deep learning models. A comparative comparison of CNN-LSTM and CNN-only classifiers revealed that the CNN-LSTM model attained the greatest classification accuracy of 88.00%, exhibiting enhanced precision and resilience in noisy and dynamic environments. These findings emphasise the efficiency of integrating advanced signal decomposition with deep sequential learning for real-time, high-precision fault identification in wind turbine power electronic converters.
format Article
id doaj-art-82c538d4b1be4489bde7f44c8d0e2bb1
institution OA Journals
issn 1996-1073
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-82c538d4b1be4489bde7f44c8d0e2bb12025-08-20T02:35:59ZengMDPI AGEnergies1996-10732025-06-011813340910.3390/en18133409Optimised Neural Network Model for Wind Turbine DFIG Converter Fault DiagnosisRamesh Kumar Behara0Akshay Kumar Saha1Electrical, Electronic, and Computer Engineering, University of KwaZulu-Natal, Durban 4041, South AfricaElectrical, Electronic, and Computer Engineering, University of KwaZulu-Natal, Durban 4041, South AfricaThis research introduces an enhanced fault detection approach, variational mode decomposition (VMD), for identifying open-circuit IGBT faults in the grid-side converter (GSC) of a doubly fed induction generator (DFIG) wind turbine system. VMD has many advantages over other decomposition methods, notably for non-stationary signals and noise. VMD’s robustness stems from its ability to decompose a signal into intrinsic mode functions (IMFs) with well-defined centre frequencies and bandwidths. The proposed methodology integrates VMD with a hybrid convolutional neural network–long short-term memory (CNN-LSTM) architecture to efficiently extract and learn distinctive temporal and spectral properties from three-phase current sources. Ten operational scenarios with a wind speed range of 5–16 m/s were simulated using a comprehensive MATLAB/Simulink version R2022b model, including one healthy condition and nine unique IGBT failure conditions. The obtained current signals were decomposed via VMD to extract essential frequency components, which were normalised and utilised as input sequences for deep learning models. A comparative comparison of CNN-LSTM and CNN-only classifiers revealed that the CNN-LSTM model attained the greatest classification accuracy of 88.00%, exhibiting enhanced precision and resilience in noisy and dynamic environments. These findings emphasise the efficiency of integrating advanced signal decomposition with deep sequential learning for real-time, high-precision fault identification in wind turbine power electronic converters.https://www.mdpi.com/1996-1073/18/13/3409doubly fed induction generatorfault diagnosisgrid side convertervariational mode decompositionconvolutional neural networklong short-term memory
spellingShingle Ramesh Kumar Behara
Akshay Kumar Saha
Optimised Neural Network Model for Wind Turbine DFIG Converter Fault Diagnosis
Energies
doubly fed induction generator
fault diagnosis
grid side converter
variational mode decomposition
convolutional neural network
long short-term memory
title Optimised Neural Network Model for Wind Turbine DFIG Converter Fault Diagnosis
title_full Optimised Neural Network Model for Wind Turbine DFIG Converter Fault Diagnosis
title_fullStr Optimised Neural Network Model for Wind Turbine DFIG Converter Fault Diagnosis
title_full_unstemmed Optimised Neural Network Model for Wind Turbine DFIG Converter Fault Diagnosis
title_short Optimised Neural Network Model for Wind Turbine DFIG Converter Fault Diagnosis
title_sort optimised neural network model for wind turbine dfig converter fault diagnosis
topic doubly fed induction generator
fault diagnosis
grid side converter
variational mode decomposition
convolutional neural network
long short-term memory
url https://www.mdpi.com/1996-1073/18/13/3409
work_keys_str_mv AT rameshkumarbehara optimisedneuralnetworkmodelforwindturbinedfigconverterfaultdiagnosis
AT akshaykumarsaha optimisedneuralnetworkmodelforwindturbinedfigconverterfaultdiagnosis