An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural Network

This study constructs a power switching device open-circuit fault diagnosis model for a three-level neutral point clamped inverter based on the multi-scale shuffled convolutional neural network (MSSCNN) and extracts and classifies the fault information contained in the output current of inverters. T...

Full description

Bibliographic Details
Main Authors: Yan Yan, Jiaqi Wu, Yanfei Cao, Bo Liu, Chen Li, Tingna Shi
Format: Article
Language:English
Published: MDPI AG 2024-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/6/1745
_version_ 1797239379699171328
author Yan Yan
Jiaqi Wu
Yanfei Cao
Bo Liu
Chen Li
Tingna Shi
author_facet Yan Yan
Jiaqi Wu
Yanfei Cao
Bo Liu
Chen Li
Tingna Shi
author_sort Yan Yan
collection DOAJ
description This study constructs a power switching device open-circuit fault diagnosis model for a three-level neutral point clamped inverter based on the multi-scale shuffled convolutional neural network (MSSCNN) and extracts and classifies the fault information contained in the output current of inverters. The model employs depthwise separable convolution and channel shuffle techniques to improve diagnostic accuracy and reduce model complexity. The experimental results show that the new model has lower model complexity, better noise resistance and higher average diagnostic accuracy compared with fault diagnosis models based on CNN, ResNet, ShuffleNet V2 and Mobilenet V3 networks.
first_indexed 2024-04-24T17:50:36Z
format Article
id doaj.art-7b075c6b90f649ae96d25ed2b9dbc95a
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-04-24T17:50:36Z
publishDate 2024-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-7b075c6b90f649ae96d25ed2b9dbc95a2024-03-27T14:03:39ZengMDPI AGSensors1424-82202024-03-01246174510.3390/s24061745An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural NetworkYan Yan0Jiaqi Wu1Yanfei Cao2Bo Liu3Chen Li4Tingna Shi5College of Electrical Engineering, Zhejiang University, Hangzhou 310027, ChinaCollege of Electrical Engineering, Zhejiang University, Hangzhou 310027, ChinaCollege of Electrical Engineering, Zhejiang University, Hangzhou 310027, ChinaCollege of Electrical Engineering, Zhejiang University, Hangzhou 310027, ChinaCollege of Electrical Engineering, Zhejiang University, Hangzhou 310027, ChinaCollege of Electrical Engineering, Zhejiang University, Hangzhou 310027, ChinaThis study constructs a power switching device open-circuit fault diagnosis model for a three-level neutral point clamped inverter based on the multi-scale shuffled convolutional neural network (MSSCNN) and extracts and classifies the fault information contained in the output current of inverters. The model employs depthwise separable convolution and channel shuffle techniques to improve diagnostic accuracy and reduce model complexity. The experimental results show that the new model has lower model complexity, better noise resistance and higher average diagnostic accuracy compared with fault diagnosis models based on CNN, ResNet, ShuffleNet V2 and Mobilenet V3 networks.https://www.mdpi.com/1424-8220/24/6/1745NPC inverteropen-circuit faultconvolutional neural networkfault diagnosis
spellingShingle Yan Yan
Jiaqi Wu
Yanfei Cao
Bo Liu
Chen Li
Tingna Shi
An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural Network
Sensors
NPC inverter
open-circuit fault
convolutional neural network
fault diagnosis
title An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural Network
title_full An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural Network
title_fullStr An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural Network
title_full_unstemmed An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural Network
title_short An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural Network
title_sort open circuit fault diagnosis method for three level neutral point clamped inverters based on multi scale shuffled convolutional neural network
topic NPC inverter
open-circuit fault
convolutional neural network
fault diagnosis
url https://www.mdpi.com/1424-8220/24/6/1745
work_keys_str_mv AT yanyan anopencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT jiaqiwu anopencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT yanfeicao anopencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT boliu anopencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT chenli anopencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT tingnashi anopencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT yanyan opencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT jiaqiwu opencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT yanfeicao opencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT boliu opencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT chenli opencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork
AT tingnashi opencircuitfaultdiagnosismethodforthreelevelneutralpointclampedinvertersbasedonmultiscaleshuffledconvolutionalneuralnetwork