Lifelong Learning-Enabled Fractional Order-Convolutional Encoder Model for Open-Circuit Fault Diagnosis of Power Converters Under Multi-Conditions

Open-circuit (OC) faults in power converters are common issues in motor drive systems, significantly affecting the safe and stable operation of the system. Conventional models can accurately diagnose faults under a single operating condition. However, when conditions change, these models may fail to...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao Li, Enyu Wang, Jun Yang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/6/1884
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850279831745331200
author Tao Li
Enyu Wang
Jun Yang
author_facet Tao Li
Enyu Wang
Jun Yang
author_sort Tao Li
collection DOAJ
description Open-circuit (OC) faults in power converters are common issues in motor drive systems, significantly affecting the safe and stable operation of the system. Conventional models can accurately diagnose faults under a single operating condition. However, when conditions change, these models may fail to recognize new fault features, resulting in a decrease in diagnosis accuracy. To address this challenge, this paper proposes a lifelong learning-enabled fractional order-convolutional encoder model for open-circuit fault diagnosis of power converters under multi-conditions. Firstly, the model automatically extracts and identifies fault signal features using the convolutional module and the encoder module, respectively. Subsequently, the model’s iterative computational process is optimized by learning historical gradient information through fractional order, and enhancing the model’s ability to capture the long-term dependencies inherent in fault signals. Finally, a multilevel lifelong learning framework has been established to enable the model to continuously learn the fault features of power converter under multi-conditions, thereby avoiding catastrophic forgetting that can occur when the model learns different tasks. The proposed model effectively addresses the challenge of low fault diagnosis accuracy that occurs when the operating conditions of the power converter change, achieving a diagnosis accuracy of 96.89% across 85 fault categories under multi-conditions.
format Article
id doaj-art-742e6cc95b994cfcbe31c1e2677c8819
institution OA Journals
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-742e6cc95b994cfcbe31c1e2677c88192025-08-20T01:48:58ZengMDPI AGSensors1424-82202025-03-01256188410.3390/s25061884Lifelong Learning-Enabled Fractional Order-Convolutional Encoder Model for Open-Circuit Fault Diagnosis of Power Converters Under Multi-ConditionsTao Li0Enyu Wang1Jun Yang2College of Railway Transportation, Hunan University of Technology, Zhuzhou 412007, ChinaCollege of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaZhuzhou Times New Material Technology Co., Ltd., Zhuzhou 412007, ChinaOpen-circuit (OC) faults in power converters are common issues in motor drive systems, significantly affecting the safe and stable operation of the system. Conventional models can accurately diagnose faults under a single operating condition. However, when conditions change, these models may fail to recognize new fault features, resulting in a decrease in diagnosis accuracy. To address this challenge, this paper proposes a lifelong learning-enabled fractional order-convolutional encoder model for open-circuit fault diagnosis of power converters under multi-conditions. Firstly, the model automatically extracts and identifies fault signal features using the convolutional module and the encoder module, respectively. Subsequently, the model’s iterative computational process is optimized by learning historical gradient information through fractional order, and enhancing the model’s ability to capture the long-term dependencies inherent in fault signals. Finally, a multilevel lifelong learning framework has been established to enable the model to continuously learn the fault features of power converter under multi-conditions, thereby avoiding catastrophic forgetting that can occur when the model learns different tasks. The proposed model effectively addresses the challenge of low fault diagnosis accuracy that occurs when the operating conditions of the power converter change, achieving a diagnosis accuracy of 96.89% across 85 fault categories under multi-conditions.https://www.mdpi.com/1424-8220/25/6/1884lifelong learningpower converteropen-circuit faultfault diagnosisfractional order
spellingShingle Tao Li
Enyu Wang
Jun Yang
Lifelong Learning-Enabled Fractional Order-Convolutional Encoder Model for Open-Circuit Fault Diagnosis of Power Converters Under Multi-Conditions
Sensors
lifelong learning
power converter
open-circuit fault
fault diagnosis
fractional order
title Lifelong Learning-Enabled Fractional Order-Convolutional Encoder Model for Open-Circuit Fault Diagnosis of Power Converters Under Multi-Conditions
title_full Lifelong Learning-Enabled Fractional Order-Convolutional Encoder Model for Open-Circuit Fault Diagnosis of Power Converters Under Multi-Conditions
title_fullStr Lifelong Learning-Enabled Fractional Order-Convolutional Encoder Model for Open-Circuit Fault Diagnosis of Power Converters Under Multi-Conditions
title_full_unstemmed Lifelong Learning-Enabled Fractional Order-Convolutional Encoder Model for Open-Circuit Fault Diagnosis of Power Converters Under Multi-Conditions
title_short Lifelong Learning-Enabled Fractional Order-Convolutional Encoder Model for Open-Circuit Fault Diagnosis of Power Converters Under Multi-Conditions
title_sort lifelong learning enabled fractional order convolutional encoder model for open circuit fault diagnosis of power converters under multi conditions
topic lifelong learning
power converter
open-circuit fault
fault diagnosis
fractional order
url https://www.mdpi.com/1424-8220/25/6/1884
work_keys_str_mv AT taoli lifelonglearningenabledfractionalorderconvolutionalencodermodelforopencircuitfaultdiagnosisofpowerconvertersundermulticonditions
AT enyuwang lifelonglearningenabledfractionalorderconvolutionalencodermodelforopencircuitfaultdiagnosisofpowerconvertersundermulticonditions
AT junyang lifelonglearningenabledfractionalorderconvolutionalencodermodelforopencircuitfaultdiagnosisofpowerconvertersundermulticonditions