Prior Knowledge-Informed Graph Neural Network with Multi-Source Data-Weighted Fusion for Intelligent Bogie Fault Diagnosis

The current multi-source fusion fault diagnosis algorithm rarely considers the information correlation of multi-sensor networks and the important difference between multi-sensors. Aiming at this challenge, we propose an intelligent fault identification method for high-speed railway bogie based on th...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuanxing Huang, Bofeng Cui, Xianqun Mao, Jinsong Yang
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Machines
Subjects:
Online Access:https://www.mdpi.com/2075-1702/12/12/838
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241236614512640
author Yuanxing Huang
Bofeng Cui
Xianqun Mao
Jinsong Yang
author_facet Yuanxing Huang
Bofeng Cui
Xianqun Mao
Jinsong Yang
author_sort Yuanxing Huang
collection DOAJ
description The current multi-source fusion fault diagnosis algorithm rarely considers the information correlation of multi-sensor networks and the important difference between multi-sensors. Aiming at this challenge, we propose an intelligent fault identification method for high-speed railway bogie based on the graph neural network embedded with prior knowledge, which brings the spatial information of the sensor network into the diagnosis algorithm and re-weights each sensor according to the diagnosis results. Firstly, the time–domain correlation of vibration signals between bogie sensor networks is calculated as the prior knowledge. Then, based on the spatial topological relationship of the sensors, the graph correlation matrix of the network is established. Further, the importance of each sensor is dynamically analyzed and updated together with the training process. The proposed method is tested on a high-precision bogie test bed, and the experimental results demonstrate the effectiveness and superiority of the proposed method.
format Article
id doaj-art-0a6c6dd94d624c3cb0d33fc6479d9bbd
institution OA Journals
issn 2075-1702
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Machines
spelling doaj-art-0a6c6dd94d624c3cb0d33fc6479d9bbd2025-08-20T02:00:39ZengMDPI AGMachines2075-17022024-11-01121283810.3390/machines12120838Prior Knowledge-Informed Graph Neural Network with Multi-Source Data-Weighted Fusion for Intelligent Bogie Fault DiagnosisYuanxing Huang0Bofeng Cui1Xianqun Mao2Jinsong Yang3Marine Design and Research Institute of China, Shanghai 200011, ChinaMarine Design and Research Institute of China, Shanghai 200011, ChinaMarine Design and Research Institute of China, Shanghai 200011, ChinaSchool of Traffic & Transportation Engineering, Central South University, Changsha 410004, ChinaThe current multi-source fusion fault diagnosis algorithm rarely considers the information correlation of multi-sensor networks and the important difference between multi-sensors. Aiming at this challenge, we propose an intelligent fault identification method for high-speed railway bogie based on the graph neural network embedded with prior knowledge, which brings the spatial information of the sensor network into the diagnosis algorithm and re-weights each sensor according to the diagnosis results. Firstly, the time–domain correlation of vibration signals between bogie sensor networks is calculated as the prior knowledge. Then, based on the spatial topological relationship of the sensors, the graph correlation matrix of the network is established. Further, the importance of each sensor is dynamically analyzed and updated together with the training process. The proposed method is tested on a high-precision bogie test bed, and the experimental results demonstrate the effectiveness and superiority of the proposed method.https://www.mdpi.com/2075-1702/12/12/838fault diagnosisdeep learningbogiegraph neural network
spellingShingle Yuanxing Huang
Bofeng Cui
Xianqun Mao
Jinsong Yang
Prior Knowledge-Informed Graph Neural Network with Multi-Source Data-Weighted Fusion for Intelligent Bogie Fault Diagnosis
Machines
fault diagnosis
deep learning
bogie
graph neural network
title Prior Knowledge-Informed Graph Neural Network with Multi-Source Data-Weighted Fusion for Intelligent Bogie Fault Diagnosis
title_full Prior Knowledge-Informed Graph Neural Network with Multi-Source Data-Weighted Fusion for Intelligent Bogie Fault Diagnosis
title_fullStr Prior Knowledge-Informed Graph Neural Network with Multi-Source Data-Weighted Fusion for Intelligent Bogie Fault Diagnosis
title_full_unstemmed Prior Knowledge-Informed Graph Neural Network with Multi-Source Data-Weighted Fusion for Intelligent Bogie Fault Diagnosis
title_short Prior Knowledge-Informed Graph Neural Network with Multi-Source Data-Weighted Fusion for Intelligent Bogie Fault Diagnosis
title_sort prior knowledge informed graph neural network with multi source data weighted fusion for intelligent bogie fault diagnosis
topic fault diagnosis
deep learning
bogie
graph neural network
url https://www.mdpi.com/2075-1702/12/12/838
work_keys_str_mv AT yuanxinghuang priorknowledgeinformedgraphneuralnetworkwithmultisourcedataweightedfusionforintelligentbogiefaultdiagnosis
AT bofengcui priorknowledgeinformedgraphneuralnetworkwithmultisourcedataweightedfusionforintelligentbogiefaultdiagnosis
AT xianqunmao priorknowledgeinformedgraphneuralnetworkwithmultisourcedataweightedfusionforintelligentbogiefaultdiagnosis
AT jinsongyang priorknowledgeinformedgraphneuralnetworkwithmultisourcedataweightedfusionforintelligentbogiefaultdiagnosis