A diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faults

Fault diagnosis occupies a pivotal position within the domain of machine and equipment management. Existing methods, however, often exhibit limitations in their scope of application, typically focusing on specific types of signals or faults in individual mechanical components while being constrained...

Full description

Saved in:
Bibliographic Details
Main Authors: Bin Wang, Manyi Wang, Yadong Xu, Liangkuan Wang, Shiyu Chen, Xuanshi Chen
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-08-01
Series:Defence Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214914725001308
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849404745273311232
author Bin Wang
Manyi Wang
Yadong Xu
Liangkuan Wang
Shiyu Chen
Xuanshi Chen
author_facet Bin Wang
Manyi Wang
Yadong Xu
Liangkuan Wang
Shiyu Chen
Xuanshi Chen
author_sort Bin Wang
collection DOAJ
description Fault diagnosis occupies a pivotal position within the domain of machine and equipment management. Existing methods, however, often exhibit limitations in their scope of application, typically focusing on specific types of signals or faults in individual mechanical components while being constrained by data types and inherent characteristics. To address the limitations of existing methods, we propose a fault diagnosis method based on graph neural networks (GNNs) embedded with multirelationships of intrinsic mode functions (MIMF). The approach introduces a novel graph topological structure constructed from the features of intrinsic mode functions (IMFs) of monitored signals and their multirelationships. Additionally, a graph-level based fault diagnosis network model is designed to enhance feature learning capabilities for graph samples and enable flexible application across diverse signal sources and devices. Experimental validation with datasets including independent vibration signals for gear fault detection, mixed vibration signals for concurrent gear and bearing faults, and pressure signals for hydraulic cylinder leakage characterization demonstrates the model's adaptability and superior diagnostic accuracy across various types of signals and mechanical systems.
format Article
id doaj-art-b98e193b2c3b4aec9f34c405fef09240
institution Kabale University
issn 2214-9147
language English
publishDate 2025-08-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Defence Technology
spelling doaj-art-b98e193b2c3b4aec9f34c405fef092402025-08-20T03:36:53ZengKeAi Communications Co., Ltd.Defence Technology2214-91472025-08-015036437310.1016/j.dt.2025.04.014A diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faultsBin Wang0Manyi Wang1Yadong Xu2Liangkuan Wang3Shiyu Chen4Xuanshi Chen5School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China; Corresponding author.School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, 210094, ChinaNorthwest Institute of Mechanical and Electrical Engineering, Xianyang, 712099, ChinaWuxi Vocational Institute of Arts & Technology, Wuxi, 214200, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing, 210094, ChinaFault diagnosis occupies a pivotal position within the domain of machine and equipment management. Existing methods, however, often exhibit limitations in their scope of application, typically focusing on specific types of signals or faults in individual mechanical components while being constrained by data types and inherent characteristics. To address the limitations of existing methods, we propose a fault diagnosis method based on graph neural networks (GNNs) embedded with multirelationships of intrinsic mode functions (MIMF). The approach introduces a novel graph topological structure constructed from the features of intrinsic mode functions (IMFs) of monitored signals and their multirelationships. Additionally, a graph-level based fault diagnosis network model is designed to enhance feature learning capabilities for graph samples and enable flexible application across diverse signal sources and devices. Experimental validation with datasets including independent vibration signals for gear fault detection, mixed vibration signals for concurrent gear and bearing faults, and pressure signals for hydraulic cylinder leakage characterization demonstrates the model's adaptability and superior diagnostic accuracy across various types of signals and mechanical systems.http://www.sciencedirect.com/science/article/pii/S2214914725001308Fault diagnosisGraph neural networksGraph topological structureIntrinsic mode functionsFeature learning
spellingShingle Bin Wang
Manyi Wang
Yadong Xu
Liangkuan Wang
Shiyu Chen
Xuanshi Chen
A diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faults
Defence Technology
Fault diagnosis
Graph neural networks
Graph topological structure
Intrinsic mode functions
Feature learning
title A diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faults
title_full A diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faults
title_fullStr A diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faults
title_full_unstemmed A diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faults
title_short A diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faults
title_sort diagnosis method based on graph neural networks embedded with multirelationships of intrinsic mode functions for multiple mechanical faults
topic Fault diagnosis
Graph neural networks
Graph topological structure
Intrinsic mode functions
Feature learning
url http://www.sciencedirect.com/science/article/pii/S2214914725001308
work_keys_str_mv AT binwang adiagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT manyiwang adiagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT yadongxu adiagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT liangkuanwang adiagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT shiyuchen adiagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT xuanshichen adiagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT binwang diagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT manyiwang diagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT yadongxu diagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT liangkuanwang diagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT shiyuchen diagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults
AT xuanshichen diagnosismethodbasedongraphneuralnetworksembeddedwithmultirelationshipsofintrinsicmodefunctionsformultiplemechanicalfaults