Computational Technology Resources - CCC

X. Zhang, T. Wang, J. Yang, "Fatigue Crack Damage Detection Using Gaussian Mixture Model Based on Information Entropy Under Time-Varying Temperature", in J. Pombo, (Editor), "Proceedings of the Sixth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 7, Paper 7.1, 2024, doi:10.4203/ccc.7.7.1

Keywords: Lamb wave, information entropy, fatigue crack, time-varying temperature, Gaussian mixture model, high speed train.

Abstract

High-speed train structures operate under time-varying conditions, which poses a significant challenge in the field of PHM due to uncertainties introduced in the extraction of damage indexes from signals. This paper presents a new fatigue crack size quantification method based on information entropy unde variable temperature environment. Two new information entropy are proposed: energy singular spectral entropy (ES) and power singular spectral entropy (PS). The baseline Gaussian mixture model is constructed on the information entropy acquired under time-varying temperature when the structure is in a healthy state. The on-line Gaussian mixture model is constructed through the online update mechanism of moving feature sample set. The minimum matching Kullback–Leibler (KL) distance of the probability component is used to quantitatively characterize the cumulative migration trend of the Gaussian mixture model under damage to realize damage detection. The framework proposed in this paper is applied to Lamb wave data collected from fatigue crack experiments under variable temperature environment. The experimental results verify the reliable fatigue crack detection performance of Gaussian mixture model-KL method under variable temperature environment.

download the full-text of this paper (PDF, 1843 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 7 PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 7.1 Fatigue Crack Damage Detection Using Gaussian Mixture Model Based on Information Entropy Under Time-Varying Temperature X. Zhang, T. Wang and J. Yang School of Traffic and Transportation Engineering, Central South University, Changsha, China doi:10.4203/ccc.7.7.1 Full Bibliographic Reference for this paper X. Zhang, T. Wang, J. Yang, "Fatigue Crack Damage Detection Using Gaussian Mixture Model Based on Information Entropy Under Time-Varying Temperature", in J. Pombo, (Editor), "Proceedings of the Sixth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 7, Paper 7.1, 2024, doi:10.4203/ccc.7.7.1 Keywords: Lamb wave, information entropy, fatigue crack, time-varying temperature, Gaussian mixture model, high speed train. Abstract High-speed train structures operate under time-varying conditions, which poses a significant challenge in the field of PHM due to uncertainties introduced in the extraction of damage indexes from signals. This paper presents a new fatigue crack size quantification method based on information entropy unde variable temperature environment. Two new information entropy are proposed: energy singular spectral entropy (ES) and power singular spectral entropy (PS). The baseline Gaussian mixture model is constructed on the information entropy acquired under time-varying temperature when the structure is in a healthy state. The on-line Gaussian mixture model is constructed through the online update mechanism of moving feature sample set. The minimum matching Kullback–Leibler (KL) distance of the probability component is used to quantitatively characterize the cumulative migration trend of the Gaussian mixture model under damage to realize damage detection. The framework proposed in this paper is applied to Lamb wave data collected from fatigue crack experiments under variable temperature environment. The experimental results verify the reliable fatigue crack detection performance of Gaussian mixture model-KL method under variable temperature environment. download the full-text of this paper (PDF, 1843 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions