Structural damage identification using modified Hilbert–Huang transform and support vector machine

Diao, Yansong; Jia, Dantong; Liu, Guodong; Sun, Zhanliang; Xu, Jing

doi:10.1007/s13349-021-00509-5

Cited by 24 publications

(11 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The damage location and quantification results were good. Diao et al [115] used a combination of the Hilbert-Huang transform and SVM for SDD. The damage features were constructed using the Hilbert-Huang transform from the measured vibration signals, whereas SVM classification was used for localizing the damage location, and regression was used for quantifying the damage severity.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Temperature Effect on Vibration Properties and Vibration-Based Damage Identification of Bridge Structures: A Literature Review

2022

View full text Add to dashboard Cite

In civil engineering structures, modal changes produced by environmental conditions, especially temperature, can be equivalent to or greater than the ones produced by damage. Therefore, it is necessary to distinguish the variations in structural properties caused by environmental changes from those caused by structural damages. In this paper, we present a review of the technical literature concerning variations in the vibration properties of civil structures under varying temperature conditions and damage identification methods for bridge structures. First, the literature on the effect of temperature on vibration properties is roughly divided into experimental and theoretical studies. According to the classification of theoretical research methods, the progress in research on the probability analysis method, the artificial intelligence method, and the optimization algorithm method in this field is reviewed. Based on the different methods of experimental research employed in this field, the experimental research is reviewed according to qualitative and quantitative analyses. Then, damage identification methods for bridge structures are reviewed, considering data-based and model-based methods. Finally, different research methods are summarized.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

Temperature Effect on Vibration Properties and Vibration-Based Damage Identification of Bridge Structures: A Literature Review

2022

View full text Add to dashboard Cite

show abstract

“…Now with Proposition 1 and Proposition 2, we are ready to characterize the set of gradient vectors in (13).…”

Section: Propositionmentioning

confidence: 99%

Global relaxation-based LP–Newton method formultiple hyperparameter selection in support vector classification with feature selection

Li,

Qian,

Zemkoho

2023

Preprint

View full text Add to dashboard Cite

Support vector classification (SVC) is an effective tool for classification tasks in machine learning. Its performance relies on the selection of appropriate hyperparameters. In this paper, our focus is on identifying the optimal value for the regularization hyperparameter \(C\), as well as determining the bounds on the features in a SVC problem. This implies that the number of hyperparameters in our SVC can potentially be very large. It is very well-known in machine learning that this could lead to the so-called {\em curse of dimensionality}. To address this challenge of multiple hyperparameter selection, the problem is formulated as a bilevel optimization problem, which is then transformed into a mathematical program with equilibrium constraints (MPEC). Our first contribution involves proving the fulfillment of a Mangasarian–Fromovitz constraint qualification tailored to the latter reformulation of the problem. Furthermore, we introduce a novel linear programming (LP)-Newton-based global relaxation method (GRLPN) for solving this problem and provide corresponding convergence results. Typically, in global relaxation methods for MPECs, the algorithm for the corresponding subproblem is treated as a blackbox. Possibly for the first time in the literature, the subproblem is specifically studied in detail. Numerical experiments substantiate the superiority of GRLPN over grid search and the global relaxation solved by the well-known nonlinear programming solver SNOPT.

show abstract

“…The shock component in the vibration signal of the SSFST system accounts for a large proportion, the frequency component is very rich, and the vibration information contained in different frequency bands is different [ 27 ]. When analyzing the vibration signal of the SSFST system, the Intrinsic Mode Function (IMF) components of each order after the Empirical mode decomposition (EMD) will contain the natural vibration components of different frequency bands caused by different vibration isolation methods [ 28 , 29 , 30 , 31 ].…”

Section: Hilbert–huang Transform Analysismentioning

confidence: 99%

Experimental Research on Vibration-Damping Effect of Combined Shear Hinge Prefabricated Steel Spring Floating Slab Track

Zeng

Huang

et al. 2022

Sensors

View full text Add to dashboard Cite

Objective: The cast-in-place steel spring floating slab track (SSFST) is difficult to maintain and repair, while the mechanical strength of the end of the traditional prefabricated SSFST is poor. In order to overcome the above shortcomings, a shear-hinge-combined prefabricated SSFST was developed, and an indoor test was carried out to analyze its vibration-damping effect. Methods: A combined shear hinge SSFST connection model with two length sizes was established. The dynamic response amplitude and frequency response characteristics of the foundation (ground) under different isolator installations and fatigue loads were studied, and the vibration-damping performance of two sizes of combined shear hinge SSFST was evaluated. Results: The vibration-damping effect of the steel spring vibration isolator mainly acts in the middle and low-frequency bands of 16–400 Hz, and the vibration near 10 Hz will be aggravated after the vibration isolator is installed. The vibration index and variation law of the two sizes of SSFST are similar, and the vibration response of 4.8 m SSFST is slightly less than 3.6 m SSFST. There is almost no change in each index when the load is 5 million times, and there is a certain range of change when the load is 10 million times, but the overall change is small. Conclusions: The combined shear hinge prefabricated SSFST can have an excellent isolation effect on vibration and can still maintain good vibration-damping ability within 10 million fatigue loads (about 5 years); 4.8 m SSFST should be laid in straight sections with higher train speeds, while 3.6 m SSFST should be applied in curved sections to ensure smooth lines.

show abstract

Structural damage identification using modified Hilbert–Huang transform and support vector machine

Cited by 24 publications

References 47 publications

Temperature Effect on Vibration Properties and Vibration-Based Damage Identification of Bridge Structures: A Literature Review

Temperature Effect on Vibration Properties and Vibration-Based Damage Identification of Bridge Structures: A Literature Review

Global relaxation-based LP–Newton method formultiple hyperparameter selection in support vector classification with feature selection

Experimental Research on Vibration-Damping Effect of Combined Shear Hinge Prefabricated Steel Spring Floating Slab Track

Contact Info

Product

Resources

About