Structural damage detection based on variational mode decomposition and kernel PCA-based support vector machine

Bisheh, Hossein Babajanian; Amiri, Gholamreza Ghodrati

doi:10.1016/j.engstruct.2022.115565

Cited by 32 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PA allowed establishing references by means of the predictions of the classes included in the study. Based on the initial predictions, the proportion of correct and incorrect classifications was determined [46]. The UA made it possible to recognize the probability that a classified category effectively represents the class determined in the field.…”

Section: Validation Of Coverage Classificationmentioning

confidence: 99%

Modeling the Influence of Changes in the Edaphic Environment on the Ecosystem Valuation of the Zone of Influence of the Ozogoche and Atillo Lake Systems in Ecuador

Pazmiño,

Felipe,

Vallbé

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Ecosystem valuation (EV) of soil resources is essential for understanding changes in environmental services in monetary terms. A lack of this information, which includes economic indices, hinders the optimal management of natural resources. This study evaluated the influence of changes in the edaphic ecosystem on the EV of the zone of influence of the Ozogoche and Atillo lake systems in Ecuador. The classification was carried out through spectral indices and support vector machines (SVMs), and the EV was determined through opportunity costs including environmental service provisioning and indirect use. The land use and EV classification methods were performed efficiently; the degradation trend was constant. The Modified Water Difference Index was the most efficient in the extraction of water bodies, with an accuracy of 91%. The SVMs algorithm, in recognizing coverage in general, had an overall accuracy of 85%. The adjustment made to the SVMs algorithm to improve the selection of hyperparameters was effective; a robust architecture of the algorithm in terms of automation was achieved. Between 2000 and 2020, moorland, water and wetland degraded by 19%, 2% and 3.4%, respectively. In 2000, the EV as a function of avoided CO2 content was USD 8.00 × 106; in 2010 and 2020, it was USD 6.00 × 106 and USD 5.00 × 106, respectively.

show abstract

Section: Validation Of Coverage Classificationmentioning

confidence: 99%

Modeling the Influence of Changes in the Edaphic Environment on the Ecosystem Valuation of the Zone of Influence of the Ozogoche and Atillo Lake Systems in Ecuador

Pazmiño,

Felipe,

Vallbé

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Zhang et al [34] employed the VMD algorithm to extract the GNSS low-frequency displacement of the bridge and combined it with high-frequency vibration measured by the speedometer; the fused results proved that VMD was resistant to noise and could calculate the bridge's spectral properties. Bisheh and Amiri [35] detected the modal parameters of two bridges from the free vibration response based on VMD and demonstrated the feasibility of this method. One disadvantage of VMD is that it requires setting the number of modal decomposition K in advance.…”

Section: Introductionmentioning

confidence: 99%

Modal frequencies evaluation of a damaged bridge using RCVMD algorithm based on sensor dynamic responses

Xiong

Shang

Liu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

This paper aims to employ high-rate global navigation satellite system real-time kinematic (GNSS-RTK) and triaxial accelerometer sensors to evaluate the modal frequencies of a damaged long-span bridge based on the proposed modified variational mode decomposition (VMD) algorithm. Firstly, in the modified VMD, the relative root mean square error (RRMSE) was presented to optimize the decomposition parameter K, the correlation criterion was introduced to select the suitable intrinsic mode function (IMF) components. The above procedure is called the RCVMD algorithm. Subsequently, the performance comparison evaluation experiments proved that the RCVMD algorithm was more advantageous in the decomposition and reconstruction of signals, had a better noise reduction effect in the signal with different noise levels, and was suitable to process the actual measurement response. Finally, in the field experiment, the modal frequencies of the damaged bridge were correctly detected from the GNSS-RTK displacement and acceleration responses according to the RCVMD algorithm, and the accelerometer picked up the high-order structural frequencies, demonstrating the reliability of the proposed method. The frequency characteristics of the damaged bridge are different from the normal state. The first and third-order frequencies increase, which is especially obvious in the first-order frequency, yet the second-order frequency decreases. The measured results have practical applications and can provide data support for the maintenance of the damaged bridge.

show abstract

“…However, there are mode mixing in the wavelet analysis and empirical mode decomposition. Variational mode decomposition can separate harmonic signals close to the frequency range without being affected by the sampling frequency, which can avoid mode mixing [8][9][10]. Variational mode decomposition is widely applied to feature extraction in the fault diagnosis fields.…”

Section: Introductionmentioning

confidence: 99%

Fault Detection of Gearbox by Multivariate Extended Variational Mode Decomposition-Based Time-Frequency Images and Incremental RVM Algorithm

Nao

Wang

2023

Preprint

View full text Add to dashboard Cite

A novel detection method based on multivariate extended variational mode decomposition-based time-frequency images and incremental RVM algorithm(MEVMDTFI-IRVM) is presented for fault detection of gearbox. The time-frequency images are constructed by multivariate extended variational mode decomposition. Compared with single-variable modal decomposition method, multivariate extended variational mode decomposition not only has an accurate mathematical framework, but also possible to better align the common frequency mode of the signal. The incremental RVM algorithm is presented for fault detection of gearbox based on the time-frequency images constructed by multivariate extended variational mode decomposition. The testing results demonstrate that the detection results of MEVMDTFI-IRVM for gearbox are stable, in addition, the detection results of MEVMDTFI-IRVM for gearbox are better than those of variational mode decomposition-based time-frequency images and incremental RVM algorithm (VMDTFI-IRVM), variational mode decomposition- RVM algorithm(VMD-RVM),and traditional RVM algorithm.

show abstract

Structural damage detection based on variational mode decomposition and kernel PCA-based support vector machine

Cited by 32 publications

References 36 publications

Modeling the Influence of Changes in the Edaphic Environment on the Ecosystem Valuation of the Zone of Influence of the Ozogoche and Atillo Lake Systems in Ecuador

Modeling the Influence of Changes in the Edaphic Environment on the Ecosystem Valuation of the Zone of Influence of the Ozogoche and Atillo Lake Systems in Ecuador

Modal frequencies evaluation of a damaged bridge using RCVMD algorithm based on sensor dynamic responses

Fault Detection of Gearbox by Multivariate Extended Variational Mode Decomposition-Based Time-Frequency Images and Incremental RVM Algorithm

Contact Info

Product

Resources

About