UAV vision detection method for crane surface cracks based on Faster R-CNN and image segmentation

Article Engineering, Mechanical

Damage identification in steel girder bridges using modal strain energy-based damage index method and artificial neural network

Hooman Nick et al.

Summary: A two-stage damage identification technique was proposed to locate and estimate damages in steel girder bridges successfully. Initially, the damage location was determined using the modal strain energy-based damage index method, and an artificial neural network (ANN) was used for estimation of damage severity. The results indicated the appropriate accuracy and proper performance of the proposed method in estimating the damage magnitude.

ENGINEERING FAILURE ANALYSIS (2021)

Add to Collection

Article Engineering, Civil

Damage identification by wavelet analysis of modal rotation differences

Andrzej Katunin et al.

Summary: This paper presents a novel damage identification approach based on differences in modal rotation fields obtained from shearographic measurements of structures and post-processed with the 2D continuous wavelet transform-based algorithm. It has been shown that the baseline approach improves the sensitivity of the method to damage, allowing for the identification of smaller damage compared to baseline-free methods. Additionally, a new method for reducing boundary effects and improving visualization of results maps has been introduced.

STRUCTURES (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Complex frequency identification using real modal shapes for a structure with proportional damping

Chun-Xu Qu et al.

Summary: This paper proposes an innovative method to identify complex frequencies for a structure with proportional damping using real modal shapes. The method considers the complex property of frequencies and uses Hilbert transform and k-means clustering method to estimate the complex frequencies effectively. The results show that the proposed method can be used in practical engineering.

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING (2021)

Add to Collection

Article Construction & Building Technology

Machine learning model for predicting the crack detection and pattern recognition of geopolymer concrete beams

N. Aravind et al.

Summary: This study focuses on detecting cracks and failure types in concrete structures using computer techniques, employing image processing, machine learning algorithms, and Python programming for validation. It was found that the support vector classifier performed the best in identifying failure patterns with an accuracy of 100%.

CONSTRUCTION AND BUILDING MATERIALS (2021)

Add to Collection

Article Remote Sensing