相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Chemistry, Multidisciplinary
Ramin Ghiasi et al.
Summary: In this study, a non-probabilistic structural damage identification technique based on an optimization algorithm and interval mathematics is proposed for uncertainty-oriented damage identification. The method takes into account uncertainty quantification and provides support for structural health diagnosis under uncertain conditions. The technique is implemented using the slime mold algorithm (SMA) for model updating and an enhanced variant of SMA (ESMA) is developed. Results show that the proposed method reduces computation time and improves the certainty of damage detection.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Ramin Ghiasi et al.
Summary: This paper proposes a novel approach using a non-probabilistic surrogate model based on WWLS-SVM for uncertainty in vibration-based damage detection. The method calculates changes in Young's modulus based on an interval analysis method, providing interval-bound output predictions considering uncertainties in input parameters. Results show superior performance compared to direct finite element models in uncertainty-based damage detection with less computational effort.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Vedhus Hoskere et al.
Summary: The rapid development of deep learning technology has driven the successful application of automated damage detection techniques, but the lack of large-scale annotated datasets for various types of damage limits its application in areas such as inspection automation. InstaDam is an open-source software platform that accelerates pixel-wise damage annotation using binary masks, improving annotation consistency and efficiency.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Jiyuan Shi et al.
Summary: In this research, VGG-Unet models were trained using two methods with different size data sets for Damage Segmentation, showing that Cropping Segmentation works better for large size damage while Squashing Segmentation performs better for minor damage. By adjusting the Background Data Drop Rate (BDDR), the accuracy of crack segmentation can be improved.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Shitong Hou et al.
Summary: The study introduced a novel method for identifying time-varying cable tension based on the variational mode decomposition (VMD) method, which can effectively handle sudden changes in cable force with a maximum error of 8.4%. The validity of the proposed method was demonstrated through the implementation of scaled and full-scale models, and accurate real-time results were obtained during on-site testing.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Mehdi Yazdchi et al.
Summary: The research demonstrated that adding 1% nano-MgO can significantly improve the mechanical properties of concrete, including reducing permeability and increasing compressive and tensile strength. The use of GEP can effectively predict the mechanical properties of concrete containing nano-MgO.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Fengzong Gong et al.
Summary: The paper introduces a method to extract bridge damping values from a VBI system for evaluation. By simplifying the VBI system with a double-beam theoretical model and utilizing the extended dynamic stiffness method, a damping ratio equation for the simplified VBI system was obtained. Comparison with more complex models showed the accuracy of the simplified method in extracting bridge damping ratios.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Rafaelle Piazzaroli Finotti et al.
Summary: This study evaluates the performance of Sparse Auto-Encoder (SAE) in characterizing structural anomalies using a supervised damage detection approach. The efficiency of the implemented methodology achieved over 99% correct structural damage classifications in both numerical beam model and highway viaduct vibration data cases, supporting SAE's ability to extract relevant features for Structural Health Monitoring applications.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Qingxia Zhang et al.
Summary: The study introduces the additional virtual mass method and damage identification method based on sparsity to improve the accuracy and precision of structural damage identification.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Shimin Tang et al.
Summary: This study explores disaster-scene understanding through deep-learning, focusing on hazard types and damage levels in images. It finds that hazard types are more identifiable than damage levels, with the latter being influenced by intra- and inter-class variations, and the treatment of hazard-agnostic damage leveling contributing to underlying uncertainties.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Wael A. Altabey et al.
Summary: The study presents a method for automatic crack identification using deep learning algorithm and 3D shadow modeling technology, which effectively diagnoses corrosion cracks in pipelines with high accuracy and efficiency.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Yonghui Su et al.
Summary: The study proposes a modified directional bat algorithm (MDBA) to address the shortcomings of the standard BA, such as premature convergence and lack of diversity. The MDBA uses individual optimal updating mechanism and an elimination strategy to improve population diversity. The results show that MDBA has better accuracy and convergence compared to other swarm intelligence algorithms with the same small population and few iterations, exhibiting good robustness against noise.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Enes Karaaslan et al.
Summary: This paper introduces a decision support system that utilizes advanced machine-learning models and NDE data integration to enhance bridge management systems, generating optimal maintenance strategies.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Yuqing Gao et al.
Summary: The study combines time series modeling and machine learning classification to propose an automated framework for damage feature extraction, successfully overcoming the limitations of non-stationarity, and demonstrating high accuracy and robustness in experimentation.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Sifat Muin et al.
Summary: This paper introduces low dimensional features based on cumulative absolute velocity (CAV) to enable the use of machine learning for rapid damage assessment in the field of structural health monitoring. The results of a computer experiment show that a combination of CAV and relative CAV with respect to linear response, RCAV, performs the best among different feature combinations. Among different machine learning models, ordinal logistic regression (OLR) shows good generalization capabilities compared to support vector machines (SVM) and artificial neural networks (ANN). The proposed methodology is capable of ensuring rapid decision-making and improving community resiliency.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Naiwei Lu et al.
APPLIED SCIENCES-BASEL
(2020)
