Computer-Aided Civil and Infrastructure Engineering最新文献

Computer vision strain sensors typically require the camera position to be fixed, limiting measurements to surface deformations of structures at pixel-level resolution. Also, sensors have a service term significantly shorter than the designed service term of the structures. This paper presents research on a high durable computer vision sensor, microimage strain sensing (MISS)-Silica, which utilizes a smartphone connected to an endoscope for measurement. It is designed with a range of 0.05 ε, enabling full-stage strain measurement from loading to failure of structures. The sensor does not require the camera to be fixed during measurements, laying the theoretical foundation for embedded computer vision sensors. Measurement accuracy is improved from pixel level to sub-pixel level, with pixel-based measurement errors around 8 µε (standard deviation approximately 7 µε) and sub-pixel calculation errors around 6 µε (standard deviation approximately 5 µε). Sub-pixel calculation has approximately 30% enhancement in measurement accuracy and stability. MISS-Silica features easy data acquisition, high precision, and long service term, offering a promising method for long-term measurement of both surface and internal structures.

Growth in urban population, travel, and motorization continue to cause an increased need for urban projects to expand road capacity. Unfortunately, these projects also cause travel delays, emissions, driver frustration, and other road user adversities. To alleviate these ills, road agencies often face two work zone design choices: close the road fully and re-reroute traffic or implement partial closure. Both options have significant implications for peri-construction road capacity, traveler costs, and the project duration and cost. This study presents a decision-making methodology to facilitate the choice between full road closure and partial closure. The presented decision-making methodology is a bi-level optimization problem: at the upper level, the road agency seeks to optimally schedule road construction work to minimize net vehicle emissions and road construction costs. The lower-level of the problem captures two types of travelers’ route choice behaviors: rational travelers who minimize their travel time and path-loyal travelers who do not change their routes from their pre-construction routes. The bi-level mixed integer nonlinear model is solved using a reinforcement learning-based algorithm (the multi-armed bandit-guided particle swarm optimization [PSO] technique). The computational experiments suggest the superiority of the proposed algorithm, compared to the classic PSO algorithm in terms of solution quality. The numerical results suggest that if the percentage of path-loyal travelers increases, the agency needs to invest more in road project construction to implement under partial closure to avoid a significant increase in vehicle emissions.

The cover image is based on the Article A multi-phase mechanical model of biochar–cement composites at the mesoscale by Muduo Li et al., https://doi.org/10.1111/mice.13307.

Asbestos has been used extensively in several applications. Once it is known as a dangerous mineral, its usage has been prohibited and its identification and remediation play a very important role from the health safety point of view. Nowadays, deep learning techniques are used in many applications, especially for image analysis. They can be used to significantly reduce the time and cost of traditional detection methods. In this paper, taking advantage of asbestos spectral signature, a deep neural network is introduced in order to implement a complete methodology to identify asbestos roofings starting from hyperspectral images in a regional context. The novelty of the proposed approach is a dynamic mixing of models with different features, in order to accommodate classifications on widespread areas of both urban and rural territories. Indeed, the dataset used during the experiments described in this paper is a large one, consisting of many wide hyperspectral images with a geometric resolution of 1 m and with 186 bands, covering an entire region of approximately 8,000 $�{\mathrm{km}}^2$. This is in contrast to other works in the literature where the analyzed areas are limited in size and uniform for physical features.

A novel damage detection model, which utilizes the spatiotemporal characteristics of the acceleration data, is proposed to assess the structural integrity of railway bridges. For this, the measured acceleration data are decomposed into several intrinsic mode functions (IMFs) using the sparse random mode decomposition model. The generated IMFs are subsequently integrated into the enhanced time series conditional generative adversarial network model to identify possible damage in bridges across various frequency bands. The influence of environmental and operational variables (EOVs), particularly temperature fluctuations, was also investigated. The proposed model was verified using both numerical and experimental data from a plate girder bridge. Further validation was conducted using the Z24 bridge dataset, and damage cases under the influence of EOVs were successfully predicted. Throughout the validation process, various anomaly metrics were introduced to establish a threshold value, and a covariance-based time domain metric was proven to be the most effective in our cases.

In damage-level classification, deep learning. models are more likely to focus on regions unrelated to classification targets because of the complexities inherent in real data, such as the diversity of damages (e.g., crack, efflorescence, and corrosion). This causes performance degradation. To solve this problem, it is necessary to handle data complexity and uncertainty. This study proposes a multimodal deep learning model that can focus on damaged regions using text data related to damage in images, such as materials and components. Furthermore, by adjusting the effect of attention maps on damage-level classification performance based on the confidence calculated when estimating these maps, the proposed method realizes an accurate damage-level classification. Our contribution is the development of a model with an end-to-end multimodal attention mechanism that can simultaneously consider both text and image data and the confidence of the attention map. Finally, experiments using real images validate the effectiveness of the proposed method.