Crack assessment of bridge piers using unmanned aerial vehicles (UAVs) eliminates unsafe factors of manual inspection and provides a potential way for the maintenance of transportation ...infrastructures. However, the implementation of UAV‐based crack assessment for real bridge piers is hindered by several key issues, including the following: (a) both perspective distortion and the geometry distortion by nonflat structural surfaces usually appear on crack images taken by the UAV system from the pier surface; however, these two kinds of distortions are difficult to correct at the same time; and (b) the crack image taken by a close‐range inspection flight UAV system is partially imaged, containing only a small part of the entire surface of the pier, and thereby hinders crack localization. In this paper, a new image‐based crack assessment methodology for bridge piers using UAV and three‐dimensional (3D) scene reconstruction is proposed. First, the data acquisition of UAV‐based crack assessment is discussed, and the UAV flight path and photography strategy for bridge pier assessment are proposed. Second, image‐based crack detection and 3D reconstruction are conducted to obtain crack width feature pair sequences and 3D surface models, respectively. Third, a new method of projecting cracks onto a meshed 3D surface triangular model is proposed, which can correct both the perspective distortion and geometry distortion by nonflat structural surfaces, and realize the crack localization. Field test investigations of crack assessment of a real bridge pier using a UAV are carried out for illustration, validation, and error analysis of the proposed methodology.
Artificial intelligence is gaining increasing popularity in structural analysis. However, at the structural system level, the appropriateness of data representation, the paucity of data, and the ...physical interpretability of results are rarely studied and remain profound challenges. To fill such gaps, a physics‐informed model named StructGNN‐E (i.e., structural analysis based on graph neural network GNN–elastic) based on the GNN architecture, which is capable of implementing the elastic analysis of structural systems without labeled data, is proposed in this study. The systems with structural topologies and member configurations are organized as graph data and later processed by a modified graph isomorphism network. Moreover, to avoid dependence on big data, a novel physics‐informed paradigm is proposed to incorporate mechanics into deep learning (DL), ensuring the theoretical correctness of the results. Numerical experiments and ablation studies demonstrate the unique effectiveness of StructGNN‐E against common DL models, with an average accuracy of 99% and excellent computational efficiency. Due to its differentiability, StructGNN‐E is promising for bidirectionally linking structural parameters and analysis results, paving the way for a new end‐to‐end structural optimization method in the future.
Current automated structural topology design methods can only deal with limited design spaces or simplified architectural layouts for lack of data or a proper representation of structure topology. To ...address this, the abundant information of manually designed architectural and structural layouts should be exploited to guide the topology design. To achieve automatic generation of structural topologies according to real‐world architectural layouts, this research introduces StrucTopo‐generative adversarial network (GAN), an end‐to‐end generative model with node and edge generation stages based on proper graph representation. Nodes are generated using an image‐to‐image translation model, and edges are generated with a GAN‐based approach. The model is trained and tested on a dataset of 300 complex architectural and structural layouts. Measured against the manually designed topologies, the results indicate that the proposed model can generate reasonable structural topologies, with a recall of 97% and an intersection‐over‐union of 80% in node generation, with a precision of 92% and a recall of 91% in edge generation. Additionally, the joint generation shows a graph similarity of 72%. The proposed model is the first of its kind to consider complex architectural layout constraints in the generation of structural topology, marking a step forward in applying artificial intelligence to practical structural design.
Crack assessment has remained one of the high‐priority research topics for structural health monitoring. However, the current research mainly focuses on the crack assessment at some point, but pays ...relatively less attention to the long‐term development of cracks, which is important for structure health monitoring. In this paper, a new method based on dual‐convolutional neural network (CNN) (well over 94% accuracy), digital image processing technology and shape context is proposed, which achieves a fully automated process composed of crack detection, crack measurement, and quantitative crack growth monitoring. In crack growth monitoring, an algorithm to label each crack is put forward for the first time, which is able to reflect the sequential order of the occurrence of cracks. Therefore, each skeleton point of cracks will be assigned an ID which contains information about its identity and width in order to monitor cracks at both a global and local level. Experimental studies of a concrete member with complex cracks are utilized for the illustration and validation of the proposed methodology.
Abstract
Crack identification is essential for the preventive maintenance of asphalt pavement. Through periodic inspection, the characteristics of existing and emerging cracks can be obtained, and ...the pavement condition index can be calculated to assess pavement health. The most common method to estimate the area of cracks in an image is to count the number of grid cells or boxes that cover the cracks in an image. Accurate and efficient crack identification is the premise of crack assessment. However, the current patch‐based classification method is limited by the receptive field and cannot be used to directly classify cracks. Furthermore, the postprocessing algorithm in anchor‐based detection is not explicitly optimized for crack topology. In this paper, a new model, which is the fusion of grid‐based classification and box‐based detection based on You Only Look Once version 5 (YOLO v5) is developed and described for the first time. The accuracy and efficiency of the model are high partly due to the implementation of a shared backbone network, multi‐task learning, and joint training. The non‐maximum suppression (NMS)–area‐reduction suppression (ARS) algorithm is presented to filter redundant, overlapping prediction boxes in the postprocessing stage for the crack topology, and the mapping and matching algorithm is proposed to combine the advantages of both the grid‐based and box‐based models. A double‐labeled dataset containing tens of thousands of asphalt pavement images is assembled, and the proposed method is verified on the test set. The fusion model has superior performance over the individual classification and detection models, and the proposed NMS‐ARS algorithm further improves the detection accuracy. Experimental results demonstrate that the presented method effectively realizes automatic crack identification for asphalt pavement.
In large‐span grid structures with thousands of members involved, bending deformation of members is one of the most commonly observed damages affecting the normal service, even the safety of ...structures. Traditional testing and monitoring methods show weakness in the accurate judgment of crooked members and precision of deformation measurements. In this paper, a new deformation inspection and monitoring method of grid structures using image‐based 3D reconstruction is proposed, wherein a new method is put forward to automatically recognize and extract the shape deformation of the structural member for the first time. First, the key area with multiple members is modeled as a three‐dimensional mesh model using image‐based 3D reconstruction. Then, a new automated recognition and extraction algorithm of shape deformation (AREAS) is carried out, and crooked members, together with their deformed shapes, are extracted from the mesh model through AREAS. In this study, a load experiment of a quadrangular pyramid grid structure containing artificial crooked members and speckled members is designed to compare the deformation measurements using image‐based 3D reconstruction with those using laser scanning. The comparison of deformation and deformation increment shows an average error within 1 mm for image‐based 3D reconstruction, which validates the proposed method in on‐site inspection and monitoring.
This study introduces a novel approach for the estimation of seismic source parameters using a multitask learning network that incorporates a Fourier Transformer architecture. The Fourier Transformer ...is designed to extract information from both the time and frequency domains, which reduces the time complexity by utilizing a fast Fourier transform (FFT) in place of the traditional attention mechanism in the Transformer encoder. The network consists of a shared encoder for general feature extraction and four task-specific decoders for parameter estimation. The model is both lightweight and accurate, capable of simultaneously estimating magnitude, epicentral distance, p travel time, and depth based on a 30-s single-station waveform. The proposed approach was validated using the Stanford Earthquake dataset (STEAD) and compared with the state-of-the-art techniques. The results show standard deviations of 0.19 for magnitude, 3.77 km for epicentral distance, 0.46 s for p travel time, and 5.77 km for depth, with a lower error and a faster response compared to the existing prediction framework. The code is available at https://github.com/KG-TSI-Civil/MFTnet .
Based on the quasi-static test on eight CFST columns subjected to pure torsion and compression–torsion cyclic load, the torsion behavior of CFST columns with various section types, steel ratios and ...axial load levels was studied. The test results showed that the hysteretic curves of CFST columns under pure torsion and low compression–torsion cyclic load are very plump, which indicate that CFST columns have good seismic capacity. The unloading stiffness of CFST columns was equal to the initial elastic stiffness. The torsion capacity of CFST columns could be improved by the low compressive load, and the ductility was also good. But the torsion capacity of CFST columns would be reduced by the high compressive load. When CFST columns subjected to pure torsion, spiral diagonal compressive struts will be created in the in-filled concrete, and the axial components of the diagonal compressive force of the in-filled concrete was equal to the axial tensile force of the steel tube in order to satisfy the axial load equilibrium condition on the section, so the axial strain will be produced in the steel tube. The shear strain has good linear relationship with the rotation angle of the section when CFST columns subjected to pure torsion and compression–torsion combined action. Based on the test results and literatures available, the torsion mechanism of CFST columns was preliminarily analyzed.
► An experimental study on CFST columns under compression torsion was carried out. ► The failure modes and strain state of CFST columns under torsion were found. ► The torsion mechanism of CFST columns was analyzed based on the test results.
A general deep learning framework based on the Unrolled Attention Sequence-to-Sequence (UA-Seq2Seq) model is developed to address the history-dependent response prediction problem. First, the ...particular traits of the history-dependent response prediction problem are analyzed, which motivate the incorporation of the unrolled gated recurrent unit (GRU) structure and the attention mechanism into the classical Seq2Seq model in natural language processing. In the UA-Seq2Seq model, the Seq2Seq skeleton frees the restrictions on both the input and target mechanical variables. Meanwhile, the novel unrolled GRU structure conforms to the general process of mechanical simulation and manages to establish the gated links with the historical states, which is further boosted by the powerful attention mechanism dedicated to retrieving the super-long-term memory information. To quickly and informatively validate the UA-Seq2Seq model, a numerical experiment based on the cyclic stress–strain response of low-yield-point steel is conducted, whose constitutive behavior depends highly on the loading history. All the training and testing configurations in the numerical experiment are specified, including a novel data normalization method – named nonlinear reference-value scaling – tailored for mechanical variables. The results verify the effectiveness of the UA-Seq2Seq model to reproduce the history-dependent hysteresis loops and confirm its capability to capture the long-term memory effect. Furthermore, a parametric analysis is carried out to demonstrate the necessity of the unrolled structure and the attention mechanism as well as the advantage of selecting the L1 loss metric, following which a qualitative mechanical interpretation of the UA-Seq2Seq model is provided to aid in the intuitive comprehension. Finally, three feasible applications and extensions of the developed framework are introduced conceptually: integration with finite element analysis, outline analysis, and transfer learning to other similar tasks. Therefore, the proposed deep learning framework is able to cover a wide range of scenarios concerning the mechanical history-dependent response simulation in practice, which facilitates its universal employment in the academic research and engineering design.
•A general deep learning framework is developed for the history-dependent response prediction problem.•The first study to apply the Seq2Seq model and attention mechanism to computational mechanics.•A universal data normalization method is tailored for all the mechanical variables.•A mechanical interpretation is provided for the deep learning framework.•The developed framework is scalable and transferable.
•Four interior UHPC/RC composite beam-column joints are cyclically tested.•Parameters including stirrup ratios, anchorage methods and lengths are studied.•The UHPC can be safely used in the joint ...zone without any stirrups.•The anchorage length of the beam longitudinal bars can be reduced in the UHPC joint zone.
In traditional precast reinforced concrete (RC) frame structures, the reinforcement details are usually complex in the joint zone, which makes the fabrication process difficult and thus affects the construction quality and speed. Ultra-high performance concrete (UHPC) exhibits substantially higher shear resistance and bond strength than normal concrete due to its much larger compressive and tensile strengths. As a result, the application of UHPC can significantly help reducing the amount of stirrups and anchorage length of the longitudinal bar in the joint zone of precast RC frames, which can obviously simplify the joint construction. This paper presents the cyclic tests of four interior precast UHPC/RC composite beam-column joints to evaluate quantitatively the effect of replacing the normal concrete by UHPC in the joint zone. Considering that the condition of steam curing is difficult to achieve in the actual construction environment, the non-steam-cured UHPC was adopted and proved to exhibit adequate compressive (>120 MPa) and tensile strength (>7 MPa) with the ultimate tensile strain larger than 1%. The main variables in this study are the anchorage methods, anchorage lengths and stirrup ratios in the joint zone. The cyclic load tests demonstrate that the cast-in-situ UHPC can work well with the precast concrete and there is no need of stirrups in the UHPC joint zone. With the use of UHPC instead of normal concrete, the anchorage length of the beam straight and headed bars can be decreased to 16db and 8.1db, respectively. Therefore, the application of UHPC in the joint zone is practicable and can greatly ease the fabrication process, especially with the use of headed bars.