Search

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Rolling friction pairs in the tower saddle of suspension bridges could significantly reduce the horizontal load that is transferred to the tower. To investigate the dependence of the rolling friction coefficient (μ) of a rolling friction pair on the normal load (fn) and the cylinder radius (R), an experiment was conducted where a sandwich-like mechanism measured μ. Based on the μ–fn–R relationship, a numerical model, which used one-dimensional (1D) Gaussian random nonplanar surface representation, was proposed in this research to calculate the overall rolling friction coefficient (μT) of a multiroller plate system. The experimental results showed that the dependence of μ on fn and R could be divided into three stages: (1) roughness; (2) elastic; and (3) inelastic. In addition, μ was proportional to fn/R in the elastic stage. The proposed numerical model could accurately calculate μT for a multiroller plate system. The μT rose with increasing surface nonplanarity and slightly increased with the number of rollers (N). This clarified that the μ–fn–R relationship and proposed numerical model could help to quickly determine the size of the rollers and the flatness of plates during design and reduce the scale of the experiments required. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

• A new fibre beam-column model updating method based on static deflection and crack width is proposed. • Crack width data are utilized in model updating for the first time. • An efficient numerical method is developed to simulate the nonlinear cracking behaviour of RC structures. • An innovative model updating procedure based on ANN is presented. • Two phases of model updating properly consider the uncertainties and complex effects of RC structures. For reinforced concrete (RC) structures in service, original finite element models (FEMs) based on design information usually deviate from actual structures due to structural damage such as cracks, displacement and material degradation. Although conventional FEMs can be updated to give results that match the response data used during the updating process, they can hardly predict the subsequent structural performance. In this study, an innovative fibre beam-column model updating method based on static deflection and crack width is proposed. First, the self-developed fibre beam-column finite element program COMPONA-MARC is modified to efficiently simulate the nonlinear cracking behaviour of RC flexural members. Second, sensitivity studies using the discrete central difference method based on the Lagrange interpolation function are conducted to select updating parameters. Third, with the combination of modified COMPONA-MARC and an automation program written in Python, plenty of sample data are obtained, and artificial neural networks (ANNs) are trained by Bayesian Regularization Backpropagation (BRB). Finally, the updated parameters are acquired by inputting the measured static deflections and crack widths. Typical RC beams and RC slabs from the literature are utilized to validate the proposed methodology and explore potential implementation scenarios. The results show that updated FEMs can satisfactorily predict mechanical behaviour and assess structural performance. The proposed method offers enlightening insights about combining structural health monitoring and inspection (SHMI) results with model updating, which can promote the applications of digital twins in performance assessments of RC structures. [ABSTRACT FROM AUTHOR]