Conventionally, the number of steel rebars at construction sites is manually counted by workers. However, this practice gives rise to several problems: it is slow, human-resource-intensive, time-consuming, error-prone, and not very accurate. Consequently, a new method of quickly and accurately counting steel rebars with a minimal number of workers needs to be developed to enhance work efficiency and reduce labor costs at construction sites. In this study, the authors developed an automated system to estimate the size and count the number of steel rebars in bale packing using computer vision techniques based on a convolutional neural network (CNN). A dataset containing 622 images of rebars with a total of 186,522 rebar cross sections and 409 poly tags was established for segmentation rebars and poly tags in images. The images were collected in a full HD resolution of 1920 × 1080 pixels and then center-cropped to 512 × 512 pixels. Moreover, data augmentation was carried out to create 4668 images for the training dataset. Based on the training dataset, YOLACT-based steel bar size estimation and a counting model with a Box and Mask of over 30 mAP was generated to satisfy the aim of this study. The proposed method, which is a CNN model combined with homography, can estimate the size and count the number of steel rebars in an image quickly and accurately, and the developed method can be applied to real construction sites to efficiently manage the stock of steel rebars.
In the study, an automated visualization of the proximity between workers and equipment is developed to manage workers’ safety at construction sites using the convolutional-neural-network-based image processing of a closed-circuit television video. The images are analyzed to automatically transform a hazard index visualized in the form of a plane map. The graphical representation of personalized proximity in the plane map is proposed and termed as safety ellipse in the study. The safety ellipse depending on the posture of workers and the area occupied by the hazardous objects (trucks) enable to represent precise proximity. Collision monitoring is automated with computer vision techniques of artificial-intelligence-based object detection, occupied space calculation, pose estimation, and homography.
An event of sensor faults in sensor networks deployed in structures might result in the degradation of the structural health monitoring system and lead to difficulties in structural condition assessment. Reconstruction techniques of the data for missing sensor channels were widely adopted to restore a dataset from all sensor channels. In this study, a recurrent neural network (RNN) model combined with external feedback is proposed to enhance the accuracy and effectiveness of sensor data reconstruction for measuring the dynamic responses of structures. The model utilizes spatial correlation rather than spatiotemporal correlation by explicitly feeding the previously reconstructed time series of defective sensor channels back to the input dataset. Because of the nature of spatial correlation, the proposed method generates robust and precise results regardless of the hyperparameters set in the RNN model. To verify the performance of the proposed method, simple RNN, long short-term memory, and gated recurrent unit models were trained using the acceleration datasets obtained from laboratory-scaled three- and six-story shear building frames.
This paper investigates dynamic characteristics of a historic wooden structure by ambient vibration testing, presenting a novel estimation methodology of story stiffness for the purpose of vibration‐based structural health monitoring. As for the ambient vibration testing, measured structural responses are analyzed by two output‐only system identification methods (i.e., frequency domain decomposition and stochastic subspace identification) to estimate modal parameters. The proposed methodology of story stiffness is estimation based on an eigenvalue problem derived from a vibratory rigid body model. Using the identified natural frequencies, the eigenvalue problem is efficiently solved and uniquely yields story stiffness. It is noteworthy that application of the proposed methodology is not necessarily confined to the wooden structure exampled in the paper.
This study proposes a retunable liquid column vibration absorber (LCVA) that can handle a wide range of natural frequencies while maintaining its original shape. The LCVA’s vertical tubes are divided into several smaller tubes (i.e., cells). Sealing a cell makes the liquid in it stand still so that only part of the liquid contained within the LCVA participates in the motion. By selecting appropriate configurations of sealed cells, the sectional area ratios of the vertical and horizontal tubes and the effective horizontal tube length are changed, which yields new natural frequencies to accommodate shifts in the natural frequency of a primary building. The proposed retunable LCVA is analytically evaluated and experimentally verified by using various patterns of sealed cells and a shake-table test to provide various natural frequencies while maintaining control performance.
The displacement responses of civil structures reveal the overall state of the structures and consist of two distinctive dynamic behaviors: pseudo-static deflection and structural vibration. In this study, a dynamic displacement estimation system is developed by integrating a laser Doppler vibrometer (LDV) and terrestrial laser scanner (TLS). The TLS displacement data contaminated with high noise and measured with a low sampling rate is converted to high sampling rate dynamic displacements including the pseudo-static motion by fusing with the velocity data measured by the LDV which are at a high sampling rate but miss the pseudo-static components.