A two-step computer vision-based framework for bolt loosening detection and its implementation on a smartphone application

Bolt loosening detection is a labor-intensive and time-consuming process for field engineers. This paper develops a two-step computer vision-based framework to quickly identify bolt loosening angle from field images captured by unmanned aerial vehicle (UAV). In step one, a total of 1200 image samples of bolted structures were used to train faster region based convolutional neural network (Faster R-CNN) for bolt detection from UAV captured images. In step two, computer vision-based technologies, including Gaussian filter, perspective transform, and Hough transform (HT), were performed to quantify bolt loosening angle. The developed framework was then integrated into web server and an iOS application (app) was designed to enable fast data communication between field workplace (UAV captured images) and web server (bolt loosening angle quantification), so that field engineers can quickly view the inspection results on their phone screens. The proposed framework and designed smartphone app greatly help field engineers to improve the accuracy and efficiency for onsite inspection and maintenance of bolted structures.

A bolt loosening detection method based on patch antenna with overlapping sub-patch

Bolts are widely used in civil engineering, and the detection of bolt loosening is of great significance to ensure the safety of a structure. This paper introduces a new method for detecting bolt loosening using a customized detachable strain sensor based on a patch antenna. A patch antenna with overlapping sub-patch is proposed to measure the longitudinal elongation of the entire bolt shaft, indicating the loosening state of the bolt. When the bolt is fastened, the elongation of the bolt under tension will change the combined length of the underlying patch and the radiation sub-patch, consequently increasing or decreasing the resonant frequency of the antenna. The resonant frequency of the antenna can be measured by the vector network analyzer. Furthermore, with wireless interrogation of the strain sensor based on the patch antenna, the proposed method can also be used in the wireless detection of bolt loosening. The authors conducted a finite element analysis of the bolt and the electromagnetic simulations of the antenna. They designed the detection sensor and conducted a series of experimental tests to demonstrate how a bolt under different applied preloads can be effective and feasible under the proposed method.

Competitive Failure of Bolt Loosening and Fatigue under Different Preloads

Existing research on the competitive failure relationship, failure mechanism, and influencing factors of bolt loosening and fatigue under different preloads is insufficient. This study analyzes the competitive failure relationship between bolt loosening and fatigue under composite excitation through competitive failure tests of bolt loosening and fatigue under different preloads. The results indicated that the failure mode of the bolt is only related to the load ratio (R) and is unrelated to the initial preload and excitation amplitude, which only determine the failure life of the bolt. The small axial loads of composite excitation can restrain bolt failure, and the significant degree of this restraining effect is different for different preloads. Subsequently, a fracture analysis of the bolt was performed to verify the competitive failure relationship of the bolt from a microscopic perspective, and the competitive failure mechanism of the bolt was determined. Based on the findings, we propose a calculation equation for the optimal preload of 8.8 grade high-strength bolts that can serve as a reference for engineering applications.

Correction: Pham et al. Bolt-Loosening Monitoring Framework Using an Image-Based Deep Learning and Graphical Model. Sensors 2020, 20, 3382

The authors wish to make the following correction to this paper [...]