Detection of Anomaly in a Pretensioned Bolted Beam-to-Column Connection Node Using Digital Image Correlation and Neural Networks

Abstract

Bolted connections, commonly applied in civil engineering structures, have many advantages. According to current trends, bolted connections in steel structures are designed as prestressed ones. Unfortunately, precise control of the prestressing forces is difficult, while the loosening (due to, e.g., dynamic interactions) may be dangerous for the entire structure. There are many control methods applied in the determination of the tightening level, among which are vision-based methods. The methods described so far enable—thanks to image processing—damage detection in connections with visible connectors. The level of the considered loosening was significant—in many cases, changes in connectors were visible with the naked eye, whereas the procedure presented here enables the detection of very small changes, impossible to detect without manual inspection of every single connector. It is not necessary to observe the connectors directly, but the near surrounding of the node should be visible. As a measurement technique, Digital Image Correlation (DIC) was used. The applied measurement method and the high sensitivity of the presented procedure makes the presented research original. The currently presented procedure, employing Artificial Neural Networks, based on the laboratory examination of an example of one selected beam-to-column connection of a two-story steel portal frame, was perfect in the detection of a change and in the determination of the number of loosened rows, 95%, and their location, 94%, with the number of false alarms below 1%.

A Digital Image Correlation Technique for Laboratory Structural Tests and Applications: A Systematic Literature Review

“…Recently, new software techniques integrated into the DIC have emerged, thanks to the advancements in the application of computer sciences to machine learning, image processing, and computer vision. For example, the DIC was coupled with the artificial neural network to detect anomalies such as the loosened bolts in the beam-to-column joints of a double-story steel frame [45]. The study used a single high-speed Phantom camera (model v341) to record the frame vibration at a frequency of 106 Hz.…”

“…In addition, camera portability, achieved through the use of devices such as smartphone cameras, has opened new venues for DIC applications in civil engineering and other fields [26][27][28][29][30][31][32]. Other factors such as sensitivity improvement, noise reduction, automation, and software integration with techniques such as acoustic emissions (AE) [33][34][35][36][37][38][39], fiber optics [40][41][42], and the recently developed combination of artificial intelligence (AI-DIC) and machine learning (ML-DIC) [43][44][45][46], have all helped to expand the use of DIC in civil engineering lab applications. Thus, the DIC applications in the civil engineering field offer great potential due to their non-contact, full-field, highly accurate, versatile, and real-time monitoring.…”

Digital Image Correlation Technique for Laboratory Structural Tests and Applications: A Systematic Literature Review

“…It is worth noting that these tests utilizing DIC were not feasible until recently (Bolhassani et The camera hardware boosting not only helped to utilize the DIC testing of large specimens but also assisted in expanding the usage of the technique for various static and dynamic tests. For example, the progressively increasing cameras frame rates helped to use the DIC for dynamic applications such as determination of the structure natural frequency, seismic response, vibration measurements, and impact tests (Beberniss & Ehrhardt, 2017 & Tekieli, 2020;Ziaja et al, 2020) all helped to expand the DIC usage in the civil engineering lab applications. Thus, the DIC applications in the civil engineering field offer great potential due to their non-contact, full-field, high accuracy, versatility, and real-time monitoring.…”

Experimental and Numerical Analysis of Multiple Low-Velocity Impact Damages in a Glass Fibered Composite Structure

“…In many cases, these changes inform about damage appearance before the defects are visible [ 22 ]. An additional advantage of DIC is the possibility of simultaneous measurement of many points of the observed area; for this reason, this method was chosen as a verification technique in this study [ 23 ].…”

“…There are fewer research works on analyzing and localizing the multiple impacts and on verification of the deformed areas after impact. In our research work, we focused not only on identification, visualization, and localization of the multiple linearly located impact damages but also studies were carried out to observe changes (verification) in the impact-deformed zones by applying a modified [ 23 ] quick thermal strain field technique.…”