Bolt Installation Defect Detection Based on a Multi-Sensor Method

• Main Authors: An, S. (Author), Fu, B. (Author), Qin, Y. (Author), Wang, D. (Author), Xiao, M. (Author)
• Format: Article
• Language: English
• Published: MDPI 2023
• Subjects: bolt installation; Bolt installation; Bolts; defect detection; Defect detection; Defects; Detection methods; Industrial automation; Installation; Multi sensor; Multiple sensors; multi-sensor; Multi-sensor method; Torque; Torque sensors; Visual sensor; YOLO v3; You only look once v3
• Online Access: View Fulltext in Publisher; View in Scopus

 With the development of industrial automation, articulated robots have gradually replaced labor in the field of bolt installation. Although the installation efficiency has been improved, installation defects may still occur. Bolt installation defects can considerably affect the mechanical properties of structures and even lead to safety accidents. Therefore, in order to ensure the success rate of bolt assembly, an efficient and timely detection method of incorrect or missing assembly is needed. At present, the automatic detection of bolt installation defects mainly depends on a single type of sensor, which is prone to mis-inspection. Visual sensors can identify the incorrect or missing installation of bolts, but it cannot detect torque defects. Torque sensors can only be judged according to the torque and angel information, but cannot accurately identify the incorrect or missing installation of bolts. To solve this problem, a detection method of bolt installation defects based on multiple sensors is proposed. The trained YOLO (You Only Look Once) v3 network is used to judge the images collected by the visual sensor, and the recognition rate of visual detection is up to 99.75%, and the average confidence of the output is 0.947. The detection speed is 48 FPS, which meets the real-time requirement. At the same time, torque and angle sensors are used to judge the torque defects and whether bolts have slipped. Combined with the multi-sensor judgment results, this method can effectively identify defects such as missing bolts and sliding teeth. Finally, this paper carried out experiments to identify bolt installation defects such as incorrect, missing torque defects, and bolt slips. At this time, the traditional detection method based on a single type of sensor cannot be effectively identified, and the detection method based on multiple sensors can be accurately identified. © 2023 by the authors.