Monitoring of Corroded and Loosened Bolts in Steel Structures via Deep Learning and Hough Transforms.

Sensors (Basel)

Department of Ocean Engineering, Pukyong National University, Nam-gu, Busan 48513, Korea.

Published: December 2020


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

In this study, a regional convolutional neural network (RCNN)-based deep learning and Hough line transform (HLT) algorithm are applied to monitor corroded and loosened bolts in steel structures. The monitoring goals are to detect rusted bolts distinguished from non-corroded ones and also to estimate bolt-loosening angles of the identified bolts. The following approaches are performed to achieve the goals. Firstly, a RCNN-based autonomous bolt detection scheme is designed to identify corroded and clean bolts in a captured image. Secondly, a HLT-based image processing algorithm is designed to estimate rotational angles (i.e., bolt-loosening) of cropped bolts. Finally, the accuracy of the proposed framework is experimentally evaluated under various capture distances, perspective distortions, and light intensities. The lab-scale monitoring results indicate that the suggested method accurately acquires rusted bolts for images captured under perspective distortion angles less than 15° and light intensities larger than 63 lux.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7731320PMC
http://dx.doi.org/10.3390/s20236888DOI Listing

Publication Analysis

Top Keywords

corroded loosened
8
loosened bolts
8
bolts steel
8
steel structures
8
deep learning
8
learning hough
8
rusted bolts
8
light intensities
8
bolts
7
monitoring corroded
4

Similar Publications

Corrosion damage presents significant challenges to the safety and reliability of connected vehicles. However, traditional non-destructive methods often fall short when applied to complex automotive structures, such as bolted lap joints. To address this limitation, this study introduces a novel corrosion monitoring approach using Lamb wave-based weighted fusion imaging methods.

View Article and Find Full Text PDF

Introduction: Revision for loosening of femoral stems requires an extensive analysis of bone defects to determine the most appropriate course of action. The drawbacks of using modular stems are that they can break or corrode at their junction. They have rarely been evaluated based on the extent of bone loss and particularly in patients with less severe bone loss.

View Article and Find Full Text PDF

In this study, a regional convolutional neural network (RCNN)-based deep learning and Hough line transform (HLT) algorithm are applied to monitor corroded and loosened bolts in steel structures. The monitoring goals are to detect rusted bolts distinguished from non-corroded ones and also to estimate bolt-loosening angles of the identified bolts. The following approaches are performed to achieve the goals.

View Article and Find Full Text PDF

In vitro studies have shown that human osteoclasts can corrode stainless steel and titanium leading to the production of metal ions responsible for inflammatory reactions. Moreover, traces of cellular activities on metal orthopaedic explants have recently been reported as inflammatory cell-induced (ICI) corrosion being the result of the cells sealing on the metal surfaces and releasing reactive oxygen species (ROS) through Fenton-like reactions. The extent and clinical relevance of this phenomenon has yet to be understood.

View Article and Find Full Text PDF

Auricular prostheses for defects of external ear are retained either by mechanical means or implants. All implant retained prostheses are retained by various means such as bar and clip, magnetic attachments or a combination of bar, clip and magnets. The commonest problem encountered with the bar and clip system is loosening of the clip after 3-4 months.

View Article and Find Full Text PDF