BiNet: Bridge Visual Inspection Dataset and Approach for Damage Detection

2021 ◽  
pp. 1027-1034
Author(s):  
Zaharah A. Bukhsh ◽  
Andrej Anžlin ◽  
Irina Stipanović
Keyword(s):  
Damage Detection ◽  
Visual Inspection

Damage Detection of Sandwich Structure Using Time Domain Reflectometry

2010 ◽  
Vol 123-125 ◽  
pp. 891-894
Author(s):  
Seung Il Kim
Keyword(s):  
Damage Detection ◽  
Impact Energy ◽  
Time Domain ◽  
Sandwich Structure ◽  
Visual Inspection ◽  
High Accuracy ◽  
Time Domain Reflectometry ◽  
Impact Location

Time Domain Reflectometry has been applied to detect damage on sandwich structure. Face plated need to be copper plated to embed sensor on surface. Core also needs to be conductive to send signal back. Total 6 lines of sensor were tested with varying impact energy and impact location. TDR were able to locate damage with high accuracy. Damage degrees were detectable for critical hit, but not clear enough to predict impact energy. However TDR was sensitive enough to detect damage that wasn’t visible by visual inspection.

Nondestructive Evaluation of Composite Material Damage Using Vibration Reciprocity Measurements

2012 ◽  
Vol 134 (4) ◽  
Author(s):  
Brandon R. Zwink
Keyword(s):  
Composite Materials ◽  
Damage Detection ◽  
Visual Inspection ◽  
Fiber Composite ◽  
Forced Response ◽  
Carbon Fiber Composite ◽  
Nonlinear Components ◽  
Impact Energies ◽  
Maintenance Personnel ◽  
Damaged Materials

Maintenance personnel in the U.S. military are interested in developing methods of damage detection for composite materials that are field expedient and less dependent on the operator’s experience than the current methods. A vibration-based method was developed for detecting damage in composite materials based on a measurement of the nonlinear forced response that damaged materials are assumed to exhibit. A damage feature was extracted for a structural component by quantifying the degree to which the reciprocity between two input-output structural paths fail due to the nonlinearities associated with damage. A dynamic nonlinear theoretical model was used to develop a better understanding of why reciprocity fails for networks of nonlinear components. Experimental results were obtained from carbon fiber composite specimens subjected to various levels of damage. It was determined that reciprocity measurements were capable of identifying damage due to impact energies of 10.8 N·m; however, the method was not capable of discerning damage that was not directly beneath the sensor locations. The levels of damage that could be consistently detected using the new methodology could be discovered through a close visual inspection. In comparison to currently employed methods of damage detection, the proposed methodology is less subjective but also less sensitive to damage. More development work will be required to propose this technology as a replacement for current methods such as ultrasound and tap testing.

scholarly journals Damage detection using in-domain and cross-domain transfer learning

2021 ◽  
Author(s):  
Zaharah A. Bukhsh ◽  
Nils Jansen ◽  
Aaqib Saeed
Keyword(s):  
Damage Detection ◽  
Learning Strategies ◽  
Transfer Learning ◽  
Large Scale ◽  
Visual Inspection ◽  
Superior Performance ◽  
Cross Domain ◽  
Domain Transfer ◽  
Domain Transfer Learning ◽  
The Impact

AbstractWe investigate the capabilities of transfer learning in the area of structural health monitoring. In particular, we are interested in damage detection for concrete structures. Typical image datasets for such problems are relatively small, calling for the transfer of learned representation from a related large-scale dataset. Past efforts of damage detection using images have mainly considered cross-domain transfer learning approaches using pre-trained ImageNet models that are subsequently fine-tuned for the target task. However, there are rising concerns about the generalizability of ImageNet representations for specific target domains, such as for visual inspection and medical imaging. We, therefore, evaluate a combination of in-domain and cross-domain transfer learning strategies for damage detection in bridges. We perform comprehensive comparisons to study the impact of cross-domain and in-domain transfer, with various initialization strategies, using six publicly available visual inspection datasets. The pre-trained models are also evaluated for their ability to cope with the extremely low-data regime. We show that the combination of cross-domain and in-domain transfer persistently shows superior performance specially with tiny datasets. Likewise, we also provide visual explanations of predictive models to enable algorithmic transparency and provide insights to experts about the intrinsic decision logic of typically black-box deep models.

Augmented reality for enhanced visual inspection through knowledge-based deep learning

2020 ◽  
pp. 147592172097698
Author(s):  
Shaohan Wang ◽  
Sakib Ashraf Zargar ◽  
Fuh-Gwo Yuan
Keyword(s):  
Deep Learning ◽  
Pilot Study ◽  
Augmented Reality ◽  
Damage Detection ◽  
Real Time ◽  
Visual Inspection ◽  
Probability Of Detection ◽  
Two Stage ◽  
Knowledge Based ◽  
Smart Glasses

A two-stage knowledge-based deep learning algorithm is presented for enabling automated damage detection in real-time using the augmented reality smart glasses. The first stage of the algorithm entails the identification of damage prone zones within the region of interest. This requires domain knowledge about the damage as well as the structure being inspected. In the second stage, automated damage detection is performed independently within each of the identified zones starting with the one that is the most damage prone. For real-time visual inspection enhancement using the augmented reality smart glasses, this two-stage approach not only ensures computational feasibility and efficiency but also significantly improves the probability of detection when dealing with structures with complex geometric features. A pilot study is conducted using hands-free Epson BT-300 smart glasses during which two distinct tasks are performed: First, using a single deep learning model deployed on the augmented reality smart glasses, automatic detection and classification of corrosion/fatigue, which is the most common cause of failure in high-strength materials, is performed. Then, in order to highlight the efficacy of the proposed two-stage approach, the more challenging task of defect detection in a multi-joint bolted region is addressed. The pilot study is conducted without any artificial control of external conditions like acquisition angles, lighting, and so on. While automating the visual inspection process is not a new concept for large-scale structures, in most cases, assessment of the collected data is performed offline. The algorithms/techniques used therein cannot be implemented directly on computationally limited devices such as the hands-free augmented reality glasses which could then be used by inspectors in the field for real-time assistance. The proposed approach serves to overcome this bottleneck.

scholarly journals Detection and Location of Damage on Pipelines

2004 ◽  
Author(s):  
Karen A. Moore ◽  
Robert Carrington ◽  
John Richardson
Keyword(s):  
Damage Detection ◽  
Real Time ◽  
Visual Inspection ◽  
Porous Metal ◽  
Time Data ◽  
Real Time Data ◽  
Unique Nature ◽  
Transmission Pipeline ◽  
Environmental Laboratory ◽  
The U.S

The U.S. Dept of Energy Idaho National Engineering and Environmental Laboratory (INEEL) has developed and successfully tested a real-time pipeline damage detection and location system. This system uses porous metal resistive traces applied to the pipe to detect and locate damage. The porous metal resistive traces are sprayed along the length of a pipeline. The unique nature and arrangement of the traces allows locating the damage in real time along miles of pipe. This system allows pipeline operators to detect damage when and where it is occurring, and the decision to shut down a transmission pipeline can be made with actual real-time data, instead of conservative estimates from visual inspection above the area.

scholarly journals Full Scale Bridge Damage Detection Using Sparse Sensor Networks, Principal Component Analysis, and Novelty Detection

Proceedings ◽  
2019 ◽  
Vol 42 (1) ◽  
pp. 34
Author(s):  
Emmanuel Akintunde ◽  
Saeed Eftekhar Azam ◽  
Ahmed Rageh ◽  
Daniel Linzell
Keyword(s):  
Principal Component Analysis ◽  
Damage Detection ◽  
Visual Inspection ◽  
Early Stage ◽  
Novelty Detection ◽  
Principal Component ◽  
Component Analysis ◽  
Full Scale ◽  
Bridge Damage ◽  
Scale Experiment

Over the decades, visual inspection has been adopted as a means to monitor infrastructure health. While visual inspection provides insights on a bridge’s condition, it has been generally agreed that it is insufficient and inefficient. This has called for the creation of autonomous, robust, continuous, and quantitative structural health monitoring (SHM) systems to detect potential deficiencies in an early stage, and monitor future condition. Various methods have been explored that associate changes in condition with changes in the structure’s vibration characteristics. These methods have been mostly tested on laboratory specimens experiencing simulated damage. There is need for extending validation of these SHM methods on in-situ structures experiencing real damage under operational and environmental conditions. This paper summarizes a full-scale experiment exploring bridge damage detection effectiveness under variable traffic loads. Three different types of damage were introduced into a full-scale, bridge deck mock-up. These included crash-induced bridge barrier damage, controlled barrier damage, and damage to the deck slab. At the end of each introduced damage case, the bridge’s response to the multiple passages was recorded using specific vehicles specifications. Data was extracted and analyzed to identify damage using principal component analysis (PCA) and independent component analysis (ICA) as damage-sensitive features. The extracted damage features were thereafter used as input for unsupervised learning (novelty detection). One interesting observation was how PCA revealed possibly significant damage after a crash, which under visual inspection appeared to be minor. Novelty detection using PCA as its damage feature was shown to provide robust damage detection irrespective of load, speed variation, and signal noise levels.

Effect of alternate feedback strategies on performance for a synthetic aircraft visual inspection task

2003 ◽  
Author(s):  
Rahul R. Desai ◽  
Anand K. Gramopadhye ◽  
Brian J. Melloy ◽  
Andrew Duchowski
Keyword(s):  
Visual Inspection ◽  
Feedback Strategies ◽  
Inspection Task

Detection of Leukemia Using Image Processing

2018 ◽  
Vol 8 (4) ◽  
pp. 61
Author(s):  
A. Sivasangari ◽  
G. Sasikumar
Keyword(s):  
Image Processing ◽  
Statistical Analysis ◽  
Early Detection ◽  
Visual Inspection ◽  
Causes Of Death ◽  
Cure Rate ◽  
Blood Disorders ◽  
Detection And Diagnosis ◽  
The Moment ◽  
Early Detection And Diagnosis

Leukemia   disease   is one   of    the   leading   causes   of death   among   human. Its  cure  rate and  prognosis   depends   mainly   on  the  early  detection   and  diagnosis  of   the  disease. At  the  moment, identification  of  blood  disorders  is  through   visual  inspection  of  microscopic  images  by  examining  changes  like  texture, geometry, colour  and   statistical  analysis  of  images . This  project  aims  to  preliminary  of  developing  a  detection  of  leukemia  types  using   microscopic  blood  sample using MATLAB. Images  are  used  as  they  are  cheap  and  do  not  expensive  for testing  and  lab  equipment.

Antioptimization for comparison of alternative structural models and damage detection

AIAA Journal ◽  
1999 ◽  
Vol 37 ◽  
pp. 857-864
Author(s):  
S. N. Gangadharan ◽  
E. Nikolaidis ◽  
K. Lee ◽  
R. T. Haftka ◽  
R. Burdisso
Keyword(s):  
Damage Detection ◽  
Structural Models
Sign in / Sign up

Export Citation Format

Share Document