Non-destructive evaluation (NDE), Infrared thermography (IRT), Impact echo (IE), Ground penetrating radar (GPR), Unmanned aerial systems (UAS), Artificial intelligence (AI), machine learning (ML), Deep convolutional neural network (DCNN), Bridge deck evaluation, delamination, defects
SDNET2021 is a uniquely validated annotated dataset for evaluating the condition of concrete bridge decks and benchmarking advanced deep learning models for defects (delamination, cracks, rebar corrosion) detection and bridge deck evaluation. Common structural defects, such as cracks, delamination, spalling, rebar corrosion, etc. are commonly detected using traditional hands-on inspections (visual, destructive, chain dragging, and sounding). These methods are accompanied with limitations such as disruption and closure of traffic, laborious, costly, time consuming and possible inconsistencies and likelihood of errors in field data collection and interpretation. Usually there exists dataset for surface defects from laboratory specimens, but rare validated datasets for sub-surface defects of several NDE techniques exists. SDNET2021 contains 1,657 annotated IE signals, over 655,818 annotated GPR signals and about 6,317,409 annotated pixels of classes of delamination for IRT images collected during 2020 summer from five (5) in-service bridge decks in Grand Forks, ND, USA. These datasets were validated and annotated with a set of ground truth maps representing the class of delamination at each point of the decks after defected concrete was removed based on chain-dragging, i.e. ground truth data. The ground truth maps also show the GPS coordinates and size of each class of removal for the delaminated portions of the bridge decks under investigation. This ground truth was developed on site prior to commencement of repair to show sound concrete Class 1 (No Delamination); Class 2 Delamination (delamination above top bar mat), and Class 3 Delamination (delamination below top bar mat). The IRT, GPR and IE data has been annotated and validated with the ground truth data collected during the investigation. SDNET2021 will be highly significant in further studies related to the development of algorithms based on AI models for classification and delamination/defects detection, which is a major frontline subject for continued research in the field of advanced NDE and structural health monitoring. SDNET2021 is freely available at https://doi.org/10.31356/data019
Advanced Evaluation Methods for Concrete Bridge Decks: Data Acquisition, Validation, and Annotation (ND DOT)
DWG, LVM (a text file), DOCX, CSV, PDF, JPEG, PNG
Ichi, Eberichi and Darafshan Sattar. Advanced Evaluation Methods for Concrete Bridge Decks, Phase I: Data Collection and Validation. October 2020. Report submitted to North Dakota Department of Transportation (ND DOT).
Ichi, Eberichi, and Darafshan Sattar. "An Annotated Dataset for Evaluation of Existing Bridge Decks for Development of Deep Learning Models". Society for Experimental Mechanics 2020 Virtual Conference. February 8, 2021.
Ichi, Eberichi, and Darafshan Sattar. "Non-Destructive Evaluation of Reinforced Concrete Bridge Decks: Challenges and Lesson Learnt." ACI Virtual Concrete Convention, ACI 123 Student Poster Session. American Concrete Institute. March 2021. Poster presentation.
Ichi, Eberichi, Amrita Das, and Darafshan Sattar. Advanced Evaluation Methods for Concrete Bridge Decks: Data Acquisition, Validation and Annotation. April 2021. Report submitted to North Dakota Department of Transportation (ND DOT).
Ichi, Eberichi and Dorafshan, Sattar, "SDNET2021: Annotated NDE dataset for Structural Defects" (2021). Datasets. 19.