A deep learning-based approach towards automating visual reinforced concrete bridge inspections
| dc.contributor.advisor | Moyo, Pilate | |
| dc.contributor.advisor | Matongo, Kabani | |
| dc.contributor.author | Dube, Bright N | |
| dc.date.accessioned | 2022-01-27T14:29:12Z | |
| dc.date.available | 2022-01-27T14:29:12Z | |
| dc.date.issued | 2021 | |
| dc.date.updated | 2022-01-27T14:28:10Z | |
| dc.description.abstract | Visual inspections are fundamental to the maintenance of RC bridge infrastructure. However, their highly subjective nature often compromises the accuracy of inspection results and ultimately leads to inaccurate prioritisation of repair and rehabilitation activities. Visual inspections are also known to expose inspectors to height and trafficrelated hazards, and sometimes require the use of costly access equipment. Therefore, the present study investigated state-of-the-art Unmanned Aerial Vehicles (UAVs) and algorithms capable of automating visual RC bridge inspections in order to reduce inspector subjectivity, minimise inspection costs and enhance inspector safety. Convolutional neural network (CNN) algorithms are state-of-the-art in relation to the automatic detection of RC bridge defects. However, much of the prior research in this area focused on detecting the presence of defects and gave little to no attention to characterizing them according to defect type and degree (D) or extent (E) ratings. Four proof-of-concept CNN models were therefore developed, namely a defect-type detector, crack-type detector, exposed-rebar detector and a shrinkage crack D-rating model. Each model was built by first compiling defect images, labelling them according to defect/crack type and creating training and test sets at a 90-10% split. The training sets were then used to train the CNN models through transfer learning and fine-tuning using the fastai deep learning python library. The performance of each model was ultimately evaluated based on prediction accuracies on the test sets and their robustness to noise. Test accuracies ≥ 87% were attained by the trained models. This result shows that CNNs are capable of accurately identifying RC bridge corrosion, spalling, ASR, cracking and efflorescence, and assigning appropriate D ratings to shrinkage cracks. It was concluded that CNN models can be built to identify and allocate D and E ratings to any visible defect type, provided the requisite training data that sufficiently represents noisy real-world inspection conditions can be acquired. This formed the basis upon which a practical framework for UAV-enabled and deep learning-based RC bridge inspections was developed. | |
| dc.identifier.apacitation | Dube, B. N. (2021). <i>A deep learning-based approach towards automating visual reinforced concrete bridge inspections</i>. (). ,Faculty of Engineering and the Built Environment ,Department of Civil Engineering. Retrieved from http://hdl.handle.net/11427/35602 | en_ZA |
| dc.identifier.chicagocitation | Dube, Bright N. <i>"A deep learning-based approach towards automating visual reinforced concrete bridge inspections."</i> ., ,Faculty of Engineering and the Built Environment ,Department of Civil Engineering, 2021. http://hdl.handle.net/11427/35602 | en_ZA |
| dc.identifier.citation | Dube, B.N. 2021. A deep learning-based approach towards automating visual reinforced concrete bridge inspections. . ,Faculty of Engineering and the Built Environment ,Department of Civil Engineering. http://hdl.handle.net/11427/35602 | en_ZA |
| dc.identifier.ris | TY - Master Thesis AU - Dube, Bright N AB - Visual inspections are fundamental to the maintenance of RC bridge infrastructure. However, their highly subjective nature often compromises the accuracy of inspection results and ultimately leads to inaccurate prioritisation of repair and rehabilitation activities. Visual inspections are also known to expose inspectors to height and trafficrelated hazards, and sometimes require the use of costly access equipment. Therefore, the present study investigated state-of-the-art Unmanned Aerial Vehicles (UAVs) and algorithms capable of automating visual RC bridge inspections in order to reduce inspector subjectivity, minimise inspection costs and enhance inspector safety. Convolutional neural network (CNN) algorithms are state-of-the-art in relation to the automatic detection of RC bridge defects. However, much of the prior research in this area focused on detecting the presence of defects and gave little to no attention to characterizing them according to defect type and degree (D) or extent (E) ratings. Four proof-of-concept CNN models were therefore developed, namely a defect-type detector, crack-type detector, exposed-rebar detector and a shrinkage crack D-rating model. Each model was built by first compiling defect images, labelling them according to defect/crack type and creating training and test sets at a 90-10% split. The training sets were then used to train the CNN models through transfer learning and fine-tuning using the fastai deep learning python library. The performance of each model was ultimately evaluated based on prediction accuracies on the test sets and their robustness to noise. Test accuracies ≥ 87% were attained by the trained models. This result shows that CNNs are capable of accurately identifying RC bridge corrosion, spalling, ASR, cracking and efflorescence, and assigning appropriate D ratings to shrinkage cracks. It was concluded that CNN models can be built to identify and allocate D and E ratings to any visible defect type, provided the requisite training data that sufficiently represents noisy real-world inspection conditions can be acquired. This formed the basis upon which a practical framework for UAV-enabled and deep learning-based RC bridge inspections was developed. DA - 2021 DB - OpenUCT DP - University of Cape Town KW - Engineering LK - https://open.uct.ac.za PY - 2021 T1 - A deep learning-based approach towards automating visual reinforced concrete bridge inspections TI - A deep learning-based approach towards automating visual reinforced concrete bridge inspections UR - http://hdl.handle.net/11427/35602 ER - | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/11427/35602 | |
| dc.identifier.vancouvercitation | Dube BN. A deep learning-based approach towards automating visual reinforced concrete bridge inspections. []. ,Faculty of Engineering and the Built Environment ,Department of Civil Engineering, 2021 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/35602 | en_ZA |
| dc.language.rfc3066 | eng | |
| dc.publisher.department | Department of Civil Engineering | |
| dc.publisher.faculty | Faculty of Engineering and the Built Environment | |
| dc.subject | Engineering | |
| dc.title | A deep learning-based approach towards automating visual reinforced concrete bridge inspections | |
| dc.type | Master Thesis | |
| dc.type.qualificationlevel | Masters | |
| dc.type.qualificationlevel | MSc |