Loading…
Artificial Intelligence (AI) for Reinforced Autoclaved Aerated Concrete (RAAC) crack defect identification
Purpose: Reinforced Autoclaved Aerated Concrete (RAAC) panels have been extensively used in the UK since the 1960s as structural roofs, floors and walls. The lack of a longitudinal, objective, consistent defect data capture process has led to inaccurate, invalid and incomplete RAAC data, which limit...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Default Article |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/2134/27376719.v1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1822173266600525824 |
|---|---|
| author | Karen Blay Chris Gorse Chris Goodier Jack Starkey Seongha Hwang Sergio Pialarissi-Cavalaro |
| author_facet | Karen Blay Chris Gorse Chris Goodier Jack Starkey Seongha Hwang Sergio Pialarissi-Cavalaro |
| author_sort | Karen Blay (3757711) |
| collection | Figshare |
| description | Purpose: Reinforced Autoclaved Aerated Concrete (RAAC) panels have been extensively used in the UK since the 1960s as structural roofs, floors and walls. The lack of a longitudinal, objective, consistent defect data capture process has led to inaccurate, invalid and incomplete RAAC data, which limits the ability to survey RAAC within buildings and monitor performance. Therefore, an accurate, complete and valid digital data capture process is needed to facilitate better RAAC performance and defect monitoring. This paper presents the development of an Artificial Intelligence (AI)-driven RAAC crack defect capture tool for improving the quality of RAAC survey data. Design/methodology/approach: RAAC crack defect image data was collected, curated and trained. A deep learning approach was employed to train RAAC surveyed defects (cracks) images from two hospitals. This approach mitigated unavoidable occlusions/obstructions and unintended ‘foreign’ objects and textures. Findings: An automatic RAAC crack identification tool has been developed to be integrated into RAAC survey processes via an executable code. The executable code categorises RAAC survey images into ‘crack’ or ‘non-crack’ and can provide longitudinal graphical evidence of changes in the RAAC over time. Originality: This paper identifies the role of AI in addressing the intrinsic defects data capture issues for RAAC and extends current debates on data-driven solutions for defect capture and monitoring. |
| format | Default Article |
| id | rr-article-27376719 |
| institution | Loughborough University |
| publishDate | 2024 |
| record_format | Figshare |
| spelling | rr-article-273767192024-11-07T17:05:20Z Artificial Intelligence (AI) for Reinforced Autoclaved Aerated Concrete (RAAC) crack defect identification Karen Blay (3757711) Chris Gorse (13764733) Chris Goodier (1257963) Jack Starkey (10728267) Seongha Hwang (17596287) Sergio Pialarissi-Cavalaro (4528021) Building Reinforced Autoclaved Aerated Concrete (RAAC) Deep Learning Cracks Data quality Defects <p><strong>Purpose: </strong>Reinforced Autoclaved Aerated Concrete (RAAC) panels have been extensively used in the UK since the 1960s as structural roofs, floors and walls. The lack of a longitudinal, objective, consistent defect data capture process has led to inaccurate, invalid and incomplete RAAC data, which limits the ability to survey RAAC within buildings and monitor performance. Therefore, an accurate, complete and valid digital data capture process is needed to facilitate better RAAC performance and defect monitoring. This paper presents the development of an Artificial Intelligence (AI)-driven RAAC crack defect capture tool for improving the quality of RAAC survey data.</p> <p><strong>Design/methodology/approach:</strong> RAAC crack defect image data was collected, curated and trained. A deep learning approach was employed to train RAAC surveyed defects (cracks) images from two hospitals. This approach mitigated unavoidable occlusions/obstructions and unintended ‘foreign’ objects and textures.</p> <p><strong>Findings: </strong>An automatic RAAC crack identification tool has been developed to be integrated into RAAC survey processes via an executable code. The executable code categorises RAAC survey images into ‘crack’ or ‘non-crack’ and can provide longitudinal graphical evidence of changes in the RAAC over time.</p> <p><strong>Originality:</strong> This paper identifies the role of AI in addressing the intrinsic defects data capture issues for RAAC and extends current debates on data-driven solutions for defect capture and monitoring.</p> 2024-11-07T17:05:20Z Text Journal contribution 2134/27376719.v1 https://figshare.com/articles/journal_contribution/Artificial_Intelligence_AI_for_Reinforced_Autoclaved_Aerated_Concrete_RAAC_crack_defect_identification/27376719 CC BY-NC 4.0 |
| spellingShingle | Building Reinforced Autoclaved Aerated Concrete (RAAC) Deep Learning Cracks Data quality Defects Karen Blay Chris Gorse Chris Goodier Jack Starkey Seongha Hwang Sergio Pialarissi-Cavalaro Artificial Intelligence (AI) for Reinforced Autoclaved Aerated Concrete (RAAC) crack defect identification |
| title | Artificial Intelligence (AI) for Reinforced Autoclaved Aerated Concrete (RAAC) crack defect identification |
| title_full | Artificial Intelligence (AI) for Reinforced Autoclaved Aerated Concrete (RAAC) crack defect identification |
| title_fullStr | Artificial Intelligence (AI) for Reinforced Autoclaved Aerated Concrete (RAAC) crack defect identification |
| title_full_unstemmed | Artificial Intelligence (AI) for Reinforced Autoclaved Aerated Concrete (RAAC) crack defect identification |
| title_short | Artificial Intelligence (AI) for Reinforced Autoclaved Aerated Concrete (RAAC) crack defect identification |
| title_sort | artificial intelligence (ai) for reinforced autoclaved aerated concrete (raac) crack defect identification |
| topic | Building Reinforced Autoclaved Aerated Concrete (RAAC) Deep Learning Cracks Data quality Defects |
| url | https://hdl.handle.net/2134/27376719.v1 |