Drone inspection with machine learning for asset maintenance
Inspection of niches in columbariums are important to ensure that the niches are in good condition. The current practice involves officers physically conducting visual inspections of the niches. However, this task is extremely repetitive and time consuming, causing it to be susceptible to huma...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/176790 |
| _version_ | 1826113375828967424 |
|---|---|
| author | Er, Tricia Yishan |
| author2 | Law Wing-Keung, Adrian |
| author_facet | Law Wing-Keung, Adrian Er, Tricia Yishan |
| author_sort | Er, Tricia Yishan |
| collection | NTU |
| description | Inspection of niches in columbariums are important to ensure that the niches are in good
condition. The current practice involves officers physically conducting visual inspections of
the niches. However, this task is extremely repetitive and time consuming, causing it to be
susceptible to human errors.
This study seeks to investigate the use of drones and machine learning for niche inspections
and evaluate the potential based on accuracy of the object detection model. First, a drone was
selected and flown in laboratory conditions. Next, an object detection model was trained to
identify the various classes identified. The classes included anomalies such as cracks and
vandalism, which were represented by hand-drawn symbols. The object detection model was
successfully trained using Roboflow after multiple rounds of trial and error using programs
such as TensorFlow and Roboflow. Tests using the trained object detection model were carried
out to ensure that the model was able to accurately identify the different classes. A confidence
interval range of 67 - 99% was achieved using the trained model.
Finally, this study also proposes to use a larger dataset to increase the confidence interval, as
well as different robots, such as land-based robots, to be tested out to better determine which
type of robot would be better in inspection of the niches. |
| first_indexed | 2024-10-01T03:22:12Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/176790 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:22:12Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1767902024-05-24T15:34:26Z Drone inspection with machine learning for asset maintenance Er, Tricia Yishan Law Wing-Keung, Adrian School of Civil and Environmental Engineering CWKLAW@ntu.edu.sg Engineering Drone inspection Machine learning Asset maintenance Inspection of niches in columbariums are important to ensure that the niches are in good condition. The current practice involves officers physically conducting visual inspections of the niches. However, this task is extremely repetitive and time consuming, causing it to be susceptible to human errors. This study seeks to investigate the use of drones and machine learning for niche inspections and evaluate the potential based on accuracy of the object detection model. First, a drone was selected and flown in laboratory conditions. Next, an object detection model was trained to identify the various classes identified. The classes included anomalies such as cracks and vandalism, which were represented by hand-drawn symbols. The object detection model was successfully trained using Roboflow after multiple rounds of trial and error using programs such as TensorFlow and Roboflow. Tests using the trained object detection model were carried out to ensure that the model was able to accurately identify the different classes. A confidence interval range of 67 - 99% was achieved using the trained model. Finally, this study also proposes to use a larger dataset to increase the confidence interval, as well as different robots, such as land-based robots, to be tested out to better determine which type of robot would be better in inspection of the niches. Bachelor's degree 2024-05-23T02:12:14Z 2024-05-23T02:12:14Z 2024 Final Year Project (FYP) Er, T. Y. (2024). Drone inspection with machine learning for asset maintenance. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/176790 https://hdl.handle.net/10356/176790 en EN-17 application/pdf Nanyang Technological University |
| spellingShingle | Engineering Drone inspection Machine learning Asset maintenance Er, Tricia Yishan Drone inspection with machine learning for asset maintenance |
| title | Drone inspection with machine learning for asset maintenance |
| title_full | Drone inspection with machine learning for asset maintenance |
| title_fullStr | Drone inspection with machine learning for asset maintenance |
| title_full_unstemmed | Drone inspection with machine learning for asset maintenance |
| title_short | Drone inspection with machine learning for asset maintenance |
| title_sort | drone inspection with machine learning for asset maintenance |
| topic | Engineering Drone inspection Machine learning Asset maintenance |
| url | https://hdl.handle.net/10356/176790 |
| work_keys_str_mv | AT ertriciayishan droneinspectionwithmachinelearningforassetmaintenance |