- 136 views
- 136 downloads
BIM Clash Report Analysis Using Machine Learning Algorithms
-
- Author / Creator
- Adegun, Ibironke
-
Clash detection has been argued as one of the most beneficial BIM (Building Information Modelling) applications. However, the clash resolution process is still manually conducted and time-consuming, and BIM information is not fully utilized to facilitate automatic clash resolution.
Previous research employed machine learning and data mining methodologies to examine model coordination information and enhance the process of decision-making. Nevertheless, there are still deficiencies. Moreover, no prior study has pinpointed the attribute combination required for the precise anticipation of clash significance.
This research explores machine learning through two main avenues: firstly, categorizing clashes by image recognition and numerical data. Applying a Convolutional Neural Network multilayer (CNN) algorithm to different combinations of clashes achieved a precision of over 80%. The image clash recognition algorithm was also developed using YOLO v8’s supervised CNN algorithm.
By forecasting clash significance with a high level of accuracy and recognizing the essential characteristics, this research makes a valuable contribution to the field of study within BIM and model coordination. Previous research had overlooked the collection of clashes across all disciplines and the identification of critical attribute combinations that result in accurate predictions. Furthermore, the development of a predictive model for clash significance presents new possibilities for professionals in the industry to enhance the efficiency of model coordination meetings by considering the disciplines, elements, and volumes of the clashes. -
- Subjects / Keywords
-
- Graduation date
- Fall 2024
-
- Type of Item
- Thesis
-
- Degree
- Master of Science
-
- License
- This thesis is made available by the University of Alberta Library with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.