Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Project Leanness Score: A Machine Learning Approach
The construction industry is known to have several inadequacies in resource utilization leading to cost and schedule overruns. One of the popular recent methods that attempts to eliminate these inadequacies is lean construction principles, techniques and tools. Lean construction is a philosophy, bac...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2022
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | The construction industry is known to have several inadequacies in resource utilization leading to cost and schedule overruns. One of the popular recent methods that attempts to eliminate these inadequacies is lean construction principles, techniques and tools. Lean construction is a philosophy, backed with principles and tools, aiming at maximizing value, eliminating waste, optimizing efficiency, and seeking continuous improvement. Lean construction techniques (such as pull planning, just-in-time delivery, fail safe for quality, etc.) are widely researched and well developed. However, their implementation in construction sites is tricky as their success depends on several other factors such as the level of trust, the use of supporting technologies, and the resistance to cultural change. In other words, just by implementing lean construction tools does not guarantee reduction in cost and time overruns. There is a gap when it comes to identifying the factors that support the success/failure of implementing lean construction tools, and quantifying the impact of those factors to the actual performance of construction projects. The goal of this research is to develop and benchmark a scoring system that utilizes lean principles to evaluate the “leanness” of construction projects and predict their performance. To achieve such goal, the methodology of the research follows a series of six steps. First is identifying the key factors that influence the “leanness” of construction projects. Second, determining the significance and relative importance of the identified factors through an expert-based survey. Third, developing a novel leanness score using the established relative importance of the factors. Fourth, benchmarking the leanness score representing the industry’s performance through collecting extensive project data from 30 construction projects. Fifth, training and validating models using machine learning algorithms such as regression, decision trees, and artificial neural networks to predict the schedule and budget performance of construction projects using the factors of the leanness score. Lastly, developing a user-friendly tool that enables companies to easily calculate the leanness score of their projects, compare it to the benchmarks, and predict their schedule and cost performance. The outcomes of this research fill the existing gap since it aims to develop a leanness index and link it to project performance. Moreover, it presents a detailed level of performance assessment through breaking down the leanness score and indicating areas of strength and weakness in the project. Also, the developed benchmarking scale enables companies to compare their level of leanness to that of other companies in the industry. In addition, the developed multiclass classification neural networks model can predict and categorize project iv schedule and budget performance with an accuracy of 96% and 94% respectively. With this, companies will be able to benchmark the performance of their projects, pinpoint the areas of strengths and weaknesses with respect to the benchmarks, and take necessary actions to meet industry practices. Thus, improving the overall quality of construction projects, decreasing overruns. |
|---|