Evaluating 3D Concrete Printing Effectiveness Through a Comparative Study Using SVM, Decision Trees, and Random Forest Techniques (2024-12)¶

This study explores the intricate dynamics of 3D concrete printing within the construction sector, emphasizing the key factors that influence its effective application. By simulating 3D concrete printing processes for both a 2-floor and a 12-floor building, a comprehensive dataset was generated. Machine learning models, including Support Vector Machines, Decision Trees, and Random Forests, were employed to analyze this dataset. Among these, the Random Forest model proved to be the most effective, achieving an accuracy of 94.2%, precision of 93.4%, recall of 94.0%, and an F1-score of 93.7%. Variables such as extrusion speed and robot location were identified as critical to the printing process. The findings highlight the potential of machine learning in optimizing 3D concrete printing, offering valuable insights for the construction industry. This research paves the way for a more efficient, data-driven approach to 3D concrete printing, underscoring the synergy between construction and technology.