Automated Scaffolding Safety Analysis: Strain Feature Investigation using Support Vector Machines
Canadian Journal of Civil Engineering
First page number:
Last page number:
This study developed a methodology that can use real-time strain data for the assessment of scaffolding safety conditions. The researchers identified 23 safety cases of individual member failure with generic global failure for a four-bay, three-story scaffold model and used scaffold member strain values to identify potential failure cases. A computer simulation on the scaffold model generated the strain datasets required for classification with a support vector machine (SVM). The SVM classification demonstrated a stable prediction accuracy after training with a certain number of strain datasets. Furthermore, the 2nd order polynomial kernel function resulted in better prediction compared to other SVM kernel functions. These results imply that the real-time assessment of scaffolding structures is possible with a limited number of training data for machine-learning classification.
Scaffold; Construction Site; Safety; Machine Learning; SVM
Civil and Environmental Engineering | Engineering
Arteaga Sanchez, C.,
Park, J. W.,
Automated Scaffolding Safety Analysis: Strain Feature Investigation using Support Vector Machines.
Canadian Journal of Civil Engineering, 47(8),