Different state DOTs have attempted to use safety leading indicators for heavy construction projects. 7
NCDOT has contractors’ prequalification guidelines and a formal process for constructability review 8
meetings. However, the safety component is not much considered, which may result in disruption of 9
construction activities due to potential site safety violations. The current prequalification process for 10
contractors requires multiple changes to improve the contractors’ selection process and secure a safe job 11
site. Prequalification process may be revised to incorporate a safety scoring system that considers the 12
contractors history, OSHA citations, availability of in-house safety plans and safety audits, availability of 13
competent persons and OSHA trainers, and formal safety training attended by the contractor’s company 14
personnel. Similarly, NCDOT formal CR meeting needs to incorporate a safety matrix to be revised by 15
project stakeholders during the meeting. The safety matrix should tie different site activities – listed in 16
NCDOT standard bid template – with the respective OSHA big four construction hazard. 17
18
Performance-based contractor prequalification allows NCDOT personnel to evaluate contractors past 19
performance on similar work to ensure high-quality work in future projects. Occupational safety and 20
health criteria are somehow included in such prequalification to limit construction site accidents and 21
violations. However, current matrix/safety prequalification criteria have significant shortfalls. In this 22
proposed research (implementation plan), the project research team will focus on utilizing artificial 23
intelligence (AI) and machine learning (ML) applications to decide on the attributes relevant to job site 24
safety and the most important parameters to be used in contractors’ prequalification procedures. The 25
research tasks will use the developed criteria through the current project phase, collect information from 26
NCDOT, other state DOTs, and OSHA to train a machine learning model to be developed specifically to 27
evaluate the correlation between different attributes and possible “future” performance of the contractor. 28
Attributes include – but not limited to – contractor’s size, budget, safety practices, previous experience, 29
employee turnover, OSHA records, and experience modification rating. Predictive analytics will provide 30
NCDOT personnel with proper algorithm to assess/predict possible contractor’s performance. The 31
outcomes of this research will result in seamless flow of construction site activities, reduced accidents, 32
and avoiding arbitration and litigation.
