Visual Data and Predictive Analytics for Proactive Project Controls on Construction Sites

摘要

This paper presents the theoretical foundation for a project controls system that improves understanding of how construction performance can be captured, communicated, and analyzed in form of a visual production system; predicts and effectively communicates the reliability of the weekly work plan and look-ahead schedules, supports root-cause assessment on plan failure at both project and task-levels; facilitates information flows; and decentralizes decision-making. Our model-driven system builds upon novel visual data analytics to map the current state of production in 4D (3D+time), compare to 4D BIM, and expose waste at both project and task-levels. Using predictive analytics and based on actual progress and productivity data, reliability in the future state of production is forecasted to highlight potential issues in a location-driven scheme and support collaborative decision making that eliminates root causes of waste. To evaluate the performance of our system, several case studies are conducted on real-world commercial building projects. It is shown that the developed system provides visual interfaces between people and information on and offsite, enables effective pull flows, decentralizes work tracking, facilitates in-process quality control and hand-overs among contractors, and most importantly transforms retroactive and task-driven workflows in contractor coordination meetings to proactive location-driven practices.