TY  - CONF
TI  - Predictive Simulation for Automated Decision-Support in Production Planning and Control
AU  - Yeung, Timson
AU  - Ribón, Jhonattan Guillermo Martinez
AU  - Sharoni, Li-Or
AU  - Sacks, Rafael
AU  - Pitkäranta, Tomi
AD  - Doctoral Candidate, Seskin Virtual Construction Laboratory, Technion – IIT, Haifa, Israel,  timsonyeung@campus.technion.ac.il, https://orcid.org/0000-0002-2195-0801
AD  - Postdoctoral Researcher, Seskin Virtual Construction Laboratory, Technion – IIT, Haifa, Israel,  jonattanm@campus.technion.ac.il, https://orcid.org/0000-0001-6715-4440
AD  - M.Sc. Student, Seskin Virtual Construction Laboratory, Technion – IIT, Haifa, Israel,  li_or@campus.technion.ac.il, https://orcid.org/0000-0002-2831-3290
AD  - Professor, Head of National Building Research Institute, Seskin Virtual Construction Laboratory, Technion – IIT, Haifa, Israel, cvsacks@technion.ac.il, https://orcid.org/0000-0001-9427-5053
AD  - Head of Concept and Partnerships, Sitedrive Oy, Helsinki, Finland, tomi.pitkaranta@sitedrive.com,  https://orcid.org/0000-0003-1100-0578
PY  - 2023
DA  - 2023/06/26
T2  - Proceedings of the 31st Annual Conference of the International Group for Lean Construction (IGLC31)
C3  - Proceedings of the 31st Annual Conference of the International Group for Lean Construction (IGLC31)
CY  - Lille, France
SP  - 1279
EP  - 1290
DO  - 10.24928/2023/0186
SN  - 2789-0015 (ISSN)
AB  - Production system design, planning and control are limited both by the incomplete situational awareness of planners and by their inability to predict the range of possible outcomes of their planning and control decisions. With the development of information technologies for monitoring products and processes on construction sites, it is increasingly possible to provide detailed status information describing the as-built products ‘as-built’ and processes ‘as-performed’. This opens the door to applying predictive analytics to provide decision-makers with frequent predictions of the outcomes for a range of changes they might contemplate to the production system design, even during construction. Within the BIM2TWIN project, we are designing and implementing an agent-based simulation engine that is a core component of an Automated Decision Support System. Currently, the simulation can be calibrated to accurately predict the range of likely project durations for a residential construction project. However, certain aspects of the trade crews’ performance, particularly with respect to the completion of tasks, appear to differ from the behaviours described by industry experts and encapsulated in the crew agent behaviour tree in the simulation.
KW  - Production system design
KW  - production planning and control
KW  - agent-based simulation
KW  - decisionsupport.
L1  - https://www.iglc.net/papers/details/2122/pdf
UR  - https://www.iglc.net/papers/details/2122
DB  - IGLC.net
LA  - English
N1  - Export date: 04 October 2026
ER  -