TY - GEN
T1 - Feasibility analysis on the use of NLP-based schedule analytics for 4D project planning and controls
AU - Jung, Yoonhwa
AU - Hockenmaier, Julia
AU - Golparvar-Fard, Mani
N1 - This material is in part based upon works supported by NSF [1446765,2020227]. The opinions, findings, and conclusions or recommendations expressed are those of the authors and do not reflect the views of the NSF, or the companies mentioned above.
PY - 2024
Y1 - 2024
N2 - 4D (3D + time) building information modeling (BIM) brings important benefits to the practice of project planning and controls in construction. Despite well-documented benefits, the level of technical effort necessary to create 4D BIM by manually tying in BIM elements with schedule activities has been a significant barrier to its wider adoption. To address it, this paper explores the possibility of identifying in each schedule activity based on ASTM's Uniformat classification and then automatically mapping it to the most relevant BIM elements in its corresponding work location. Specifically, the feasibility of training a transformer-based natural language processing model to infer Uniformat classification of a schedule activity is explored. Results from testing the proposed model on four real-word project schedules show the potential for a path forward toward automated 4D BIM creation. Insights from the performance of this model and a path forward for model improvements are discussed.
AB - 4D (3D + time) building information modeling (BIM) brings important benefits to the practice of project planning and controls in construction. Despite well-documented benefits, the level of technical effort necessary to create 4D BIM by manually tying in BIM elements with schedule activities has been a significant barrier to its wider adoption. To address it, this paper explores the possibility of identifying in each schedule activity based on ASTM's Uniformat classification and then automatically mapping it to the most relevant BIM elements in its corresponding work location. Specifically, the feasibility of training a transformer-based natural language processing model to infer Uniformat classification of a schedule activity is explored. Results from testing the proposed model on four real-word project schedules show the potential for a path forward toward automated 4D BIM creation. Insights from the performance of this model and a path forward for model improvements are discussed.
UR - http://www.scopus.com/inward/record.url?scp=85184284165&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85184284165&partnerID=8YFLogxK
U2 - 10.1061/9780784485224.006
DO - 10.1061/9780784485224.006
M3 - Conference contribution
AN - SCOPUS:85184284165
T3 - Computing in Civil Engineering 2023: Data, Sensing, and Analytics - Selected Papers from the ASCE International Conference on Computing in Civil Engineering 2023
SP - 42
EP - 50
BT - Computing in Civil Engineering 2023
A2 - Turkan, Yelda
A2 - Louis, Joseph
A2 - Leite, Fernanda
A2 - Ergan, Semiha
PB - American Society of Civil Engineers
T2 - ASCE International Conference on Computing in Civil Engineering 2023: Data, Sensing, and Analytics, i3CE 2023
Y2 - 25 June 2023 through 28 June 2023
ER -