Automated look-ahead schedule generation using linked-data based constraint checking for construction projects
This PhD study was cosponsored by Bentley Systems UK and a through a Skempton Scholarship from the Department of Civil and Environmental Engineering, Imperial College London. This project started on March 2017 and is due to finish by end of July 2020.
This PhD study focuses on developing a data-driven approach to support look-ahead planning through the development of an information modelling approach to codify and validate detailed construction process information. The proposed approach comprises information modelling, constraint checking and automated Look-Ahead Schedule (LAS) generation. Constraint checking validates the up-to-date construction information against a set of modelled constraints. This process identifies the activities that are scheduled, however, cannot be executed due to violation of modelled constraints. LAS generation method produces a list of activities that are ready to be executed for a time period.
Aim and Objectives
The research aim is to develop an information modelling approach to codify and validate detailed construction process information in BIM-enabled projects, in order to support data-driven decision-making for look-ahead planning in construction.
Three objectives are framed around the research aim. The objectives are as follows.
Objective 1: To understand the codification challenges in the late-design and construction phase of BIM-enabled projects;
Objective 2: To develop an information modelling approach to codify and validate construction process information including dynamic constraint information; and
Objective 3: To develop a method to generate look-ahead-schedule for construction projects automatically using the codified process information.
- The partial codification of information in machine-readable formats is based on a range of challenges in late design and construction phases of BIM-enabled projects, related to software and information sharing, with a particular lack of process information.
- The issue of data siloes in construction information can be addressed by leveraging the power of linked-data to traverse across the web of data created by linking across the heterogeneous construction information datasets.
- Linked data based constraint checking method using SHACL can be effectively used to model and validate construction scheduling constraints distributed over multiple datasets, thus supporting look-ahead planning.
- Construction information codified using linked data based constraint checking method can be reused to generate look-ahead-schedules by incorporating linked data based constraint checking within the machine learning framework.
- Soman, R.K., & Whyte, J.K. (2020), Codification challenges for data science in construction, ASCE Journal of construction engineering and management, 146 (7), 04020072.
- Soman, R.K. (2019), Linked-data based dynamic constraint solving framework to support look-ahead-planning in construction, 36th International Council for Research and Innovation in Building and Construction W78 Conference on ICT in Design, Construction and Management in Architecture, Engineering, Construction and Operations (AECO), Newcastle, United Kingdom.
- Soman, R.K. (2019). Modelling construction scheduling constraints using Shapes Constraint Language (SHACL), European Conference on Computing in Construction (EC³ 2019). Crete, Greece.
- Senthilvel, M., Soman, R.K., Mahalingam, A., Whyte, J.K., Raphael, B., Brilakis, I., & Varghese, K. (2018). Towards digital delivery of metro-rail projects in India. 7th World Construction Symposium 2018: Built Asset Sustainability: Rethinking Design, Construction and Operations. Colombo, Sri Lanka.
- Soman, R.K., Birch, D., & Whyte, J.K. (2017). Framework for shared visualization and real-time information flow to the construction site. 24th European Group for Intelligent Computing in Engineering (EG-ICE) International Workshop on Intelligent Computing in Engineering. Nottingham, UK.
- Soman, R.K., & Whyte, J.K. (2017). A framework for cloud-based virtual and augmented reality using real-time information for construction progress monitoring. Lean & Computing in Construction Congress (LC3). Heraklion, Greece.
The current study is the first step toward a linked-data-based constraint-checking environment. To exploit the full potential of this method, further research should be done to extend the linked-data-based constraint-checking environment method. Researchers working on linked-data in the architecture and construction domain can extend this method to investigate the applicability of this method to detect violations related to workspace constraints, construction safety constraints, and construction-site layout constraints by exploiting the geometric data in the domain models.
The research is being done at Centre for Systems Engineering and Innovation and is funded through Skempton scholarship and co-sponsored by Bentley Systems. Ranjith spent 6 months (October 2018-March 2018) at the The Alan Turing Institute using the PhD enrichment scheme at Turing.