Automating look-ahead schedule generation for construction using linked-data based constraint checking and reinforcement learning

Soman, Ranjith K.; Molina-Solana, Miguel

doi:10.1016/j.autcon.2021.104069

Cited by 28 publications

(7 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, 2014). The high subjectivity of the manual work means the task is time-consuming, error-prone, and tedious (Soman and Molina-Solana, 2022). Therefore, an automatic and accurate construction schedule generation method plays a critical role in improving management efficiency and innovating management mode.…”

Section: Introductionmentioning

confidence: 99%

“…The current issue and full text archive of this journal is available on Emerald Insight at: https://www.emerald.com/insight/0969-9988.htm consuming, error-prone, and tedious (Soman and Molina-Solana, 2022). Therefore, an automatic and accurate construction schedule generation method plays a critical role in improving management efficiency and innovating management mode.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Automatic generation of BIM-based construction schedule: combining an ontology constraint rule and a genetic algorithm

Guo²

2022

ECAM

View full text Add to dashboard Cite

PurposeThe purpose of this study is to automatically generate a construction schedule by extracting data from the BIM (Building Information Modeling) model and combining an ontology constraint rule and a genetic algorithm (GA).Design/methodology/approachThis study developed a feasible multi-phase framework to generate the construction schedule automatically through extracting information from the BIM, utilizing the ontology constraint rule to demonstrate the relationships between all the components and finally using the GA to generate the construction schedule.FindingsTo present the functionality of the framework, a prototype case is adopted to show the whole procedure, and the results show that the scheme designed in this study can quickly generate the schedule and ensure that it can satisfy the requirements of logical constraints and time parameter constraints.Practical implicationsA proper utilization of conceptual framework can contribute to the automatic generation of construction schedules and significantly reduce manual errors in the Architectural, Engineering, and Construction (AEC) industry. Moreover, a scheme of BIM-based ontology and GA for construction schedule generation may reduce additional manual work and improve schedule management performance.Social implicationsThe hybrid approach combines the ontology constraint rule and GA proposed in this study, and it is an effective attempt to generate the construction schedule, which provides a direct indicator for the schedule control of the project.Originality/valueIn this study, the data application process of the BIM model is divided into four modules: extraction, processing, optimization, and output. The key technologies including secondary development, ontology theory, and GA are introduced to develop a multi-phase framework for the automatic generation of the construction schedule and to realize the schedule prediction under logical constraints and duration interference.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Automatic generation of BIM-based construction schedule: combining an ontology constraint rule and a genetic algorithm

Guo²

2022

ECAM

View full text Add to dashboard Cite

show abstract

“…They allow project managers to automatically generate optimised schedules based on different scenarios and AI algorithms [60][61][62][63]. However, representing and integrating uncertain knowledge while generating onsite construction schedules is still the main weakness of these methods [51].…”

Section: Planning Methodsmentioning

confidence: 99%

The Creation of Construction Schedules in 4D BIM: A Comparison of Conventional and Automated Approaches

2022

View full text Add to dashboard Cite

Building Information Modelling (BIM) is now a globally recognised phenomenon, though its adoption remains inconsistent and variable between and within the construction sectors of different countries. BIM technology has enabled a wide range of functional applications, one of which, ‘4D BIM’, involves linking the tasks in a project’s construction schedule to its object-orientated 3D model to improve the logistical decision making and delivery of the project. Ideally, this can be automatically generated but in reality, this is not currently possible, and the process requires considerable manual effort. The level of maturity and expertise in the use of BIM amongst the project participants still varies considerably; adding further obstacles to the ability to derive full benefits from BIM. Reflecting these challenges, two case studies are presented in this paper. The first describes a predominantly manual approach that was used to ameliorate the implementation of 4D BIM on a project in Paris. In fact, there is scope for automating the process: a combination of BIM and Artificial Intelligence (AI) could exploit newly-available data that are increasingly obtainable from smart devices or IoT sensors. A prerequisite for doing so is the development of dedicated ontologies that enable the formalisation of the domain knowledge that is relevant to a particular project typology. Perhaps the most challenging example of this is the case of renovation projects. In the second case study, part of a large European research project, the authors propose such an ontology and demonstrate its application by developing a digital tool for application within the context of deep renovation projects.

show abstract

“…Hyun et al [29] developed a multi-objective optimization tool for modular unit production lines based on GAs that assumes that the duration of activities on a production line in modular construction depends on the number of workers, and reducing construction duration and labour cost will be the optimization objectives. Soman and Molina-Solana [30] presented a novel Look-Ahead Schedule generation method that uses reinforcement learning algorithms and linked data-based constraint checking to help construction planners as a decision support system. The output schedule is compared with the manually generated one, with the critical path method, and with the modified GA by Liu et al [28].…”

mentioning

confidence: 99%

A genetic algorithm-based approach for the time, cost, and quality trade-off problem for construction projects

Bragadin,

Kähkönen,

Pozzi

2023

Tema

View full text Add to dashboard Cite

Quality identifies the overall level of performance of the desired building facility or civil infrastructure. Quality can include safety and sustainability requirements, and planning the desired quality level is paramount in construction projects. Nevertheless, two other significant project management Key Performance Indicators (KPIs) must be considered in construction project management: time and cost. Project Managers always perform a trade-off between these three KPIs, but it is known that the relationship between these three indicators can be difficult to understand. Therefore, a multi-objective Genetic Algorithm (GA) has been proposed to develop a comprehensive approach to optimize project performance in construction. The proposed multi-objective GA can be used as a decision support system for the detailed design stage of a construction project to detect better and alternative detailed design and construction solutions. A GA is an Artificial Intelligence application (AI) that develops an evolutionary learning optimization process that discards worse solutions and re-introduces better solutions with an iterative process. Therefore, the most suitable solution can be found by performing a trade-off between the three indicators. The research aims to demonstrate the availability of AI applications to understand and perform the Time-Cost-Quality trade-off for construction projects. The developed procedure has been tested on a simple pilot study of a building renovation project, and the best-found optimized results have been detected with Solv-er® and discussed. Future research work will be aimed at improving the procedure's efficiency so that it can be implemented in larger projects.

show abstract

Automating look-ahead schedule generation for construction using linked-data based constraint checking and reinforcement learning

Cited by 28 publications

References 75 publications

Automatic generation of BIM-based construction schedule: combining an ontology constraint rule and a genetic algorithm

Automatic generation of BIM-based construction schedule: combining an ontology constraint rule and a genetic algorithm

The Creation of Construction Schedules in 4D BIM: A Comparison of Conventional and Automated Approaches

A genetic algorithm-based approach for the time, cost, and quality trade-off problem for construction projects

Contact Info

Product

Resources

About