Building Information Models’ data for machine learning systems in construction management (fo)
Paper in proceedings, 2019

A vast amount of data can be used within construction management, reflecting both qualitative information and quantitative material. However, despite the capabilities offered by construction informatics, such data has scarcely been utilized systematically and in its full capacity for descriptive and predictive purposes; as such, all possible data sources have not been exploited to their full extent. Building Information Models (BIM), increasingly used within the construction industry and deeply integrating within the business models of construction firms and organizations, are such a data source. Within BIM, there are numerous structures acting as interoperable sources of utilizable data and information throughout the lifecycle and the various Levels of Development (LODs) of a construction project – for example, Industry Foundation Classes (IFCs), aecXML, change logs, and component-related databases – that are currently under-exploited. To fully and meaningfully exploit the data pools that BIM present, data mining can be utilized, namely the set of processes that computationally discover and comprehend patterns in datasets. More particularly, machine learning, used at the peak of state-of-the-art data mining and defined as the exploration of algorithms that enable computing systems to “learn” and make data-driven predictions by building a model from a sample dataset and without being explicitly programmed, can be at the methodological forefront of fully exploiting all data found in BIM. In this paper, the capabilities of the information structures found in BIM (and especially IFCs) to be used as data sources for developing machine learning predictive models, will be examined. In addition, and by tying the potentially extracted data with the concept of constructability, their suitability for predicting – through such machine learning models – the cost and time overheads in the delivery of a construction project, will be considered.

machine learning

construction informatics

Building Information Models

Industry Foundation Classes

data mining

Author

Dimosthenis Kifokeris

Chalmers, Architecture and Civil Engineering, Construction Management

Mattias Roupé

Chalmers, Architecture and Civil Engineering, Construction Management

Mikael Johansson

Chalmers, Architecture and Civil Engineering, Construction Management

Christian Koch

Chalmers, Architecture and Civil Engineering, Construction Management

CCC 2019 Creative Construction Conference
Budapest, Hungary,

Areas of Advance

Information and Communication Technology

Building Futures (2010-2018)

Production

Driving Forces

Sustainable development

Innovation and entrepreneurship

Subject Categories

Construction Management

Environmental Analysis and Construction Information Technology

Other Civil Engineering

Building Technologies

More information

Latest update

3/5/2019 7