Using Geometry based Anomaly Detection to check the Integrity of IFC classifications in BIM Models

Abstract

Although Industry Foundation Classes (IFC) provide standards for exchanging Building Information Modeling (BIM) data, authoring tools still require manual mapping between BIM entities and IFC classes. This leads to errors and omissions, which results in corrupted data exchanges that are unreliable and thus compromise the validity of IFC. This research explored precedent work by Krijnen and Tamke, who suggested ways to automate the mapping of IFC classes using a machine learning technique, namely anomaly detection. The technique incorporates geometric features of individual components to find outliers among entities in identical IFC classes. This research primarily focused on applying this approach on two architectural BIM models and determining its feasibility as well as limitations. Results indicated that the approach, while effective, misclassified outliers when an IFC class had several dissimilar entities. Another issue was the lack of entities for some specific IFC classes that prohibited the anomaly detection from comparing differences. Future research to improve these issues include the addition of geometric features, using novelty detection and the inclusion of a probabilistic graph model, to improve classification accuracy.

Applying Ai Technology to Recognize Bim Objects and Visible Properties for Achieving Automated Code Compliance Checking

“…In this study, the authors only derive further judgments using the space-object relationship based on the AI recognition results for BIM object recognition. In addition to the space-object relationship, other factors should also be considered, such as the relationship between objects as well as the ratio of an object's internal dimensions (Krijnen & Tamke, 2015;Koo & Shin, 2017;Sacks et al, 2017;Koo et al, 2019). If these factors are integrated, the recognition of the system will be more intelligent, which, in turn, would lead to more accurate results.…”

“…Recent studies have also explored the use of machine learning and deep learning methods to alleviate the semantic enrichment problem in BIM models. For instance, Krijnen and Tanke (2015) proposed an anomaly detection method for checking IFC classifications; this approach is a form of machine learning (ML) technology (Koo & Shin, 2017). Koo and Shin (2018) adopted a novel detection method to detect misclassified BIM elements.…”