Numerous studies have developed extensions to the IFC schema to meet the needs of specialized domains or represent nascent technologies, and in turn have expanded the scope of interoperability for BIM data exchanges. However, these studies used varying approaches for IFC extensions and validation, making it difficult to identify research gaps and agree on legitimate extension protocols. This study collected 64 studies of IFC schema extensions spanning over two decades, from 2001 to 2022. The analysis first focused on categorizing these cases with respect to their target domains and sectors, their purpose and extension approaches, as well as their methods for implementation and validation. Timeline analyses were also conducted to track the temporal trends over the specified period. The results revealed that architectural cases have recently shifted from process to product representations due to new technology adoptions, while infrastructure cases, initially centered on major sector elements, have transitioned towards operation and maintenance processes. The findings also showed the need for a more holistic and organized approach for extensions, as current ad hoc developments were limited to products and processes only applicable for specific sectors.

Ensuring the correct mapping of model elements to Industry Foundation Classes (IFC) classes is fundamental for the seamless exchange of information between Building Information Modeling (BIM) applications, and thus achieve true interoperability. This research explored the possibility of employing novelty detection, a machine learning approach, as a way to detect potential misclassifications that occur during current ad hoc and manual mapping practices. By training the algorithm to learn the geometry of BIM elements for a given IFC class, outliers are detected automatically. A framework for leveraging multiple BIM models and training individual one-class SVM's was formulated and tested on four IFC classes. Performance results demonstrate the classification models to be robust and unbiased. The algorithms developed thus can be leveraged to check the integrity of IFC data, a prerequisite for BIM-based quality control and code compliance. Highlights The correct mapping of BIM elements to IFC classes is critical for IFC based interoperability. A framework is formalized for applying novelty detection to automate the checking of misclassifications. One-class SVM's are trained and tested on two architectural and two infrastructure IFC classes. Performance metrics indicate robust and unbiased models with high accuracy and true negative rates. Novelty detection is a superior approach to outlier detection in identifying misclassifications of BIM to IFC associations.

Safe Routes To School (SRTS) programs improve safety and health conditions as well as reduce the energy consumption and CO₂ emissions by encouraging more children to walk to school. Implementation of the programs requires improved infrastructure to create a safe walking environment to school. To achieve this goal, program participants should comprehensively and consistently evaluate the existing walking environments to prioritize the infrastructure required for improvement. However, in current practice, this evaluation process is challenging due to the lack of formal representation of the existing walking environments. To overcome this limitation, our research team developed an ontology required for the Building Information Model (BIM) to consistently and completely provide information about the existing walkability. The team applied this ontology to an elementary school in the United States and visualized the existing walkability by integrating BIM and Geographical Information System (GIS). Based on the visualization result, the team was able to explicitly describe the existing walkability to program participants. Consequently, we highlight that the ontology supports the participants in more consistently and comprehensively evaluating the existing walkability required for implementation of SRTS programs.

Ensemble learning is explored as an approach to improve the classification of BIM elements using multiple deep learning classifiers. Existing studies have focused on improving the performance of a single classifier, thereby restricting the types of features available for training. Two classifiers, MVCNN and MLP were trained on nine BIM element classes extracted from a 20-story office building. MVCNN used multiple images of these elements, while MLP used adjacency relations between elements. The predictions of the classifiers were then ensembled using a maximum rule-based algebraic combiner. Results showed that the overall classification accuracy improved by +0.05. The Ensemble model, in effect, leveraged the strength of each classifier: MVCNN for elements with distinct features and MLPs for elements with high similarity. The Ensemble model enables the automatic checking of the semantic accuracy of elements in BIM models, thus endorsing the seamless information exchanges required for true interoperability in BIM-centric project collaboration.

More than ten years have passed since Building Information Modeling (BIM) was introduced in Korea, but the industry lacks established approaches to assist firms in estimating the costs of providing additional BIM services in the design phases of a project. The deficiency also inhibits government agencies to allocate discrete and reasonable budgets when requesting BIM related services. This research focuses on the Architecture and Engineering (AE) industry and provides a framework to estimate costs for BIM design services based on the cost-plus pricing approach. The framework utilizes cost data from 54 projects to estimate average man-hours, and ‘man-hour coefficients’ for standard and non-standard work items. The man-hours can further be broken down to different design phases, disciplines and at different levels of development. The framework was implemented in an Excel-based system, which allows users to produce estimates for 11 different building project types, while providing flexibility in selecting preferred BIM services. Validation showed that the system produces accurate estimates for specific projects with customized requirements. By providing an objective approach for estimating the costs of BIM services, it allows clients and AE firms to agree upon a fair cost, and thus expedite its adoption in Korea.

Recent studies in the domain of semantic enrichment have employed artificial intelligence (AI) approaches to distinguish and classify building information modeling (BIM) elements to check their conformance with open standard data formats. Training AI algorithms requires the development of well-balanced and robust datasets of BIM elements. However, collection is difficult as sources are limited to existing models and sample libraries. This study developed a parametric augmentation approach to create synthetic copies of BIM elements, and thus rapidly supplement manually collected samples. The approach was used to create ArchShapesNet, a dataset consisting of 11 common architectural elements with an equal size of 4,000 samples per class. Two multi-view convolutional neural networks (CNN), a geometric deep learning algorithm, were trained and tested separately on ArchShapesNet and an initial dataset with sample imbalances. Results showed significant improvement in the accuracy and F₁ scores, providing evidence of the utility of ArchShapesNet. The size and scope of the dataset are considered to be the first of their kind and provide a benchmark for testing the semantic integrity of BIM models. The augmentation approach also provides a general framework to create custom datasets for different specialties in the Architectural Engineering and Construction industry.