Wonbok Lee

This study presents KDS2Code, a practical workflow for automatically translating engineering codes, specifically Korean Design Standards (KDS), into executable Python implementations to support BIM-based Automated Code Checking (ACC). The proposed approach integrates hierarchical document parsing, table recognition, hybrid rule identification using regex-based filtering and LLM-based semantic classification, template-constrained code generation, and multi-level validation. A key feature is the separation of computational and non-computational clauses, enabling the extraction of implementable computational rules from text-based standards. The method was evaluated on four KDS 11 geotechnical and foundation-related documents. Across the evaluation set, 45 computational rules were identified and translated into Python implementations. Among them, 14/17 ground-truth (GT) rules achieved reference-based functional agreement. Separately, the 28 newly discovered rules achieved 27/28 initial and 28/28 corrected smoke-test passes. All generated implementations achieved structure validity, and no aggregated correctness rate was reported. The results indicate that remaining discrepancies mainly arise from ambiguity in engineering standard specifications rather than syntax, structure, or runtime failures. Overall, KDS2Code demonstrates an initial step toward scalable engineering-standard-to-code translation for digitalizing engineering standards in ACC applications.

Automated clash detection in Building Information Modeling (BIM) often produces an excessive number of results, many of which are irrelevant or non-critical to constructability. This burden requires project teams to manually filter clashes, introducing inefficiency and subjectivity. To address this limitation, this study proposed a deep learning–based framework for classifying irrelevant clashes into penetration categories that reflect their constructability implications. A taxonomy of 15 categories was developed through expert consultation, differentiating penetrations by orientation, size, and shape. Two multi-view architectures were evaluated: the Multi-View Convolutional Neural Network (MVCNN), a widely adopted baseline, and the Multi-View Vision Transformer (MVT), a state-of-the-art architecture designed to capture inter-view dependencies through attention mechanisms. A dataset generated from a federated BIM model was used to train and test both models. Results showed that MVT achieved superior performance across accuracy and F1-score, with particular improvements in minority categories involving small or diagonal penetrations. IoU-based analysis further demonstrated that MVT attended more precisely to clash regions, enhancing interpretability. The findings confirmed that Transformer-based multi-view learning offers significant advantages for clash classification. By linking automated classification with reinforcement and constructability requirements, the proposed framework supports more reliable constructability analysis, cost estimation, and project planning.

As the digitalization of construction standards accelerates, the integration of structural analysis results into Building Information Modeling (BIM) environments has become a critical prerequisite for effective BIM-based Automated Code Checking (ACC), particularly for structural code compliance. In current practice, structural analysis results generated by Computer-Aided Engineering (CAE) tools are often manually transferred into IFC-based BIM models, leading to inefficiencies and increased risk of human error. To address this limitation, this study proposes an extended IFC-based representation, termed IFC-KR-Structure, designed to systematically organize and manage section-wise and load combination-dependent structural analysis results required for code compliance within the IFC environment. Based on the proposed schema, an automated CAE-to-BIM integration module was implemented within the IFC-KR Toolkit to enable direct integration of analysis results generated by a commercial CAE tool (midas Civil NX) into IFC models. The approach establishes consistent element correspondence between structural and BIM models through coordinate alignment and spatial mapping procedures and represents multidimensional analysis results using a schema-compliant, tabular data structure embedded within IFC models. The applicability of the proposed framework was validated using a prestressed concrete girder bridge case, confirming that structural analysis results were accurately mapped, stored, visualized, and subsequently utilized within a BIM-based ACC workflow. The results demonstrate that the proposed approach enables systematic reintegration of CAE-generated analysis results into BIM models and significantly improves the efficiency, consistency, and reliability of BIM-based code compliance processes.

As the digitalization of construction standards accelerates, the integration of structural analysis results into Building Information Modeling (BIM) environments has become a critical prerequisite for effective BIM-based Automated Code Checking (ACC), particularly for structural code compliance. In current practice, structural analysis results generated by Computer-Aided Engineering (CAE) tools are often manually transferred into IFC-based BIM models, leading to inefficiencies and increased risk of human error. To address this limitation, this study proposes an extended IFC-based representation, termed IFC-KR-Structure, designed to systematically organize and manage section-wise and load combination–dependent structural analysis results required for code compliance within the IFC environment. Based on the proposed schema, an automated CAE-to-BIM integration module was implemented within the IFC-KR Toolkit to enable direct integration of analysis results generated by a commercial CAE tool (midas Civil NX) into IFC models. The approach establishes consistent element correspondence between structural and BIM models through coordinate alignment and spatial mapping procedures and represents multidimensional analysis results using a schema-compliant, tabular data structure embedded within IFC models. The applicability of the proposed framework was validated using a prestressed concrete girder bridge case, confirming that structural analysis results were accurately mapped, stored, visualized, and subsequently utilized within a BIM-based ACC workflow. The results demonstrate that the proposed approach enables systematic reintegration of CAE-generated analysis results into BIM models and significantly improves the efficiency, consistency, and reliability of BIM-based code compliance processes.

In Korea, research initiatives have commenced to digitize engineering and construction codes, and automate their compliance using BIM models for mandatory submission in public projects. The initiatives require employing IFC, a neutral and standard data format, to associate individual codes with relevant BIM elements. However, the IFC does not provide explicit extensions to represent the varied codes, which include the Korean Design Standards (KDS) and the Korean Construction Specifications (KCS). To address this limitation, this study developed an extended IFC schema called 'IFC-KR', focusing initially on bridges. The extensions define subtypes to represent various types of bridges, structures, and elements, along with property sets that capture the relevant attributes and properties of 1,437 KDS codes. Moreover, a specialized extension module named 'IFC-KR Toolkit' has been developed to automate the addition of KDS data relevant to each element within the IFC Physical File. To validate the functionality of the module, KDS items were applied to an Extradosed (ED) cablestayed bridge model. The results confirmed that all data were accurately integrated, and the extended data was consistently verified using a third-party IFC viewer, demonstrating its accuracy and interoperability.

This study aimed to evaluate ChatGPT-3.5 and ChatGPT-4’s understanding of the building information modelling (BIM) knowledge domain by testing on the multiple-choice section of Korea's BIM Expertise Exam (KBEE), a professional license exam tailored for BIM. ChatGPT-4 achieved passing scores across all tested years and averaged 85%, 20% higher than its predecessor. Nevertheless, ChatGPT-4 had difficulty in certain areas including the ‘BIM guidelines’ subcategory, as the problems required access to documents specific to Korea's BIM policies and stipulations. By supplying the required documents using Retrieval Augmented Generation (RAG), GPT-4’s score further improved to 88.6%, an improvement of 25.7%. The results provide evidence that ChatGPT-4, albeit within the context of the KBEE, is overall knowledgeable in its understanding of the BIM domain. The results of RAG demonstrate that partial gaps in its knowledge can be bolstered by providing the appropriate documents. The study verified that this capability was particularly valuable for categories that varied depending on local and regional contexts. The findings suggest that ChatGPT, when integrated with RAG, holds significant potential as a comprehensive and adaptive knowledge model in the BIM domain, and thereby alleviates the barriers for BIM adoption, such as the lack of experts, the cost of training, complexity of the BIM models, and additional workloads required during the BIM delivery process.

The South Korean government has mandated the use of Building Information Modeling (BIM) as the main medium for design deliverables in public projects. Such stipulations require detailed BIM models to be submitted in the detailed design phases, which places a burden especially on small- to medium-sized design firms. The requirement means that both the interior and exterior finishes of a building need to be explicitly modeled, which when performed manually is labor intensive and error prone. The goal of this study was to apply parametric modeling techniques to automatically model such details, focusing on the exterior finishes. Through interviews with design experts, four elements were selected: parapets, external wall finishes, downspouts, and inspection ladders. Parametric processes and rules for each finish were developed and subsequently programmed as add-ins in Autodesk Revit. Validation through case studies conducted using three different BIM models resulted in the average scores of 92.28% and 92.44% in terms of accuracy and efficiency, respectively. In particular, downspouts achieved a perfect accuracy score, while external wall finishes achieved a 94.42% reduction in modeling time. Modeling errors, which occurred due to inconsistencies in the test models, also demonstrate the need for specifying uniform modeling conventions of BIM model submissions in the detailed design phases.