Research on a BIM Model Quality Compliance Checking Method Based on a Knowledge Graph

The recent blocking of President Trump’s twitter account has raised awareness of the danger of the impact of fake news and the importance of detecting it. Indeed, if one can doubt information, ignoring what is true or false it can lead to a loss of confidence in the decisions and other dangers. The objective of this paper is to propose an automatic method for fact checking using Knowledge Graphs, such as Wikipedia. Knowledge Graphs (KGs) have applications in many tasks such as Question Answering, Search Engines and Fact Checking, but they suffer from being incomplete. Recent work has focused on answering this problem with an abstract embedding of the KG and a scoring function, yielding results that are not easily interpretable. On the other hand, Path Ranking methods answer this problem with deductions represented by alternative paths in the KG, easily understood by a human. Favoring the Path Ranking approach for its interpretability, we propose an attention-based Path Ranking model that uses label information in the KG, making the model easily transferable between datasets, allowing us to leverage pretraining and demonstrate competitive results on popular datasets.KeywordsFact checkingKnowledge graphsDeep learning

Detecting logical relationships in mechanical, electrical, and plumbing (MEP) systems with BIM using graph matching

Knowledge graph-based data integration system for digital twins of built assets

A building information model often provides the functional and physical data of an electrical facility for the downstream construction, operation and maintenance of the built power grid infrastructure. Therefore, the rapid and convenient query of the required information from the design model is crucial for all the project participants. However, the query of the design data from a BIM model is frequently burdensome and tedious. Moreover, the Grid Information Modeling (GIM) schema, developed by the China State Grid for describing electrical equipment with more engineering details, exaggerates the difficulty of querying the design model. This study applies the Natural Language Interface to Database (NLIDB) approach for querying data from the Neo4j graph database that fuses both IFC data for architectural or structural design and GIM data for electrical equipment. Meanwhile, this study also develops a tool to automatically convert the natural language questions into Cypher queries. In addition, a knowledge graph is also developed for linking the semantic elements extracted from the natural language questions with the IFC semantics stored in the Neo4j database.

Safety code compliance checking before construction is a key step in risk control. However, the conventional safety compliance checking methods are static model-oriented, which can lead to both the low adaptability of the model to the dynamic construction process, and low checking efficiency. This paper develops a dynamic safety checking method based on BIM and topology for enhancing construction safety management, by incorporating actual construction processes. Firstly, based on the four stages of automatic safety checking, a comprehensive dynamic safety checking framework is proposed. Secondly, the object attributes and spatial location in the BIM model are extracted to form a dynamic topological relationship database. Following this, the dynamic safety checking method is designed, and the checking results are intuitively reported to users based on BIM software. An actual construction scenery is taken as an example to verify the feasibility of the method in the final stage. The results showed that the dynamic safety checking method, based on topology and rules, can help to accurately identify safety risks in the pre-construction stage and reduce the safety risks due to poor design considerations or construction process modification.

The management of Aviation Problem Reports (PRs) remains a significant bottleneck in aircraft development, heavily reliant on manual expertise for tasks like duplicate detection and compliance checks. This reliance not only impedes efficiency but also introduces risks of oversight. To address these challenges systematically, this paper proposes an intelligent management framework underpinned by three core technical innovations. Our approach centers on a multi-modal historical PR database. From this foundation, we develop a deep semantic matching model using a dual-tower neural network to identify duplicates with high accuracy. Furthermore, we construct an airworthiness regulation knowledge graph and leverage a Graph Attention Network (GAT) enhanced with a path validation mechanism to intelligently recommend relevant clauses for new PRs. Finally, we introduce a hybrid prediction model that integrates time series decomposition with a collaboratively trained Transformer to forecast PR trends and pinpoint high-risk subsystems. Comprehensive evaluation on real-world project data indicates our method can reduce redundant work by approximately 20%, improve compliance review efficiency by 35%, and provide actionable early warnings, with detailed ablation studies confirming the contribution of each component. The results demonstrate a significant advancement over traditional methods, paving the way for more proactive and intelligent PR management.

Ensuring compliance with complex industry standards and regulations during the design and implementation phases of construction projects is a significant challenge in the building information modeling (BIM) domain. Traditional manual compliance checking methods are inefficient and error-prone, failing to meet modern engineering demands. Natural language processing (NLP) and deep learning methods have improved efficiency and accuracy in rule interpretation and compliance checking. However, these methods still require extensive manual feature engineering, large, annotated datasets, and significant computational resources. Large language models (LLMs) provide robust language understanding with minimal labeled data due to their pre-training and few-shot learning capabilities. However, their application in the AEC field is still limited by the need for fine-tuning for specific tasks, handling complex texts with nested clauses and conditional statements. This study introduces an innovative automated compliance checking framework that integrates LLM, deep learning models, and ontology knowledge models. The use of LLM is motivated by its few-shot learning capability, which significantly reduces the need for large, annotated datasets required by previous methods. Deep learning is employed to preliminarily classify regulatory texts, which further enhances the accuracy of structured information extraction by the LLM compared to directly feeding raw data into the LLM. This novel combination of deep learning and LLM significantly enhances the efficiency and accuracy of compliance checks by automating the processing of regulatory texts and reducing manual intervention. This approach is crucial for architects, engineers, project managers, and regulators, providing a scalable and adaptable solution for automated compliance in the construction industry with broad application prospects.

Planning regulations determine a substantial part of buildings, but their constraints are usually not included in the setup of a BIM model or used explicitly for design guidance, but only tested in compliance checks once a model has been made. This is symptomatic of wider tendencies and ingrained biases that emphasize tacit knowledge and assume that information in a project starts from scratch—an assumption that runs contrary to predesign information ordering practices, as well as to the findings of creativity studies. In terms of process control, it negates important possibilities for feedforward. The paper proposes that BIM and design computerization, in general, should avoid the generate-and-test view of design, the view of design knowledge as tacit, and the adherence to analogue workflows, but develop, instead, approaches and workflows that keep information explicit and utilize it to frame design problems. To demonstrate this, we describe an exercise in which the expectation that the geometric representation of planning regulations returns permissible building envelopes was tested on the basis of a large number of cases produced by students who each collected planning regulations for a particular plot of land in the Netherlands and modelled their constraints in BIM, using a workflow that can be accommodated within the scope of predesign information gathering in any project. The results confirm that, for a large part of Dutch housing, the representation of planning regulations in BIM returns the permissible building envelope, and, so, forms a clear frame for subsequent design actions. They also suggest that including such information in the setup of a model is constructive and feasible, even for novices, and produces a bandwidth view of project information that integrates pre-existing information in a BIM workflow through feedforward. By extension, they also indicate a potential for a closer relation between analysis and synthesis in BIM, characterized by transparency and simultaneity, as well as the thorough understanding of problem constraints required for both efficiency and creativity.

A review of the state of the art in the field of automated code compliance checking revealed that existing applications are limited in the scope of clauses they are able to check. While some building code clauses are straightforward, requiring direct checking of parameter values, others depend on the topological relationships among objects, making automated checking of BIM models more challenging. Moreover, existing applications require the user to extensively preprocess the model in preparation for checking. We propose applying semantic enrichment for pre-processing the BIM models. The goal of a semantic enrichment process in support of automated code compliance checking is to derive the needed clause test values automatically and to represent them explicitly. A successful semantic enrichment process can therefore widen the scope of requirements that can be checked automatically. This work demonstrates such a process for checking code clauses involving topologically complex requirements. Although semantic enrichment proved to be successful for several purposes in previous research, dealing with complex topologies involves different types of semantic enrichment tasks. We explore the subject through a test case of requirements from the Israeli code for security rooms.

Data spaces have recently emerged as an innovative paradigm for cross-organizational data sharing. These decentralized environments require sophisticated data governance protocols to ensure compliance with data standards, roles and policies. While current policy-based solutions address enforcement of data access control and usage rights, they lack mechanisms for automated data validation -essential for ensuring data quality for collaborative analytics. To address this gap, we present a knowledge graph-based framework to automate data validation inline with data policies. This framework relies on the concept of policy checkers, which represent high-level and technology-agnostic data validation plans that can be dynamically translated into technology-specific user defined functions (UDFs) for compliance checking. Importantly, the usage of knowledge graphs to describe the policy checkers enhances the transparency and traceability of data validation processes, while the two-stage process (technology-agnostic policy checkers and technology-specific UDFs) accommodate data validation on multimodal data. We accompany the description of our approach with a proof of concept that demonstrates the feasibility of this solution in real data spaces.

The integration of Design for Manufacture and Assembly (DfMA) into the design process of industrialized construction has the potential to reduce errors and changes occurring after the design has been finalized, ultimately improving overall productivity. Based on DfMA, the designers would need to consider whether their designs meet the architectural and performance requirements, as well as the manufacturing and assembly requirements from assembly and manufacturing technicians. However, some limitations present challenges for DfMA-oriented prefabricated design, such as lack of information interoperability, lack of conflict detection and management, and inefficient data processing and requirement checking. Thus, this research presents a novel BIM and ontology-based framework for DfMA of prefabricated and modular components. Various types of algorithms, plugins, and programming are also integrated to support the operation of the framework. The primary functions of this framework include: (1) collection of various stakeholder requirements in a standardized data format; (2) conflict detection and resolution between the design, manufacturing, and assembly requirements; and (3) automated compliance checking of whether the designed BIM models meet DfMA requirements. This research applies the framework on a prefabricated hotel project as a case study to validate the feasibility of the framework. Based on the results of a user experience survey, the developed framework shows promise for improving the DfMA process and stakeholder communication. Although a few limitations were encountered, such as the low computer operating speed and the limited ontology, the framework has been validated and shows great potential in advancing prefabricated component design applications