Due to higher efficiency and lower cost, prefabricated construction is gradually gaining acceptance within the market. Laser scanning has already been adopted in civil engineering to reconstruct 3D model of structure and monitoring the deformation and so on. This paper seeks to explore a more automated and accurate quality control process focusing on the surface defects in prefabricated elements. Laser scanning is adopted for data collection and the 3D reconstruction of the prefabricated components. Besides, a new point cloud pre-processing, involving the KNN algorithm, reduction of data dimension and data gridding, is developed to improve the efficiency and accuracy of subsequent algorithms. The Delaunay triangle is used to extract the contour of the point cloud, then the contour is fitted to further determine the geometric data. Meanwhile, a comprehensive quality control system of prefabricated components based on relevant specifications is proposed, and the quality of prefabricated components is monitored intuitively by the values of indicators. In order to integrate into the BIM platform and better store the obtained quality information, the production quality information is designed to be extended to the IFC standard. The proposed approach will be applied to analyze the causes of quality problems in the production process and strengthen the quality control. This study designs a more efficient and accurate quality evaluation process, including data collection, data processing, indicator calculation and quality evaluation. Moreover, the results forward can feedback to the cause of the quality issues, and further improve the production quality of prefabricated elements.

Prefabricated construction promotes providing better productivity and project results. Building models, including their elements’ fabrication details, are complex structures that need accurate information delivery among the project participants and their partial designs. This paper extends the IFC data model to support prefabricated construction. Also, it discusses the advantages of systematically managing exchange requirements in a database to facilitate generating IDM (Information Delivery Manual). The paper first introduces a BIM-based collaborative work mode by sharing and extracting the model views. The core of the sharing is the establishment of view exchange standard about the linked model and the definition of exchange requirements based on the design process, leading to the formulation of the IDM standard again from the perspective of the actual design. Process maps covering architecture, structure, plumbing, mechanical engineering, and electrical engineering are made to show how to realize BIM-based collaborative work. Then the exchange requirements referred to the object and attribute of the BIM model which should be delivered in a special phase are defined in particular tables. To facilitate the automation of managing and exchanging requirements, a database management system is designed with its corresponding user-interface, which enhances the collaboration and delivery throughout the project life cycle. The proposed approach supports better information reuse and delivery among the project participants.

This paper proposes a novel method for construction component classification by designing a feature-based deep learning network to tackle the automation problem in construction digitization. Although scholars have proposed a variety of ways to achieve the use of deep learning to classify point clouds, there are few practical engineering applications in the construction industry. However, in the process of building digitization, the level of manual participation has significantly reduced the efficiency of digitization and increased the application restrictions. To address this problem, we propose a robust classification method using deep learning networks, which is combined with traditional shape features for the point cloud of construction components. The proposed method starts with local and global feature extraction, where global features processed by the neural network and the traditional shape features are processed separately. Then, we generate a feature map and perform deep convolution to achieve feature fusion. Finally, experiments are designed to prove the efficiency of the proposed method based on the construction dataset we establish. This paper fills in the lack of deep learning applications of point clouds in construction component classification. Additionally, this paper provides a feasible solution to improve the construction digitization efficiency and provides an available dataset for future work.

Dynamic relation repair aims to efficiently validate and repair the instances for knowledge graph enhancement (KGE), where KGE captures missing relations from unstructured data and leads to noisy facts to the knowledge graph. With the prosperity of unstructured data, an online approach is asked to clean the new RDF tuples before adding them to the knowledge base. To clean the noisy RDF tuples, graph constraint processing is a common but intractable approach. Plus, when adding new tuples to the knowledge graph, new graph patterns would be created, whereas the explicit discovery of graph constraints is also intractable. Therefore, although the dynamic relation repair has an unfortunate hardness, it is a necessary approach for enhancing knowledge graphs effectively under the fast-growing unstructured data. Motivated by this, we establish a dynamic repairing and enhancing structure to analyze its hardness on basic operations. To ensure dynamic repair and validation, we introduce implicit graph constraints, approximate graph matching, and linkage prediction based on localized graph patterns. To validate and repair the RDF tuples efficiently, we further study the cold start problems for graph constraint processing. Experimental results on real datasets demonstrate that our proposed approach can capture and repair instances with wrong relation labels dynamically and effectively.