An accurate assessment of the type and extent of sewer damage is an important prerequisite for maintenance and repair. At present, distinguishing drainage pipe defect types in the engineering field mainly relies on the human eye, which is time consuming, labor intensive, and subjective. Some studies have used deep learning to classify the types of pipe defects, but this method can only identify one main pipe defect. However, sometimes a combination of defects, such as corrosion and precipitation on a section of pipe wall, can be classified as one category by picture classification, which is significantly different from the reality. Furthermore, the deep learning method for defect classification is unable to pinpoint the precise location and severity of a defect or estimate the number of flaws and the cost of maintenance and repair. Therefore, an image segmentation method based on deep convolutional neural networks is proposed to achieve pixel-level image segmentation of defect regions while classifying pipe defects. Compared with the deep learning network for defect classification, it can segment a variety of defects and reduce the number of samples, which is convenient for defect measurement. First, the image defect locations of seven typical defects were manually labeled to create the dataset. Then, a model based on the SegNet network was used to label defect areas automatically in an image. The pipeline image dataset was used to test the previously trained model using the CamVid dataset. Finally, the model was applied to drainage pipe network images that were provided by periscope and closed-circuit television inspection cameras, and the pixel accuracy of image segmentation reached 80%. From the results, it can be concluded that image segmentation and annotation technology based on deep learning is applicable to sewer defect detection. The identification results of pipeline defects were accurate. The SegNet model is a reliable method for image analysis of pipeline defects, which can accurately evaluate the type and degree of sewer damage.

Collaborative work in the construction industry has always been one of the problems solved by BIM (Building Information Modeling) technology. The integration of IFC (Industry Foundation Classes) data as a general building information standard is one of the indispensable functions in collaborative work. The most practical approach of merging IFC data depends on GUID (Global Universal Identifier) comparison at present. However, GUID is not stable in current applications and often changes when exported. The intact representation of relationships between IFC entities is an essential prerequisite for proper association of IFC entities in IFC mergence. This paper proposes a graph‐based method for IFC data merging. The IFC data are represented as a graphical data structure, which completely preserves the relationship between IFC entities. IFC mergence is accomplished by associating other data with an isomorphic graph that is obtained by mining the IFC graph. The feasibility of the method is proven by a program, and the method can ignore the impacts of GUID and other factors.

Code compliance checking is a very important step in engineering construction, but most of code compliance checking relies on manual review at present. With the development of semantic web technology, ontology can be used to represent code information and check the code automatically. However, code ontology is established manually by researchers who have sufficient domain knowledge, in which it is easy to cause poor hierarchical structure of classes. It is also possible for code ontology not being suitable for compliance check. This paper proposes a semiautomatic construction method of railway code ontology based on ifcOWL. The railway code ontology is developed by converting ifcOWL which extends semantic information of railway code. This method can ensure the completeness of the hierarchical relationship of the classes in code ontology with good scalability, which makes use of taxonomy in ifcOWL. The establishment of ontology is divided into two processes with low coupling, namely, extension and conversion, which reduces the domain knowledge requirements of the researchers. Finally, a practical specification is selected to generate a code ontology that achieves some clauses checking.

The research and application of new wall materials have been attracting increasing attention owing to the continuous promotion of sustainable development in the building industry. An alkali-activated slag ceramsite compound insulation block (AASCCIB) is used as the research object. Based on the finite element method, the effects of different numbers of hole rows and hole ratios on the thermal and mechanical performances of AASCCIBs are analyzed using ANSYS CFX. On this basis, the AASCCIB with the optimal comprehensive performance is determined by a multi-objective optimization analysis. Finally, the improvement effect of the AASCCIB wall on the indoor thermal environment relative to an ordinary block (OB) wall is quantitatively analyzed using ANSYS CFX. The results show that the von Mises equivalent stress and heat transfer coefficient of the AASCCIB decrease with the increase in the hole ratio when the hole shape and number of hole rows are constant. ${\mathrm{AASCCIB} \mathrm{B}}_1$ has the optimal comprehensive performance among six AASCCIBs, with the heat transfer coefficient and average von Mises equivalent stress of 0.446 W/(m²∙K) and 9.52 MPa, respectively. Compared with the indoor lowest and average temperatures of the building with the OB wall, those of the building with the AASCCIB wall increased by at least 1.39 and 0.82 °C on the winter solstice, respectively. The indoor temperature difference decreased by at least 0.83 °C. In addition, the indoor highest temperature, average temperature, and temperature difference decreased by at least 1.75, 0.79, and 1.89 °C on the summer solstice, respectively.

To meet the requirements of specifications, intelligent optimization of steel bar blanking can improve resource utilization and promote the intelligent development of sustainable construction. As one of the most important building materials in construction engineering, reinforcing bars (rebar) account for more than 30% of the cost in civil engineering. A significant amount of cutting waste is generated during the construction phase. Excessive cutting waste increases construction costs and generates a considerable amount of COCO₂ emission. This study aimed to develop an optimization algorithm for steel bar blanking that can be used in the intelligent optimization of steel bar engineering to realize sustainable construction. In the proposed algorithm, the integer linear programming algorithm was applied to solve the problem. It was combined with the statistical method, a greedy strategy was introduced, and a method for determining the dynamic critical threshold was developed to ensure the accuracy of large-scale data calculation. The proposed algorithm was verified through a case study; the results confirmed that the rebar loss rate of the proposed method was reduced by 9.124% compared with that of traditional distributed processing of steel bars, reducing CO₂ emissions and saving construction costs. As the scale of a project increases, the calculation quality of the optimization algorithm for steel bar blanking proposed also increases, while maintaining high calculation efficiency. When the results of this study are applied in practice, they can be used as a sustainable foundation for building informatization and intelligent development.