The paper presents a methodology for addressing the scarcity of labeled industrial data for training deep neural networks for semantic segmentation. A platform is proposed for synthetic generation of training point cloud datasets based on a minimal number of real laser-scanning samples of mechanical, electrical, and plumbing networks. The algorithm includes detecting the axes of cylindrical elements using the Random Sample Consensus method, constructing perpendicular joint planes, and applying affine transformations to create assemblies of 2–7 elements. The training set is increased from 8 real scans to more than 800 synthetic examples, which makes it possible to improve the segmentation accuracy of the PointNet++ deep hierarchical point cloud learning architecture from 72% to 89% in terms of the Intersection over Union (IoU) metric. The developed system enables automated creation of BIM models of engineering infrastructure with 90–95% accuracy with respect to design parameters.

Keywords: synthetic data generation, point clouds, semantic segmentation, laser scanning, Random Sample Consensus method, shortage of labeled data, BIM modeling, engineering networks, deep learning

A method of selecting admixtures for the production of dry building mixes is proposed based on the results of an expert assessment of the complex indicator of the workability of application (connectivity, continuity when pulling with a toothed trowel, elasticity, quality of rollers) on a 100-point scale and the strength of adhesion to the concrete base, followed by the calculation of the specific cost of admixtures in the mixture per ton of products, respectively, by one point of workability of application and 1 MPa of adhesion strength, developed as a result of studies of adhesive mixtures made using 4 different cements, 5 water-retaining additives and 12 redispersible polymer powders. The possibility of obtaining adhesive compositions of adhesion class C 2 using redispersible polymer powders of domestic production is shown.

Keywords: dry building mix, adhesion strength to the base, unit cost, processability of application

The authors examine the peculiarities of fiber-optic cable electric parameters changes under the influence of a strong homogeneous alternating electromagnetic field. Variants of the process which can be used to describe the influence of the electromagnetic field on the fiber-optic cable are proposed.

Keywords: Fiber optic cable, electrothermal degradation, kevlar, electrical conduction