摘要：The main task, the solution of which the work is focused on, is the automation of the fuzzy inference system, which is one of the subsystems of the system for assessing the technical condition of construction objects. The proposed assessment system is assigned to services that specialize in conducting construction and technical examinations. The process of conducting examinations in this area is accompanied by uncertainties of a different nature, and the production activities of specialists are often based on heuristics. That is why, the object of research are models and tools that can function in fuzzy conditions. To automate expert activities in the field of assessing the influence of external factors on the technical condition of compacted urban areas, a specialized assessment system has been designed based on knowledge and an artificial neuro-fuzzy network of the Takagi-Sugeno-Kang category. The use of neuro-fuzzy models for fuzzy inference makes it possible to automate the process of obtaining logical conclusions from input according to fuzzy rules specified by experts. At the same time, settings for membership functions can be carried out using artificial neural networks. The Takagi-Sugeno-Kang fuzzy neural network is designed to solve this problem. The feasibility of using this model to solve the problem of assessing the technical condition of construction objects with damage is justified by its ability to solve the problem of fuzzy classification. The second main criterion for choosing this model is the ability to set the rules by the input function, since under the conditions of compacted urban development, the factors affecting the external environment on the technical condition of objects are complex non-linear. The principle of adaptation of the fuzzy inference system is shown by the example of fuzzification of environmental influences caused by vibrations of a different nature. The studies carried out in the work, unlike the previous ones, expand the knowledge base of the system by presenting information about the real state of the environment in which the construction objects operate. It is expected that the use of the Takagi-Sugeno-Kang artificial neural network will significantly reduce the influence of the human factor on the performance of construction and technical examinations performed under conditions of compositional uncertainty. The practical significance of the work is to reduce the timing and increase the reliability of the assessment of the technical condition of construction objects with damage of a different nature.
