Using of artificial intelligence methods in the automated system for assessing the vibration effects of vehicles on infrastructure facilities

The development of urban areas and transport infrastructure is accompanied by an increase in the level of vibration effects on surrounding objects. This creates the need to develop new tools for analyzing and predicting such impacts. An important area of research is the use of artificial intelligence technologies, including neural network and fuzzy modeling technologies, to develop automated systems for assessing the impact of transport vibrations with the possibility of integration into intelligent monitoring and diagnostic systems. The purpose of the article is to develop an approach to improving monitoring and diagnostic systems based on the creation of a tool for assessing the vibration effects of vehicles on infrastructure facilities using neural network models. The article analyzes the directions of using neural network models in the automated vibration assessment system. The features of presenting data obtained on the basis of field measurements of vibrations caused by the movement of underground trains have been described. The main types of artificial neural networks that can be used to assess the vibration effects of subway vehicles on urban infrastructure have been described. A sequence of stages for development of an automated vibration assessment system has been proposed. The possibilities of integrating neural network technologies, an expert knowledge base, and a graph model of spatial interactions designed to assess vibration exposure levels, taking into account the construction of a graph of object placement, have been considered. The results of the work can be used in solving problems of modeling, evaluating and predicting vibration effects, problems of developing intelligent monitoring systems and decision support systems, as well as problems of automating the design of vibration isolation measures.