Comprehensive Research of Physical and Mechanical Characteristics of Composite Materials Using Neural Networks

The paper presents the results of studies of the physical and mechanical properties of materials: compressive failure stress, tensile failure stress, impact strength, and residual stresses in the material. To determine these parameters, we used modern methods of analyzing experimental studies, neural networks, to ensure a high measurement accuracy. Particular attention is paid to the research of the impact strength of residual stresses in the material, which allows for predicting the behavior of products in service. Impact toughness is one of the main indicators for evaluating materials that are operated under complex stress–strain conditions. It is proved that the values of both the compressive and tensile destructive stresses, impact strength, and residual stresses significantly affect the ability of the material to resist fracture under the action of both static and dynamic alternating loads. Critical values of residual stresses have been determined, the excess of which reduces the resistance of materials to fracture. The research has established the regularities of residual stresses and their magnitude in materials with different structural organizations. The research results are important from a scientific and technical point of view for the creation of new composite materials with high resistance to fracture, which will increase the operational reliability of the product as a whole.