Oleksandr Oleksandrovych Liaposhchenko

Scientific and Methodological Approach for the Identification of Mathematical Models of Mechanical Systems by Using Artificial Neural Networks

The article is aimed at developing the scientific and methodological approach of using artificial neural networks (ANN) for solving applied problems in the field of mechanical engineering. This approach is based on the comprehensive implementation of ANN with the modern methods of numerical analysis (e.g., the finite element method) and analytical methods of the research with the use of mathematical modeling of the dynamic state for mechanical systems. Conceptual schemes for the implementation of the abovementioned approach are proposed for solving a number of interdisciplinary problems, such as investigation of the dynamics for rotary machines and hydroaeroelastic interaction of gas-liquid mixtures with deformable structural elements, as well as the dynamic analysis of fixtures. The main advantages of the proposed approach in comparison with the traditional regression analysis are the ability to learn and improve the ANN architecture, and to solve nonlinear problems of the parameters’ identification for mathematical models by using data of the results of physical experiments and numerical simulations. This approach allows refining parameters of the linear and nonlinear mathematical models describing the complicated mechanical and hydro-mechanical interactions under the impossibility of determination of an absolutely precise solution of the equations describing the process, as well as the incompleteness of the initial data.

Modelling of Liquid’s Distribution and Migration in the Fibrous Filter Layer in the Process of Inertial-Filtering Separation

The obtained solution of the mathematical model of liquid’s distribution and migration in the filter layer as flow model in the fibrous environment, which describes the non-pressure filtration motion in the gravity field of the separated liquid film from the gas-drop flow, allows to determine the saturation conditions of the free volume of the filter layer, distribution of speed and pressure under the conditions of free liquid’s movement in the filter layer, as well as to calculate the required cross-sectional area of the thin-layer fibrous filter element and the optimum height of the location of the overflow chutes for draining the separated liquid from the inertial-filtering to the drainage channels in order to avoid the secondary removal of droplets with the turbulent gas flow. As a result, the application rate of the separated liquid which falls from the filter element of the inertial-filtering separation channel to the drainage channels is obtained, as well as the dependence for the overflowed gutter of diverting the separated liquids from the inertial-filtering to the drainage channels is presented.