Vitalii Oleksandrovych Ivanov

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.

Fundamental Approach for Analysis of Dynamic Characteristics of Fixtures

Present work is aimed at research of locating and clamping process of prismatic parts in fixtures during the machining on drilling-milling-boring machines. The fundamental approach for developing mathematical modeling of the system “fixture – workpiece” has been proposed. It allows to determine critical frequencies of functional elements oscillations and amplitude-frequency response characteristics, as well as dynamic component of fixture deformations at operating frequency of the machining process. The developed mathematical model is evaluated by numerical calculations of spectrum of critical frequencies considering the stiffness of cutting tool. The further researches are directed on the development of the methodology of calculation of the system “fixture – workpiece” by computer means of numerous realization and development of practical recommendations regarding its use during fixture design.

Flexible Fixtures for CNC Machining Centers in Multiproduct Manufacturing

In modern manufacturing engineering, a major challenge is the contradiction between the need to reduce the time required to design and manufacture the products and the increasing complexity of product design. Todays market requires more varieties of products, and consequently the equipment and processes should be more flexible. Fixtures play an essential role in production of high-quality and competitive products in multiproduct manufacturing. The paper describes the ways of increasing of machining efficiency of parts. The principally new constructions of functional modules of modular adjustable fixtures for locating and clamping of workpieces are introduced. Use of the proposed fixtures with the possibility of automatized adjustment ensures the spreading of technological capabilities of CNC metal-cutting equipment, decreasing of preparatory time and setup time, and therefore, assists improving of the efficiency of production planning.

Technological Assurance of Complex Parts Manufacturing

The ways of intensification of machining complex parts of vehicles on the modern metal-cutting equipment were described. The classification of parts such as levers was developed on the basis of design and technological features. Based on the developed classification the structural code that allows to encode any lever design was proposed. The structural code can be used in computer-aided fixture design and in information retrieval systems for selecting optimal fixture for levers. The reasonability of intensification of parts machining such as levers was substantiated, the typical manufacturing process was analyzed, and opportunities for optimization subject to current trends in machining and technological capabilities of modern equipment were identified. The adjustable locating-and-clamping module characterized by high level of flexibility was proposed for CNC multiaxis machining operation. Comparative analysis of manufacturing processes by labor content, quantity of fixtures and machine tools, number of setups, and production area was performed.

Process-Oriented Approach to Fixture Design

Machining of parts on the metal-cutting machine tools could not be ensured without the use of fixtures. They are an integral part of the closed-loop technological system “machine tool – fixture – cutting tool – workpiece” and make the significant impact on the accuracy and quality of machining of machine parts surfaces. The work presents the structural stages of computer-aided fixture design and determines the data flows between them to ensure the comprehensive approach. The process-oriented model of fixture design process has been developed, which provides the manufacturing analysis of the workpiece, synthesis and optimization of fixture configurations, verification of the mechanical system “fixture – workpiece” for set production conditions, and functional links and data flows between stages have been determined. The above-mentioned allows realizing a comprehensive approach to the computer-aided fixture design in multiproduct manufacturing.

Application of Artificial Neural Network for Identification of Bearing Stiffness Characteristics in Rotor Dynamics Analysis

In this article the implementation of the mathematical model for rotor oscillations on non-linear bearing supports for the multistage centrifugal compressor is considered by using the computer program “Critical frequencies of the rotor”. It realized the finite element mathematical model, which allows taking into account the non-linear dependence of bearing stiffness on the rotor speed, as well as gyroscopic moments of inertia of impellers and shell-type parts. The artificial neural network “Virtual Gene Developer” software is proposed for evaluating the operating parameters of the approximating curve “bearing stiffness – rotor speed” by the dataset of numerical simulation results in the abovementioned software. Actual parameters of non-linear bearing stiffness are obtained by the results of the experimental research of rotor critical frequencies for the multistage centrifugal compressor 295GC2-190/44-100M on the experimental accelerating-balancing stand “Schenck”. The main advantages of the proposed approach and methodology for application of Artificial Neural Networks are stated.