621.9, 621.914.1

parallel mechanisms, PSKV, PSKM, samples, neural network, milling, roughness, precision.

In the article examines the structure of technological systems with a parallel kinematic structure. The path location optimization problem consists of three sets, namely a set of design variables, a set of objective functions, and a set of design constraints. Accordingly, the optimization task is aimed at identifying design variables, such as hexapod, tripod, triglide, and others, that characterize the surface fabrication path in order to minimize or maximize objective functions subject to design constraints. The Hexapod mathematical model includes inverse and direct kinematic problems. The solution of the inverse kinematic problem for hexapods is tied to calculating the length of the racks and the location of the hinges at a given position of the movable platform. The spectral characteristics and qualitative and quantitative indicators of the processed samples were measured. Calculations were also performed on the ratio of initial parameters, cutting modes, and obtaining quality characteristics of Ra and T for each of the 25 samples. Kinematic pairs by class are reviewed and their functional and structural characteristics are determined , which makes it possible to estimate the degree of freedom for mechanisms with parallel structure kinematics. For Structural Simplification and reduction of time and complexity when choosing a PSKM scheme, they are shown in the graphical form of kinematic structures. To assess the quality of the system, as well as its ability to perform the functions assigned to it in the basic state, a table of output data was compiled, as well as a sample from which a data matrix was compiled to cover the entire possible range of output parameters, which significantly affects the result. The graphs show the spectral characteristics of technological systems with PSKV for the sections of the treated surfaces of samples No. 1, No. 2 and No. 3.

1. Shchelkunov E. B., Mechanisms of parallel structure in metal-cutting machine tools. Shchelkunov E. B., Vynohradov S. V., Shchеlkunova M. E., Samar E. V. “Scientific notes” of the Komsomolsk-on-Amur State Technical University. Science of nature and technology. 2016. P. 67–72.
2. Serje-Martinez Parallel kinematics machine tools: Research, development and future trends. Serje-Martinez, David Alfonso and Pacheco-Bolivar. Jovanny Alejandro. Dyna rev.fac.nac.minas [online]. 2017. Vol. 84. No. 201. P. 17–26. ISSN 0012-7353.
3. Zhiyuan He An Error Identification and Compensation Method of a 6-DoF Parallel Kinematic Machine. Zhiyuan He, Binbin Lian, Qi Li, Yue Zhang, Yimin Song, Yong Yang, And Tao Sun, 9040. Vol. 8. 2020. P. 119038–119047, ISSN: 2169-3536.
4. Toquica J. S. and Oliveira P. and Motta J. M. S. T. and Borges D. L. A proposal to solve the inverse kinematics problem of a parallel robot configuration with neural networks. Proceedings of International Conference on Computers and Industrial Engineering, CIE, 2018. Р. 15 ISSN: 21648689.
5. Sun Tao Stiffness and mass optimization of parallel kinematic machine. Sun Tao, Binbin Lian. Mechanism and Machine Theory. Volume 120. February 2018. P. 73–88 ISSN 0094-114Х.
6. Dimitri Gouot, Frédéric Chapelle, Gérard Granet, Jean-Jacques Lemaire, Yuri Lapusta Methodology for the selection of a smart material as actuator in neurosurgical robotics. Scientific Journal of TNTU. 2020. Vol. 100. No. 4. P. 5–10.
7. Roman Butsiy Serhii Lupenko Comparative analysis of neurointerface technologies for the problem of their reasonable choice in human-machine information systems. Scientific Journal of TNTU. 2020. Vol. 100. No. 4. P. 135–148.
8. Juan S.Toquica An analytical and a Deep Learning model for solving the inverse kinematic problem of an industrial parallel robot. Juan S.Toquica, Patrícia S.Oliveira, Witenberg S.R.Souza, José Maurício S.T.Motta, Díbio L.Borges. Computers & Industrial Engineering. Vol. 151. Р. 106682–106688. ISSN: 03608352
9. Kahanov Yu. T., Karpenko A. P. Modelyrovanye y optymyzatsyia nekotorыkh parallelnыkh mekhanyzmov. Informatsyonnye tekhnolohyy. Prylozhenye. 2010. № 5. Р. 1–32.
10. Yemets V. V., Kovalevskyi S. V. Proektuvannia ta doslidzhennia tekhnolohichnykh mozhlyvostei pryvodiv intelektualnykh mobilnykh mashyn. “Neiromerezhevi tekhnolohii ta yikh zastosuvannia NMTiZ-2017”. Kramatorsk: DDMA, 2017. Р. 54–59.

1. Shchelkunov E. B., Mechanisms of parallel structure in metal-cutting machine tools. Shchelkunov E. B., Vynohradov S. V., Shchеlkunova M. E., Samar E. V. “Scientific notes” of the Komsomolsk-on-Amur State Technical University. Science of nature and technology. 2016. P. 67–72.
2. Serje-Martinez Parallel kinematics machine tools: Research, development and future trends. Serje-Martinez, David Alfonso and Pacheco-Bolivar. Jovanny Alejandro. Dyna rev.fac.nac.minas [online]. 2017. Vol. 84. No. 201. P. 17–26. ISSN 0012-7353.
3. Zhiyuan He An Error Identification and Compensation Method of a 6-DoF Parallel Kinematic Machine. Zhiyuan He, Binbin Lian, Qi Li, Yue Zhang, Yimin Song, Yong Yang, And Tao Sun, 9040. Vol. 8. 2020. P. 119038–119047, ISSN: 2169-3536.
4. Toquica J. S. and Oliveira P. and Motta J. M. S. T. and Borges D. L. A proposal to solve the inverse kinematics problem of a parallel robot configuration with neural networks. Proceedings of International Conference on Computers and Industrial Engineering, CIE, 2018. Р. 15 ISSN: 21648689.
5. Sun Tao Stiffness and mass optimization of parallel kinematic machine. Sun Tao, Binbin Lian. Mechanism and Machine Theory. Volume 120. February 2018. P. 73–88 ISSN 0094-114Х.
6. Dimitri Gouot, Frédéric Chapelle, Gérard Granet, Jean-Jacques Lemaire, Yuri Lapusta Methodology for the selection of a smart material as actuator in neurosurgical robotics. Scientific Journal of TNTU. 2020. Vol. 100. No. 4. P. 5–10.
7. Roman Butsiy Serhii Lupenko Comparative analysis of neurointerface technologies for the problem of their reasonable choice in human-machine information systems. Scientific Journal of TNTU. 2020. Vol. 100. No. 4. P. 135–148.
8. Juan S.Toquica An analytical and a Deep Learning model for solving the inverse kinematic problem of an industrial parallel robot. Juan S.Toquica, Patrícia S.Oliveira, Witenberg S.R.Souza, José Maurício S.T.Motta, Díbio L.Borges. Computers & Industrial Engineering. Vol. 151. Р. 106682–106688. ISSN: 03608352
9. Kahanov Yu. T., Karpenko A. P. Modelyrovanye y optymyzatsyia nekotorыkh parallelnыkh mekhanyzmov. Informatsyonnye tekhnolohyy. Prylozhenye. 2010. № 5. Р. 1–32.
10. Yemets V. V., Kovalevskyi S. V. Proektuvannia ta doslidzhennia tekhnolohichnykh mozhlyvostei pryvodiv intelektualnykh mobilnykh mashyn. “Neiromerezhevi tekhnolohii ta yikh zastosuvannia NMTiZ-2017”. Kramatorsk: DDMA, 2017. Р. 54–59.