«Automation and Informatization of the fuel and energy complex»

Approbation of a universal computational express-method for developing a neural network model of the copper processing on a vertical milling machine

UDC: 004.855.5:004.942
DOI: -

Authors:

¹ Kazan National Research Technological University, Kazan, Russia
² Kazan Innovation University, Kazan, Russia

Keywords: modeling, copper, milling machine, neural network models, computational express-method, fuel and energy complex (FEC), energy efficiency

Annotation:

The authors of the article focus on testing a universal computational express-method for developing a neural network model of copper processing on a vertical milling machine. The emphasis is paid to modern information technologies application, especially artificial neural networks (ANN), to modeling complex systems and optimizing materials mechanical processing in order to improve the production processes energy efficiency in the fuel and energy complex (FEC). Modern technologies optimize energy consumption and costs of processing materials like copper used in FEC equipment. A neural network model for predicting the output parameter (thrust force) with a prediction error not exceeding 7,7 % is developed. The methodology includes creating a knowledge base, developing and training a uniform neural network in the NeuroShell development environment as well as testing the model. The high significance of input characteristics such as spindle speed, feed rate, surface roughness, machining time and ovality for accurate output prediction were confirmed in the course of the study. The above-said information confirms the potential of using ANN for optimizing energy-intensive processes, being the most essential problem of FEC. The optimization enhances processing accuracy, reduces production costs and increases FEC efficiency in Russia. In particular, the results also show prospects for applying neural network modeling to solve the problems that arise in the course of copper processing on a vertical milling machine, valuable for materials science and production, thus being practically important for material engineering and production of various materials.

Bibliography:

1. Mukhutdinov A.R., Marchenko G.N., Vakhidova Z.R. Neyrosetevoe modelirovanie i optimizatsiya slozhnykh protsessov i naukoemkogo teploenergeticheskogo oborudovaniya: monogr. – Kazan': Kazan. gos. energet. un-t, 2011. – 296 s.
2. Mukhutdinov A.R., Efimov M.G., Vakhidova Z.R. Neyrosetevoe modelirovanie protsessa nagreva bituminoznogo plasta i issledovanie vliyaniya razlichnykh faktorov // Avtomatizatsiya i informatizatsiya TEK. – 2022. – № 9(590). – S. 13–17. – DOI: 10.33285/2782-604X-2022-9(590)-13-17
3. Mukhutdinov A.R., Efimov M.G. Universal'nye vychislitel'nye ekspress-metody dlya sozdaniya iskusstvennoy neyronnoy seti slozhnogo ob"ekta i innovatsionnogo programmnogo modulya na ee osnove: monogr. – Kazan': KNITU, 2022. – 164 s.
4. Ovsyannikov I.V., Ovsyannikov A.V., Nikonenok V.G. Sovremennye informatsionnye tekhnologii v matematicheskom modelirovanii // Auditorium. – 2023. – № 2(38). – S. 8–13.
5. Sarker I.H. AI-Based Modeling: Techniques, Applications and Research Issues Towards Automation, Intelligent and Smart Systems // SN Computer Science. – 2022. – Vol. 3. – Article No. 158. – DOI: 10.1007/s42979-022-01043-x
6. Zhou Cong. Integration of modern technologies in higher education on the example of artificial intelligence use // Education and Information Technologies. – 2022. – Vol. 28. – P. 3893–3910. – DOI: 10.1007/s10639-022-11309-9
7. ANN Approach for Modelling Parameters in Drilling Operation / T.D.B. Kannan, G.R. Kannan, M. Umar, S.A. Kumar // Indian J. of Science and Technology. – 2015. – Vol. 8, Issue 22. – DOI: 10.17485/ijst/2015/v8i22/79097
8. Application of Genetic Algorithm Technique for Machining Parameters Optimization in Drilling of Stainless Steel / T.D.B. Kannan, B.S. Kumar, G.R. Kannan [et al.] // Mechanics and Mechanical Engineering. – 2019. – Vol. 23, Issue 1. – P. 271–276. – DOI: 10.2478/mme-2019-0036
9. Multi-Objective Optimization of Metal Removal Rate, Dimensional and Profile Accuracy during Drilling of ASTM A516 (Grade70) Steel / S.V. Kumar, R. Rekha, M.G. Rajan [et al.] // Key Engineering Materials. – 2022. – Vol. 933. – P. 97–106. – DOI: 10.4028/p-19hm0h
10. Application of Artificial Neural Network Modeling for Machining Parameters Optimization in Drilling Operation / T.D.B. Kannan, G.R. Kannan, B.S. Kumar, N. Baskar // Procedia Materials Science. – 2014. – Vol. 5. – P. 2242–2249. – DOI: 10.1016/j.mspro.2014.07.433
11. Arafat M., Sjafrizal T., Anugraha R.A. An artificial neural network approach to predict energy consumption and surface roughness of a natural material // SN Applied Sciences. – 2020. – Vol. 2, Issue 7. – Article No. 1174. – DOI: 10.1007/s42452-020-2987-6
12. Lue Khu Dyl, Volkov V.Yu. Metod opredeleniya stepeni vliyaniya vkhodnykh vozdeystviy na vykhodnye parametry mnogosvyaznogo ob"ekta upravleniya // Izv. TulGU. Tekhnicheskie nauki. – 2013. – № 10. – S. 277–282.