Artificial intelligence

Abstract: The article deals with the application of neural networks to the creation of a system for identification and management of mobile machines - robots. A new approach with the use of spectral analysis of the absorption functions by the mechanism of the machine is proposed - the work of the excited acoustic wave with the further processing of information on deep neural networks of cascade architecture. The mathematical model of the process includes the equation of modified activation functions that have a folding bond structure, and reflects the interconnection of the acoustic spectrum and the coordinates of the actual point of the object. The acoustic spectrum of the response, which is the sum of the excited, absorbed and reflected acoustic waves, can be processed through deep neural networks. The neural network reference model was constructed, which allows to diagnose the current characteristics of the state of objects such as the configuration of the mechanism, its geometric parameters, the dynamics of nodes moving.

Keywords: acoustic diagnostics, machine - robot, neural networks, reference model

References:

1. Isaksen A., Kalsaas B.T. Suppliers and strategies for upgrading in global production networks: the case of a supplier to the global automotive industry in a high-cost location. // European Planning Studies. – 2009. Vol. 17(4). – P. 569-585.
2. Dreval' A., Vasilev V., Vinogradov D., Malkov O. Measuring Diagnostic Stand for Experimental Researches in Technology Machining. // Nauka i Obrazovanie. –2014. – No 12. – P. 22-58.
3. High precision parallel robots for micro-factory applications / Clavel R. and others // Colloquium. –2005. – P. 85–296.
4. Bushuev V.V. Mehanizmyi parallelnoy strukturyi v mashinostroenii / V.V. Bushuev, I.G. Holshev // STIN. – 2001. – #1. S. 3 - 8.
5. Gavrilov V. A., Koltsov A. G., Shamutdinov A. H. Klassifikatsiya mehanizmov dlya tehnologicheskih mashin s parallelnoy kinematikoy // STIN. – 2005. – # 9. – S. 28
6. Kuznietsov Yu.M., Kryzhanivskyi V.A., Skliarov R.A. Suchasnyi stan, prohnozuvannia i perspektyvy rozvytku verstativ z paralelnoiu kinematykoiu //Vysnik ZhDTU. – 2005. – No1. – S. 332-333.
7. Kruglov I.A. Neural networks modeling of multivariable vector functions in ill-posed approximation problems / I.A. Kruglov, O.A. Mishulina // Journal of Computer and System Sciences International. – 2013. – Vol. 52, No. 4. – P. 503-518.
8. Yusimit Z., Yoandrys M., Arlys L., Roberto B. Influence of the cutting parameters on flank wear of coated inserts during turning of AISI 316L // Enfoqute. – 2015. – No 6. – P.13-24.
9. Kyrychenko A.M. Provedennia do zony obrobky zhorstkosti ta podatlyvosti obladnannia z mekhanizmamy paralelnoi struktury / A.M. Kyrychenko // Visnyk Natsionalnoho tekhnichnoho universytetu Ukraini „Kyivskyi politekhnichnyi instytut”. Seriia „Mashynobuduvannia”. – 2010. – No59. – S. 205-210.
10. Glushko E.A., Radchenko S.G. Ustoychivoe modelirovanie tehnologicheskih protsessov i sistem // VIsnik NatsIonalnogo tehnIchnogo unIversitetu UkraYini KPI. SerIya „Mashinobuduvannya”. – 2010. – #58. – S. 12-17.
11. Kovalevskyy S.V. Acoustic Monitoring with Neural Network Diagnostics / S.V. Kovalevskyy, O.S. Kovalevska // American Journal of Neural Networks and Applications. – 2015. – Vol. 1, No. 2. – P. 39-42. – doi: 10.11648/j.ajnna.20150102.12
12. Size control products using spectrum of natural vibrations and neural networks machining / S.V. Kovalevskyy, P Dašić, I.N. Starodubcev, O.S. Kovalevska // Вісник Донбаської державної машинобудівної академії. – 2012. – No 2 (27). – С. 38–43.