Abstract
The effectiveness of neural networks in predicting the temperature of key heat sources and various machine tool components is investigated. The accuracy of prediction is assessed experimentally. Two network architectures are compared. The results of a machine experiment confirm that thermal models are effective in terms of accurate forecasts.
Similar content being viewed by others
REFERENCES
Wiessner, M., Blaser, P., Bohl, S., et al., Thermal test piece for 5-axis machine tools, Precis. Eng., 2018, vol. 52, pp. 407–417.
Jian, B.L., Wang, C.C., Hsieh, C.T., et al., Predicting spindle displacement caused by heat using the general regression neural network, Int. J. Adv. Manuf. Technol., 2019, vol. 104, pp. 4665–4674.
Fu, G., Gong, H., Gao, H., et al., Integrated thermal error modeling of machine tool spindle using a chicken swarm optimization algorithm-based radial basic function neural network, Int. J. Adv. Manuf. Technol., 2019, vol. 105, pp. 2039–2055.
Sleptsov, G.N., Compilation of a training sample of an artificial neural network to predict the technical changes of a complex technical system, Kachestvo. Innovatsii. Obraz., 2015, no. 8, pp. 44–47.
Pozevalkin, V.V. and Polyakov, A.N., A model for predicting the temperature of a machine tool structure by a neural network using the sliding window method, IOP Conf. Ser.: Mater. Sci. Eng., 2021, vol. 1061, art. ID 012035.
Funding
The work was supported by the Russian Foundation for Basic Research, project 20-38-90045.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Translated by B. Gilbert
About this article
Cite this article
Pozevalkin, V.V., Polyakov, A.N. Effectiveness of Neural Networks in Predicting Machine-Tool Temperatures. Russ. Engin. Res. 41, 1260–1262 (2021). https://doi.org/10.3103/S1068798X21120340
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1068798X21120340