[1] Lei Chunli, Zhao Mingqi, Liu Kai, Song Ruizhe, et al. Temperature prediction model for a high-speedmotorized spindle based on back-propagation neural networkoptimized by adaptive particle swarm optimization [J]. Journal of Southeast University (English Edition), 2022, 38 (3): 235-241. [doi:10.3969/j.issn.1003-7985.2022.03.004]

Copy

Temperature prediction model for a high-speedmotorized spindle based on back-propagation neural networkoptimized by adaptive particle swarm optimization()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

38

Issue:

2022 3

Page:

235-241

Research Field:

Mechanical Engineering

Publishing date:

2022-09-20

Info

Title:

Temperature prediction model for a high-speedmotorized spindle based on back-propagation neural networkoptimized by adaptive particle swarm optimization

Author(s):

Lei Chunli;  Zhao Mingqi;  Liu Kai;  Song Ruizhe;  Zhang Huqiang

School of Mechanical and Electrical Engineering, Lanzhou University of Technology, Lanzhou 730050, China

Keywords:

temperature prediction;  high-speed motorized spindle;  particle swarm optimization algorithm;  back-propagation neural network;  robustness

PACS:

TH-39

DOI:

10.3969/j.issn.1003-7985.2022.03.004

Abstract:

To predict the temperature of a motorized spindle more accurately, a novel temperature prediction model based on the back-propagation neural network optimized by adaptive particle swarm optimization(APSO-BPNN)is proposed. First, on the basis of the PSO-BPNN algorithm, the adaptive inertia weight is introduced to make the weight change with the fitness of the particle, the adaptive learning factor is used to obtain different search abilities in the early and later stages of the algorithm, the mutation operator is incorporated to increase the diversity of the population and avoid premature convergence, and the APSO-BPNN model is constructed. Then, the temperature of different measurement points of the motorized spindle is forecasted by the BPNN, PSO-BPNN, and APSO-BPNN models. The experimental results demonstrate that the APSO-BPNN model has a significant advantage over the other two methods regarding prediction precision and robustness. The presented algorithm can provide a theoretical basis for intelligently controlling temperature and developing an early warning system for high-speed motorized spindles and machine tools.

References:

[1] Mayr J, Jedrzejewski J, Uhlmann E, et al. Thermal issues in machine tools[J]. CIRP Annals, 2012, 61(2): 771-791. DOI: 10.1016/ j.cirp. 2012. 05.008.
[2] Bryan J. International status of thermal error research(1990)[J].CIRP Annals, 1990, 39(2): 645-656. DOI:10.1016/s0007-8506(07)63001-7.
[3] Abele E, Altintas Y, Brecher C. Machine tool spindle units[J]. CIRP Annals, 2010, 59(2): 781-802. DOI:10.1016/j.cirp.2010.05.002.
[4] Zhang Y, Wang L F, Zhang Y D, et al. Design and thermal characteristic analysis of motorized spindle cooling system[J].Advances in Mechanical Engineering, 2021, 13(5): 168781402110208. DOI:10.1177/16878140211020878.
[5] Li X H, Liu J Y, Li C, et al. Research on the influence of air-gap eccentricity on the temperature field of a motorized spindle[J].Mechanical Sciences, 2021, 12(1): 109-122. DOI:10.5194/ms-12-109-2021.
[6] Lee J H, Yang S H. Statistical optimization and assessment of a thermal error model for CNC machine tools[J].International Journal of Machine Tools and Manufacture, 2002, 42(1): 147-155. DOI:10.1016/S0890-6955(01)00110-9.
[7] Gao Q, Lu L H, Zhang R, et al. Investigation on the thermal behavior of an aerostatic spindle system considering multi-physics coupling effect[J].The International Journal of Advanced Manufacturing Technology, 2019, 102(9/10/11/12): 3813-3823. DOI:10.1007/s00170-019-03509-4.
[8] Feng G, Xia C H, Sun L, et al. Fast identification of machine tool spindle temperature rise characteristics based on nonlinear prediction[J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(6): 341-348. DOI:10. 6041/j.issn.1000-1298. 2015. 06. 049. (in Chinese)
[9] Zhang L X, Li C Q, Li J P, et al. The temperature prediction mode of high speed and high precision motorized spindle[J]. Journal of Mechanical Engineering, 2017, 53(23): 129-136. DOI:10. 3901/JME.2017.23.129. (in Chinese)
[10] Kim S M, Lee S K. Prediction of thermo-elastic behavior in a spindle-bearing system considering bearing surroundings[J].International Journal of Machine Tools and Manufacture, 2001, 41(6): 809-831. DOI:10.1016/S0890-6955(00)00103-6.
[11] Liu Y, Wang X F, Zhu X G, et al. Thermal error prediction of motorized spindle for five-axis machining center based on analytical modeling and BP neural network[J].Journal of Mechanical Science and Technology, 2021, 35(1): 281-292. DOI:10.1007/s12206-020-1228-7.
[12] Jian B L, Guo Y S, Hu C H, et al. Prediction of spindle thermal deformation and displacement using back propagation neural network[J].Sensors and Materials, 2020, 32(1): 431. DOI:10.18494/sam.2020.2606.
[13] Kumar S, Pal S K, Singh R. A novel hybrid model based on particle swarm optimisation and extreme learning machine for short-term temperature prediction using ambient sensors[J]. Sustainable Cities and Society, 2019, 49: 101601. DOI:10.1016/j.scs.2019.101601.
[14] Liu C J, Ding W F, Li Z, et al. Prediction of high-speed grinding temperature of titanium matrix composites using BP neural network based on PSO algorithm[J].The International Journal of Advanced Manufacturing Technology, 2017, 89(5/6/7/8): 2277-2285. DOI:10.1007/s00170-016-9267-z.
[15] Li B, Tian X T, Zhang M. Thermal error modeling of machine tool spindle based on the improved algorithm optimized BP neural network[J].The International Journal of Advanced Manufacturing Technology, 2019, 105(1/2/3/4): 1497-1505. DOI:10.1007/s00170-019-04375-w.
[16] Abdulshahed A M, Longstaff A P, Fletcher S. The application of ANFIS prediction models for thermal error compensation on CNC machine tools[J]. Applied Soft Computing, 2015, 27: 158-168. DOI:10.1016/j.asoc.2014.11.012.
[17] Ku°rková V. Kolmogorov’s theorem and multilayer neural networks[J]. Neural Networks, 1992, 5(3): 501-506. DOI:10.1016/0893-6080(92)90012-8.
[18] Cui Q L, Li Q Y, Li G Y, et al. Globally-optimal prediction-based adaptive mutation particle swarm optimization[J].Information Sciences, 2017, 418/419: 186-217. DOI:10.1016/j.ins.2017.07.038.
[19] Kennedy J, Eberhart R. Particle swarm optimization[C]//Proceedings of ICNN’ 95—International Conference on Neural Networks. Perth, WA, Australia, 1995: 1942-1948. DOI:10.1109/ICNN.1995.488968.
[20] Holland J. Adaptation in natural and artificial systems[M]. Michigan: The University of Michigan Press, 1975:42-56.
[21] Ding F J, Jia X D, Hong T J, et al. Flow stress prediction model of 6061 aluminum alloy sheet based on GA-BP and PSO-BP neural networks [J]. Rare Metal Materials and Engineering, 2020, 49(6):1840-1853.(in Chinese)
[22] Niu H T. Smart safety early warning model of landslide geological hazard based on BP neural network[J]. Safety Science, 2020, 123: 104572. DOI:10.1016/j.ssci.2019.104572.
[23] Zhang L, Zhang X G, Chen H, et al. A robust temperature prediction model of shuttle kiln based on ensemble random vector functional link network [J]. Applied Thermal Engineering, 2019, 150: 99-110. DOI: 10.1016 /j. applthermaleng. 2018.12.092.

Memo

Memo:

Biography: Lei Chunli(1977—), female, doctor, associate professor, lclyq2004@163.com.
Foundation items: The National Natural Science Foundation of China(No. 51465035), the Natural Science Foundation of Gansu, China(No.20JR5R-A466).
Citation: Lei Chunli, Zhao Mingqi, Liu Kai, et al. Temperature prediction model for a high-speed motorized spindle based on back-propagation neural network optimized by adaptive particle swarm optimization[J].Journal of Southeast University(English Edition), 2022, 38(3):235-241.DOI:10.3969/j.issn.1003-7985.2022.03.004.

Common functions