Temperature Rise Prediction of Oil-Air Lubricated Angular Contact Ball Bearings Using Artificial Neural Network

Author(s): Baomin Wang*, Xiao Chang.

Journal Name: Recent Patents on Mechanical Engineering

Volume 12 , Issue 3 , 2019

Become EABM
Become Reviewer

Abstract:

Background: Angular contact ball bearing is an important component of many high-speed rotating mechanical systems. Oil-air lubrication makes it possible for angular contact ball bearing to operate at high speed. So the lubrication state of angular contact ball bearing directly affects the performance of the mechanical systems. However, as bearing rotation speed increases, the temperature rise is still the dominant limiting factor for improving the performance and service life of angular contact ball bearings. Therefore, it is very necessary to predict the temperature rise of angular contact ball bearings lubricated with oil-air.

Objective: The purpose of this study is to provide an overview of temperature calculation of bearing from many studies and patents, and propose a new prediction method for temperature rise of angular contact ball bearing.

Methods: Based on the artificial neural network and genetic algorithm, a new prediction methodology for bearings temperature rise was proposed which capitalizes on the notion that the temperature rise of oil-air lubricated angular contact ball bearing is generally coupling. The influence factors of temperature rise in high-speed angular contact ball bearings were analyzed through grey relational analysis, and the key influence factors are determined. Combined with Genetic Algorithm (GA), the Artificial Neural Network (ANN) model based on these key influence factors was built up, two groups of experimental data were used to train and validate the ANN model.

Results: Compared with the ANN model, the ANN-GA model has shorter training time, higher accuracy and better stability, the output of ANN-GA model shows a good agreement with the experimental data, above 92% of bearing temperature rise under varying conditions can be predicted using the ANNGA model.

Conclusion: A new method was proposed to predict the temperature rise of oil-air lubricated angular contact ball bearings based on the artificial neural network and genetic algorithm. The results show that the prediction model has good accuracy, stability and robustness.

Keywords: Angular contact ball bearing, Artificial Neural Network (ANN), Genetic Algorithm (GA), oil-air lubrication, prediction method, temperature rise.

[1]
Yeo SH, Ramesh K. Ultra-high-speed grinding spindle characteristics upon using oil/air mist lubrication. Int J Mach Tools Manuf 2002; 42(7): 815-23.
[http://dx.doi.org/10.1016/S0890-6955(02)00013-5]
[2]
Li Y, Yang ZJ, Chen F, Zhao J. Effect of air inlet flow rate on flow uniformity under oil-air lubrication. Ind Lubr Tribol 2018; 70(2): 282-9.
[http://dx.doi.org/10.1108/ILT-12-2016-0296]
[3]
Zhang J, Liu C, Zeng Q. Application status and study of oil-air lubrication system for high speed rolling bearing. Lubr Eng 2015; 3: 103-8.
[4]
Chang Z, Jia Q, Yuan X, Chen YL. Main failure mode of oil-air lubricated rolling bearing installed in high speed machining. Tribol Int 2017; 112: 68-74.
[http://dx.doi.org/10.1016/j.triboint.2017.03.024]
[5]
Chen Y, Gao W, Liu XH. Backing bearing oil-air lubricating device for 20-rolling mill for rolling oriented silicon steel. CN201711346883 (2017)
[6]
Markus M, Juergen K, Andreas S, Stefan S. Oil-air Lubricant Distributor. US201615297681 (2016).
[7]
Wu H, Zhou Q. Vibration analysis on the rolling element bearing-rotor system of an air blower. J Mech Sci Technol 2012; 26(3): 653-9.
[http://dx.doi.org/10.1007/s12206-011-1201-6]
[8]
Zhang Y, Mei XS. Spindle unit of NC machine tool in aviation manufacturing and its development trend. Aeronaut Manuf Technol 2010; 4: 26-9.
[9]
Kim KS, Lee DW. A numerical approach to determine the frictional torque and temperature of an angular contact ball bearing in a spindle system. Int J PR Eng Man 2015; 16(1): 135-42.
[http://dx.doi.org/10.1007/s12541-015-0017-1]
[10]
Zhao CJ, Yu XK, Huang QX, Ge SD, Gao X. Analysis on the load characteristics and coefficient of friction of angular contact ball bearing at high speed. Tribol Int 2015; 87: 50-6.
[http://dx.doi.org/10.1016/j.triboint.2015.02.012]
[11]
Zhang B, Wang H, Tang Y, Pang BT, Gao XH. Residual useful life prediction for slewing bearing based on similarity under different working conditions. Exp Tech 2018; 42(3): 279-89.
[http://dx.doi.org/10.1007/s40799-018-0235-4]
[12]
Wang LQ, Chen GC. Operating temperature in high-speed ball bearing. P I Mech EnG C-. J Mec 2007; 221(3): 353-9.
[13]
Jeong WH, Ju SN, Young JP, Geun HL, Yong YN. An experimental study on the performance and fatigue life of pitch bearing for wind turbine. J Mech Sci Technol 2015; 29(5): 1963-71.
[http://dx.doi.org/10.1007/s12206-015-0417-2]
[14]
Palmgren A. Ball and Roller Bearing Engineering 3rd ed Burbank: Philadelphia, USA . 1959.
[15]
Shoaib I, Farid AB, Jan C, Bert P, Wim D. Frictional power loss in solid-grease-lubricated needle roller bearing. Lubr Sci 2013; 25(5): 351-67.
[http://dx.doi.org/10.1002/ls.1195]
[16]
Yang Y, Cheng Q, Cai LG, Feng QN. The Heat Generation of High-Speed Spindle Bearings under Different Preload Methods. In: Liu H-C, Sung W-P, Yao W, Eds Computing, Control, Information and Education Engineering. Talor & Francis Group 2015; pp. 153-5.
[http://dx.doi.org/10.1201/b18828-37]
[17]
Harris TA. Rolling Bearing Analysis. 4th ed. John Wiley & Sons: New York, USA 2001.
[18]
Cao W, Wang J, Pu W, Zhang Y, Wu J. A study on the effect of acceleration on slip velocity and lubrication performance in cylindrical roller bearings. P I Mech Eng J J Eng 2016; 230(10): 1231-43.
[19]
Jiang SY, Mao HB. Investigation of the high speed rolling bearing temperature rise with oil-air lubrication. Tribol Int 2011; 133(2)021101
[http://dx.doi.org/10.1115/1.4003501]
[20]
Wu CH, Kung KT. A parametric study on oil/air lubrication of a high-speed spindle. Precis Eng 2005; 29(2): 162-7.
[http://dx.doi.org/10.1016/j.precisioneng.2004.06.005]
[21]
Jeng YR, Gao CC. Investigation of the ball-bearing temperature rise under an oil-air lubrication system. P I Mech Eng B-. J Eng 2001; 215(2): 139-48.
[22]
Hu XQ, Chen WF. Thermal characteristics analysis and experiment for angular contact ball bearing. Xi’an Jiaotong Univ 2015; 49(2): 106-10.
[23]
Jeng YR, Huang PY. Predictions of temperature rise for ball bearings. Tribol T 2003; 46(1): 49-56.
[http://dx.doi.org/10.1080/10402000308982599]
[24]
Yan K, Wang N. Theo retical and experimental investigation on the thermal characteristics of double-row tapered roller bearings of high speed locomotive. Int J Heat Mass Transf 2015; 84: 1119-30.
[http://dx.doi.org/10.1016/j.ijheatmasstransfer.2014.11.057]
[25]
Deng XL, Fu JZ. A predictive model for tem perature rise of spindle-bearing integrated system. J Manuf Sci 2015; 137(2)021014
[http://dx.doi.org/10.1115/1.4029445]
[26]
Xu M, Jiang SY. An improved thermal model for machine tool bearings. Int J Mach Tools Manuf 2007; 47(1): 53-62.
[http://dx.doi.org/10.1016/j.ijmachtools.2006.02.018]
[27]
Kim KS, Lee DW. A numerical approach to deter mine the frictional torque and temperature of an angular contact ball bearing in a spindle system. Int J Precis Eng Manuf 2016; 16(1): 135-42.
[http://dx.doi.org/10.1007/s12541-015-0017-1]
[28]
Zeng QF, Zhang JH. A comparative study on simulation and experiment of oil-air lubrication unit for high speed bearing. Ind Lubr Tribol 2016; 68(3): 325-35.
[http://dx.doi.org/10.1108/ILT-05-2015-0066]
[29]
Zhang GW, Yang R, Gao WG, et al. Spindle end thermal deformation synthesis simulation analysis method. CN201810568785 (2018)
[30]
Zhang YE, Yu FD, Ye HJ. Pivoting support with high bearing capacity under high-temperature environment and method for improving bearing capacity of pivoting support. CN201610625931 (2016).
[31]
Najar FA, Harmain GA. Thermal effects for conventional and water-cooled thrust bearing using finite difference method: Comparative analysis. Int J Precis Technol 2015; 5(1): 14-26.
[http://dx.doi.org/10.1504/IJPTECH.2015.069970]
[32]
Mazumder S. Comparative assessment of the finite difference, finite element, and finite volume methods for a benchmark one-dimensional steady-state heat conduction problem. J Heat Trans-T ASME 2017; 139(7)071301
[http://dx.doi.org/10.1115/1.4035713]
[33]
Zheng DX, Chen WF. Thermal performances on angular contact ball bearing of high-speed spindle considering structural constraints under oil-air lubrication. Tribol Int 2018; 109: 593-601.
[http://dx.doi.org/10.1016/j.triboint.2017.01.035]
[34]
Yan K, Hong J. Thermal-deformation coupling in thermal network for transient analysis of spindle-bearing system. Int J Therm Sci 2016; 104: 1-12.
[http://dx.doi.org/10.1016/j.ijthermalsci.2015.12.007]
[35]
Ai SY, Wang WZ, Wang YL, Zhao ZQ. Temperature rise of double-row tapered roller bearings analyzed with the thermal network method. Tribol Int 2015; 87: 11-22.
[http://dx.doi.org/10.1016/j.triboint.2015.02.011]
[36]
Hu JB, Wu W. Numerical investigation of the air-oil two-phase flow inside an oil-jet lubricated ball bearing. Int J Heat Mass Transf 2014; 68: 85-93.
[http://dx.doi.org/10.1016/j.ijheatmasstransfer.2013.09.013]
[37]
Wu W, Hu JB, Yuan SH, Hu CH. Numerical and experimental investigation of the stratified air-oil flow inside ball bearings. Int J Heat Mass Transf 2016; 103: 619-25.
[http://dx.doi.org/10.1016/j.ijheatmasstransfer.2016.07.090]
[38]
Wu W, Hu CH, Hu JB, Yuan SH. Jet cooling for rolling bearings: Flow visualization and temperature distribution. Appl Therm Eng 2016; 105: 217-24.
[http://dx.doi.org/10.1016/j.applthermaleng.2016.05.147]
[39]
Rodrigo JGL, Rosa MQF. Assessment of CFD/VOF method for trickle-bed reactor modeling in the catalytic wet oxidation of phenolic wastewaters. Ind Eng Chem Res 2010; 49(6): 2638-48.
[http://dx.doi.org/10.1021/ie901412x]
[40]
Jiaqiang E, Zhang ZQ, Tu ZF, Zuo W, Hu WY, Han DD, et al. Effect analysis on flow and boiling heat transfer performance of cooling water-jacket of bearing in the gasoline engine turbocharger. Appl Therm Eng 2018; 130: 754-66.
[http://dx.doi.org/10.1016/j.applthermaleng.2017.11.070]
[41]
Meng Z, Hu M. Rolling bearing fault diagnosis method based on LMD multi scale entropy and probabilistic neural network. Chin J Mech Eng-En 2016; 4: 433-7.
[42]
Alonso JM, Alvarruiz F. Combining neural network and genetic algorithms to predict and reduce diesel engine emissions. IEEE Trans Evol Comput 2007; 11(1): 46-55.
[http://dx.doi.org/10.1109/TEVC.2006.876364]
[43]
Jiang F, Dong L, Dai Q. Electrical resistivity imaging inversion: An ISFLA trained kernel principal component wavelet neural network approach. Neural Netw 2018; 104: 114-23.
[http://dx.doi.org/10.1016/j.neunet.2018.04.012]
[44]
Milad F, Gholamreza A. A review of Genetic Programming and Artificial Neural Network applications in pile foundations. Int J Geo-Eng 2018; 9(2)
[http://dx.doi.org/10.1186/s40703-017-0067-6]
[45]
Li H, Wang XS, Ding SF. Research and development of neural network ensembles: a survey. Artif Intell Rev 2018; 49(4): 455-79.
[http://dx.doi.org/10.1007/s10462-016-9535-1]
[46]
Kasiviswanathan KS, Sudheer KP. Methods used for quantifying the prediction uncertainty of artificial neural network based hydrologic models. Stochastic Environ Res Risk Assess 2017; 31(7): 1659-70.
[http://dx.doi.org/10.1007/s00477-016-1369-5]
[47]
Drees KH. Building management system with augmented deep learning using combined regression and artificial neural network modeling. US201816054805 (2018).
[48]
Wang Y, Chen FY, Wang MS, Li ZM, Yan TY, Pan TH. Short-term load predicting method for Elman neural network based on improved ABC algorithm. CN201810473235 (2018).
[49]
Zheng S, Luo D, Ge M, Zheng XQ, Wei J. Process industrial system prediction model based on multivariate correlation and time delay. CN201810774602 (2018).
[50]
Zhang GZ, Ao WJ, Zeng GR, Song W, Yin CC, Hu XT. Method for predicting mechanical property of propellant based on BP (Back Propagation) artificial neural network. CN201810137068 (2018)
[51]
Guo BB, Li F. Prediction method of vessel maintenance outlay based on the BP neural network. J Syst Eng Electron 2003; 13(3): 61-70.
[52]
Liu F, Liu J. Prediction of β-turns using double BP network with novel coding schemes of amino acids. Wuhan Univ J Nat Sci 2009; 142(2): 119-24.
[http://dx.doi.org/10.1007/s11859-009-0205-x]
[53]
Lü YM, Tang DZ. Productivity matching and quantitative prediction of coal bed methane wells based on BP neural network. Sci China Technol Sci 2011; 54(5): 1281-6.
[http://dx.doi.org/10.1007/s11431-011-4348-6]
[54]
Lin YC, Chen DD, Chen MS, Chen XM, Li J. A precise BP neural network-based online model predictive control strategy for die forging hydraulic press machine. Neural Comput Appl 2018; 29(9): 585-96.
[http://dx.doi.org/10.1007/s00521-016-2556-5]
[55]
Hu ZL, Zhao Q, Wang J. The prediction model of cotton yarn intensity based on the CNN-BP neural network. Wirel Pers Commun 2018; 102(2): 1905-16.
[http://dx.doi.org/10.1007/s11277-018-5245-0]
[56]
Grant BJB. Artificial neural network for predicting respiratory disturbances and method for developing the same. US6083173 (2000).
[57]
Hiu MD. Predicting well markers from artificial neural-networkpredicted lithostratigraphic facies. US9501740 (2016).
[58]
Jiang Y, Zhu CR. Stock index futures price forecasting method based on EDM algorithm and BP neural network. CN201810793961 (2018).
[59]
Zhou Y. Power grid fault prediction method. CN201810690571 (2018).
[60]
Cheng JT, Mei J, Xiong Y. Transformer fault diagnosis method based on improved cuckoo search optimal neural network. CN201810270330 (2018).
[61]
Deng JL. Grey system theory. Huazhong University of Science and Technology Press: Wuhan 2002.
[62]
Wang BM, Gao C. Prediction of the friction torque in grease lubricated angular contact ball bearing using grey system theory. J Mech Sci Technol 2016; 30(5): 2195-201.
[http://dx.doi.org/10.1007/s12206-016-0427-8]
[63]
Tuo S, Wei J, Ping L. A method of clustering ensemble based on grey relation analysis. Wirel Pers Commun 2018; 103(1): 871-85.
[http://dx.doi.org/10.1007/s11277-018-5484-0]
[64]
Long YQ, Li QH, Zhou H, Meng AH, Zhang YG. A grey-relation-based method (GRM) for thermogravimetric (TG) data analysis. J Mater Cycles Waste 2018; 20(2): 1026-35.
[http://dx.doi.org/10.1007/s10163-017-0665-6]
[65]
Zeng WX. Brake wear early warning method and system. CN106594131 (2017).
[66]
Li H, Feng G, Shi R, Wang RP. Extension clustering method and system based on grey correlation degree. CN201711444377 (2017).
[67]
Yokono M. Neural network learning system. US5295227 (1994).
[68]
Buescher KL. Adaptive model predictive process control using neural networks. US5659667 (1997).
[69]
Pannese PD. Applications of neural networks. US8442667 (2013).
[70]
Eremia M, Liu CC, Edris AA. Genetic Algorithms Advanced solutions in power systems: HVDC, FACTS, and artificial intelligence. John Wiley & Sons: New York, USA 2016.
[71]
Guha A. Genetic algorithm synthesis of neural networks. US5140530 (1992)
[72]
Harvey RL. Genetic algorithm technique for designing neural networks. US5249259 (1993).
[73]
Li DJ, Li YY, Li JX, Yu F. Gesture recognition based on BP Neural Network improved by chaotic genetic algorithm. Int J Automat Comput 2018; 15(3): 267-76.
[http://dx.doi.org/10.1007/s11633-017-1107-6]
[74]
Yang HD, Sen Z. Precision prediction model in FDM by the combination of genetic algorithm and BP neural network algorithm. J Aerosp Eng 2017; 5(3): 134-41.
[75]
Mao HB. Investigation of high speed rolling-bearings under oil-air lubrication Master Dissertation, Southeast University, Nanjing, China 2010.
[76]
Xie J. Experimental study on friction and wear of gemstone bearings and high speed motorized spindle oil and gas lubrication Master Dissertation, Southeast University, Nanjing, China, 2006.


Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 12
ISSUE: 3
Year: 2019
Page: [248 - 261]
Pages: 14
DOI: 10.2174/2212797612666190530115739
Price: $25

Article Metrics

PDF: 14
HTML: 1