Oil leakage between the slipper and swash plate of an axial piston pump has a significant effect on the efficiency of the pump. Therefore, it is extremely important that any leakage can be predicted. This study investigates the leakage, oil film thickness, and pocket pressure values of a slipper with circular dimples under different working conditions. The results reveal that flat slippers suffer less leakage than those with textured surfaces. Also, a deep learning-based framework is proposed for modeling the slipper behavior. This framework is a long short-term memory-based deep neural network, which has been extremely successful in predicting time series. The model is compared with four conventional machine learning methods. In addition, statistical analyses and comparisons confirm the superiority of the proposed model.
Özkan Özmen
,
Cem Sinanoğlu
,
Abdullah Caliskan
,
Hasan Badem
. Prediction of Leakage from an Axial Piston Pump Slipper with Circular Dimples Using Deep Neural Networks[J]. Chinese Journal of Mechanical Engineering, 2020
, 33(2)
: 28
-28
.
DOI: 10.1186/s10033-020-00443-5
[1] D Gropper, L Wang, T J Harvey. Hydrodynamic lubrication of textured surfaces: A review of modeling techniques and key findings. Tribology International, 2016, 94: 509-529.
[2] E Koc, C J Hooke. Considerations in the design of partially hydrostatic slipper bearings. Tribology International, 1997, 30(11): 815-823.
[3] E Koc, C J Hooke, K Y Li. Slipper balance in axial piston pumps and motors. Journal of Tribology, 1992, 114(4): 766-772.
[4] J M Bergada, J Watton, J M Haynes, et al. The hydrostatic/hydrodynamic behaviour of an axial piston pump slipper with multiple lands. Meccanica, 2010, 45(4): 585-602.
[5] J M Bergada, J M Haynes, J Watton. Leakage and groove pressure of an axial piston pump slipper with multiple lands. Tribology Transactions, 2008, 51(4): 469-482.
[6] I Etsion, G Halperin, V Brizmer, et al. Experimental investigation of laser surface textured parallel thrust bearings. Tribology Letters, 2004, 17(2): 295-300.
[7] S C Sharma, S K Yadav. A comparative study of full and partial textured hybrid orifice compensated circular thrust pad bearing system. Tribology International, 2016, 95: 170-180.
[8] S Ye, H Tang, Y Ren, et al. Study on the load-carrying capacity of surface textured slipper bearing of axial piston pump. Applied Mathematical Modelling, 2020, 77: 554-584.
[9] M A Karkoub, O E Gad, M G Rabie. Predicting axial piston pump performance using neural networks. Mechanism and Machine Theory, 1999, 34(8): 1211-1226.
[10] M Karkoub, A Elkamel. Modelling pressure distribution in a rectangular gas bearing using neural networks. Tribology International, 1997, 30(2): 139-150.
[11] F Canbulut, C Sinanoğlu, Ş Yıldırım, et al. Design of neural network model for analyzing hydrostatic circular recessed bearings with axial piston pump slipper. Industrial Lubrication and Tribology, 2004, 56(5): 288-299.
[12] F Canbulut, C Sinanoğlu, Ş Yildirim. Neural network analysis of leakage oil quantity in the design of partially hydrostatic slipper bearings. Industrial Lubrication and Tribology, 2004, 56(4): 231-243.
[13] F Canbulut, E Koç, C Sinanoğlu. Design of artificial neural networks for slipper analysis of axial piston pumps. Industrial Lubrication and Tribology, 2009, 61(2): 67-77.
[14] F Canbulut, Ş Yildirim, C Sinanoğlu. Design of an artificial neural network for analysis of frictional power loss of hydrostatic slipper bearings. Tribology Letters, 2004, 17(4): 887-899.
[15] Ö Özmen, C Sinanoğlu, T Batbat, et al. Prediction of slipper pressure distribution and leakage behaviour in axial piston pumps using ANN and MGGP. Mathematical Problems in Engineering, 2019, https://doi.org/10.1155/2019/7317520.
[16] F Canbulut, C Sinanoğlu, M Erkilet, et al. Neural predictor to analyse the efficiency of positive displacement pumps. Journal of the Balkan Tribological Association, 2012, 18(4): 530-539.
[17] Y LeCun, Y Bengio, G Hinton. Deep learning. Nature, 2015, 521(7553): 436-444.
[18] Q Chao, J Zhang, B Xu, et al. Test rigs and experimental studies of the slipper bearing in axial piston pumps: A review. Measurement, 2019, 132: 135-149.
[19] S Kumar, J M Bergada, J Watton. Axial piston pump grooved slipper analysis by CFD simulation of three-dimensional NVS equation in cylindrical coordinates. Computers & Fluids, 2009, 38(3): 648-663.
[20] Caliskan, M E Yuksel, H Badem, et al. A deep neural network classifier for decoding human brain activity based on magnetoencephalography. Elektronika ir Elektrotechnika, 2017, 23(2): 63-67.
[21] H Badem, A Caliskan, A Basturk, et al. Classification and diagnosis of the Parkinson disease by stacked autoencoder. ELECO 2016 - IEEE National Conference on Electrical, Electronics and Biomedical Engineering, Bursa, Turkey, 2016: 499-502.
[22] A Caliskan, M E Yuksel, H Badem, et al. Performance improvement of deep neural network classifiers by a simple training strategy. Engineering Applications of Artificial Intelligence, 2018, 67: 14-23.
[23] H Badem, A Basturk, A Caliskan, et al. A new efficient training strategy for deep neural networks by hybridization of artificial bee colony and limited-memory BFGS optimization algorithms. Neurocomputing, 2017, 266: 506-526.
[24] R Jozefowicz, W Zaremba, I Sutskever. An empirical exploration of recurrent network architectures. ICML 2015 - International Conference on Machine Learning, Lille, France, 2015: 2342-2350.
[25] S Hochreiter, J Schmidhuber. Long short-term memory. Neural Computation, 1997, 9(8): 1735-1780.
[26] H Sak, A Senior, F Beaufays. Long short-term memory recurrent neural network architectures for large scale acoustic modeling. INTERSPEECH 2014, In Fifteenth Annual Conference of the International Speech Communication Association, Singapore, 2014: 338-342
[27] F Canbulut, C Sinanoğlu, E Koç. Experimental analysis of frictional power loss of hydrostatic slipper bearings. Industrial Lubrication and Tribology, 2009, 61(3): 123-131.
