Using the finite element method and data mining techniques as an alternative method to determine the maximum load capacity in tapered roller bearings

被引:26
|
作者
Lostado-Lorza, Ruben [1 ]
Escribano-Garcia, Ruben [1 ]
Fernandez-Martinez, Roberto [2 ]
Illera-cueva, Marcos [1 ]
Mac Donald, Bryan J. [3 ]
机构
[1] Univ La Rioja, Dept Mech Engn, Logrono, Spain
[2] Univ Basque Country, UPV EHU, Dept Elect Engn, Bilbao, Spain
[3] Dublin City Univ, Sch Mech & Mfg Engn, Dublin, Ireland
关键词
Finite elements method; Data mining techniques; Optimization; Design of experiments; Double-row tapered roller bearing; REGRESSION; APPROXIMATION; MODELS; ALGORITHMS; STRESS;
D O I
10.1016/j.jal.2016.11.009
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Double-row tapered roller bearings (TRBs) are mechanical devices designed to support a combination of preload, radial load, axial load and torque. They are widely used in vehicles for high load and moderate rotation speeds. This combination of loads produces high contact stresses on the bearing raceways that are difficult to calculate, and can cause undesirable defects like fatigue spelling and pitting. In recent decades, the Finite Element Method (FEM) has been used to obtain the distribution of the contact stresses on each of the raceways, although this method has the disadvantage of a high computational cost. The myriad of possible combinations of input loads on the TRB (preload, radial load, axial load and torque) makes it much harder to calculate the distribution of these contact stresses. This paper proposes a methodology that combines the FEM and data mining techniques to determine the maximum load capacity in TRBs. First, a three-dimensional finite element (FE) model was generated according to the real materials' properties, geometry and coefficients of friction of all parts that make up the double-row TRB. Subsequently, a Design of Experiment (DoE) was completed that considered a combination of the mentioned input loads, which were simulated in the FE model. Based on the contact stresses obtained from the FE simulations, a group of regression models linear regression (LR), Gaussian processes (GP), artificial neural networks (ANN), support vector machines (SVM) and regression trees (RT) were built to predict the contact stresses ratios that act on each of the row of rollers in the outer raceway of the TRB. Finally, the best combination of input loads was achieved by applying evolutionary optimization techniques based on genetic algorithms (GA) to the best regression models previously obtained. The maximum load capacity of the TRB was achieved when the radial load obtained was a maximum, while the stresses ratios of the two contacts in the outer raceway of the TRB were close to 25%. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码:4 / 14
页数:11
相关论文
共 50 条
  • [1] Combination of the Finite Element Method and Data Mining Techniques to Design and Optimize Bearings
    Lostado-Lorza, Ruben
    Escribano-Garcia, Ruben
    Fernandez-Martinez, Roberto
    Illera-Cueva, Marcos
    Mac Donald, Bryan J.
    INTERNATIONAL JOINT CONFERENCE SOCO'14-CISIS'14-ICEUTE'14, 2014, 299 : 165 - 174
  • [2] Combining the Finite Element Method and Response Surface Methodology for Adjustment of Contact Stress Ratios in Tapered Roller Bearings
    Lostado, R.
    Escribano, R.
    Fernandez Martinez, R.
    Mac Donald, B. J.
    NEW TRENDS IN MECHANISM AND MACHINE SCIENCE: FROM FUNDAMENTALS TO INDUSTRIAL APPLICATIONS, 2015, 24 : 957 - 964
  • [3] Finite Element Method Analysis and Optimal Design of Roller Convexity of Tapered Roller Bearing
    Wang, Zhiwei
    Meng, Lingqin
    Hao, Wensi
    Zhang, E.
    MANUFACTURING ENGINEERING AND AUTOMATION I, PTS 1-3, 2011, 139-141 : 1079 - +
  • [4] Optimization of hot forming process using data mining techniques and finite element method
    Zheng, G. J.
    Zhang, J. W.
    Hu, P.
    Shi, D. Y.
    INTERNATIONAL JOURNAL OF AUTOMOTIVE TECHNOLOGY, 2015, 16 (02) : 329 - 337
  • [5] Optimization of hot forming process using data mining techniques and finite element method
    G. J. Zheng
    J. W. Zhang
    P. Hu
    D. Y. Shi
    International Journal of Automotive Technology, 2015, 16 : 329 - 337
  • [6] Determination of the contact stresses in double-row tapered roller bearings using the finite element method, experimental analysis and analytical models
    Ruben Lostado
    Roberto Fernandez Martinez
    Bryan J. Mac Donald
    Journal of Mechanical Science and Technology, 2015, 29 : 4645 - 4656
  • [7] Determination of the contact stresses in double-row tapered roller bearings using the finite element method, experimental analysis and analytical models
    Lostado, Ruben
    Fernandez Martinez, Roberto
    Mac Donald, Bryan J.
    JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, 2015, 29 (11) : 4645 - 4656
  • [8] Prediction models for calculating bolted connections using data mining techniques and the finite element method
    Fernandez, J.
    Pernia, A.
    Martinez-de-Pison, F. J.
    Lostado, R.
    ENGINEERING STRUCTURES, 2010, 32 (10) : 3018 - 3027
  • [9] Genetic Algorithms Combined with the Finite Elements Method as an Efficient Methodology for the Design of Tapered Roller Bearings
    Lostado-Lorza, Ruben
    Sanz-Garcia, Andres
    Gonzalez-Marcos, Ana
    Pernia-Espinoza, Alpha
    SOFT COMPUTING MODELS IN INDUSTRIAL AND ENVIRONMENTAL APPLICATIONS, 6TH INTERNATIONAL CONFERENCE SOCO 2011, 2011, 87 : 243 - 252
  • [10] Investigations into the load-bearing capacity of excavations using the finite element method
    Juergens, Hauke
    GEOTECHNIK, 2025, 48 (01)