Characterizing Spring Durability for Automotive Ride Using Artificial Neural Network Analysis

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    This paper presents the establishment of a relationship between coil spring fatigue life and automotive vertical vibration using neural network. During an automotive suspension design process, the suspension components are designed with the consideration of structure strength and fatigue life as well as the effects toward automotive ride. Hence, it is important to have a functional mathematical model to predict the fatigue life and automotive life simultaneously. To build the mathematical model, a multibody kinematic quarter model of suspension system was constructed to simulate force and acceleration time histories from the suspension system and the sprung mass of the vehicle model. The force time histories were used to predict the fatigue life of the coil spring while the acceleration time histories were converted into ISO vertical vibration index. A neural network model was created and used to fit the spring fatigue life and vehicle vertical vibration into a mathematical function. The neural network with 1 hidden layer and 2 neurons has shown a good fitting of the data with coefficient of determination as high as 0.88, 0.98, 0.96 for training, validation and testing, respectively. This constructed neural network serves to predict the vehicle vertical vibration using the spring fatigue life and suspension natural frequencies as input, and hence reduce the automotive suspension design process.  



  • Keywords

    Spring Fatigue; Vertical Vibration, Curve Fitting, Neural Network

  • References

      [1] Yunus M, Alsoufi MS, Basha MT (2016), Functional design for the manufacture of quality and cost-effective assembly components of an automobile car using FEA. Elixir Mechanical Engineering 93, 39506 – 39510.

      [2] Hassaan GA (2015), Car dynamics using quarter model and passive suspension, Part IV: destructive miniature humps (bump). Global Journal of Advanced Research 2(2), 451 – 463.

      [3] Čorić M, Deur J, Kasac J, Tseng E, Hrovat D (2016), Optimisation of active suspension control inputs for improved vehicle handling performance. Vehicle System Dynamics 54(11), 1574 – 1600.

      [4] Kamal M & Rahman MM (2014), Finite Element-based fatigue behavior of springs in automobile suspension. International Journal of Automotive and Mechanical Engineering 10, 1910 – 1919.

      [5] Putra TE, Abdullah S, Schramm D, Nuawi MZ, Bruckmann T (2017), Reducing cyclic testing time for components of automotive suspension system utilising the wavelet transform and the Fuzzy C-means. Mechanical Systems and Signal Processing 90, 1 – 14.

      [6] Ngwangwa, HM, Heyns PS, Breytenbach HGA, Els PS (2014), Reconstruction of road defects and road roughness classification using artificial neural network simulation and vehicle dynamic responses: Application to experimental data. Journal of Terramechanics 53, 1 – 18.

      [7] Zhu Y & Zhu S (2014), Nonlinear time-delay suspension adaptive neural network active control. Abstract and Applied Analysis 765871.

      [8] Tian Z, Wong L, Safaei N (2010), A neural network approach for remaining useful life prediction utilizing both failure and suspension histories. Mechanical Systems and Signal Processing 24(5), 1542 – 1555.

      [9] Ali JB, Chebel-Morello B, Saidi L, Malinowski S, Fnaiech F (2015), Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network. Mechanical Systems and Signal Processing 56-57, 150 – 172.

      [10] Kang JY, Choi BI, Lee HK, Kim JS, Kim KJ (2006), Neural network application in fatigue damage analysis under multiaxial random loadings. International Journal of Fatigue 28(2), 132 – 140.

      [11] Wang L, Knarachos S, Christensen J (2016), Characterisation of vibration input to flywheel used on urban bus. Journal of Physics 744, 012214.

      [12] Putra TE, Abdullah S, Schramm D, Nuawi, M.Z., Bruckmann, T. 2015. Generating strain signals under consideration of road surface profiles. Mechanical Systems and Signal Processing 60 – 61, 485 – 497.

      [13] Woods DE & Jawad BA (1999), Numerical design of racecar suspension parameters. SAE technical paper series 1999-01-2257.

      [14] ISO 2631-1 (1997), Mechanical Vibration and Shock-evaluation of Human Exposure to Whole-body Vibration—part 1: General Requirements, ISO, Geneva, Switzerland.

      [15] Ince A & Glinka G (2011), A modification of Morrow and Smith-Watson-Topper mean stress correction models. Fatigue and Fracture of Engineering Materials and Structures 34(11), 854 – 867.

      [16] Goncalves VRM, Canale LCF, Lesvlovsek V, Podgonik B (2016), Influence of cryogenic treatment on the fracture toughness of conventional and super clean spring steels. SAE technical papers 2016-36-0064.

      [17] Cui M, Zhao Y, Xu B, Gao X (2017), A new approach for determining damping factors in Levenberg-Marquadt algorithm for solving an inverse heat conduction problem. International Journal of Heat and Mass Transfer 107, 747 – 754.

      [18] Chen X (2014), Analysis of crosswind fatigue of wind-excited structures with nonlinear aerodynamic damping. Engineering Structures 74, 145 – 156.

      [19] Lu F, Kennedy D, Williams FW, Lin JH (2008), Symplectic analysis of vertical random vibration for coupled vehicle-track systems. Journal of Sound and Vibration 317, 236 – 249.

      [20] Chen MZQ, Hu Y, Huang L, Chen G (2014), Influence of inerter on natural frequencies of vibration systems. Journal of Sound and Vibration 333(7), 1874 – 1887.

      [21] Heaton, J (2008), Introduction to neural networks for c#, 2nd ed, Heaton research, U.S.A.

      [22] Dorofki M, Elshafir AH, Jaafar O, Karim OA, Mastura F (2012), Comparison of artificial neural network transfer function abilities to simulate extreme runoff data, 2012 International Conference on Environment, Energy and Biotechnology 33, 39 – 44.

      [23] Sivák P & Ostertagová E (2012), Evaluation of Fatigue Tests by Means of Mathematical Statistics. Procedia Engineering 48, 636-642.

      [24] Azadi S & Karimi-Jashni A (2016), Verifying the performance of artificial neural network and multiple linear regression in predicting the mean seasonal municipal solid waste generation rate: A case study of Fars province, Iran. Waste Management 48, 14 – 23.




Article ID: 16622
DOI: 10.14419/ijet.v7i3.17.16622

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.