An Improved Model for Predicting the Scattered S-N Curves

In this article an improved neural network model is presented that allows us to predict the scattered S-N curves. The model is capable of predicting the S-N curve in its high-cycle and very-high-cycle fatigue domains by considering also the increased scatter of the fatigue-life data below the knee point of the S-N curve. The scatter of the fatigue-life data for an arbitrary amplitude-stress level is modelled with a two-parametric Weibull%s probability density function, the parameters of which are varied as a function of the amplitude-stress level. The parameters of the S-N curve trend and its scatter distribution are not fixed, but depend on the parameters of the production process via a serial-hybrid neural network. The article presents the theoretical background and the application in the case of real experimental fatigue data for 51CrV4 spring steel manufactured with two different manufacturing technologies and two different heat treatments.

[1]  Peter Vamplew,et al.  Accelerating Real-Valued Genetic Algorithms Using Mutation-with-Momentum , 2005, Australian Conference on Artificial Intelligence.

[2]  Yong Xiang Zhao,et al.  The framework for a strain-based fatigue reliability analysis , 2008 .

[3]  Zhen Xiao,et al.  Studying the Fatigue Life of a Non-pneumatic Wheel by Using Finite-Life Design for Life Prediction , 2018 .

[4]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[5]  W. Schütz.  Prof. Dr.‐Ing. Erwin Haibach Betriebsfestigkeit Verfahren und Daten zur Bauteilberechnung , 1991 .

[6]  Bathias.  There is no infinite fatigue life in metallic materials , 1999 .

[7]  Matija Fajdiga,et al.  Modelling the scatter of E–N curves using a serial hybrid neural network , 2012, Neural Computing and Applications.

[8]  H. Akaike.  A new look at the statistical model identification , 1974 .

[9]  Matija Fajdiga,et al.  Joint estimation of E–N curves and their scatter using evolutionary algorithms , 2013 .

[10]  William Q. Meeker,et al.  Estimating Fatigue Curves With the Random Fatigue-Limit Model , 1999, Technometrics.

[11]  Roberto Tovo.  On the fatigue reliability evaluation of structural components under service loading , 2001 .

[12]  Mukul Agarwal,et al.  Combining neural and conventional paradigms for modelling, prediction and control , 1997, Int. J. Syst. Sci..

[13]  David R. Anderson,et al.  Model selection and multimodel inference : a practical information-theoretic approach , 2003 .

[14]  Marko Nagode,et al.  Parametric modelling and scatter prediction of rainflow matrices , 2001 .

[15]  Peter Schaumann,et al.  Fatigue tests of axially loaded butt welds up to very high cycles , 2013 .

[16]  Fatigue Design of Ferritic-Pearlitic Nodular Cast Iron Components with Surface Discontinuities , 2018, Strojniški vestnik - Journal of Mechanical Engineering.

[17]  Marko Nagode,et al.  A neural network approach to describing the scatter of S–N curves , 2006 .

[18]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[19]  V. Leskovšek,et al.  Microstructure refinement and its effect on properties of spring steel , 2014 .

[20]  Daniel R. Eno.  Practical Reliability Engineering, 4th Ed. , 2003 .

[21]  Jernej Klemenc,et al.  Influence of fatigue-life data modelling on the estimated reliability of a structure subjected to a constant-amplitude loading , 2015, Reliab. Eng. Syst. Saf..

[22]  J. Klemenc,et al.  Theoretical framework for estimating a product's reliability using a variable-amplitude loading spectrum and a stress-based approach , 2018 .