A neural network approach to fatigue life prediction

Abstract In this work, a novel approach to fatigue life prediction under step-stress conditions is introduced, where the cumulative distribution function for the failure of components was implemented by means of a neural network. The model was fit to experimental data on the fatigue life of steel under step-stress conditions. For comparison, a standard approach based on the lognormal distribution function was also implemented and fit to the same experimental data. Both models were optimized by evolutionary computation, using a maximum likelihood estimator. The Kolmogorov–Smirnov test was applied to compare the results of the new approach to those obtained with the lognormal distribution function.

[1]  S. Winterstein,et al.  Random Fatigue: From Data to Theory , 1992 .

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  W. Sha,et al.  Software products for modelling and simulation in materials science , 2003 .

[4]  W. Nelson.  Statistical Methods for Reliability Data , 1998 .

[5]  Avinash Dharmadhikari,et al.  A model for step‐stress accelerated life testing , 2003 .

[6]  Kenneth de Jong,et al.  Evolutionary computation: a unified approach , 2007, GECCO.

[7]  Siew-Leng Teng,et al.  A least-squares approach to analyzing life-stress relationship in step-stress accelerated life tests , 2002, IEEE Trans. Reliab..

[8]  P. K. Ray,et al.  Prediction of residual fatigue life under interspersed mixed‐mode (I and II) overloads by Artificial Neural Network , 2009 .

[9]  Chengjie Xiong,et al.  Step-stress life-testing with random stress-change times for exponential data , 1999 .

[10]  W. B. Nelson,et al.  Residuals and Their Analyses for Accelerated Life Tests With Step and Varying Stress , 2008, IEEE Transactions on Reliability.

[11]  Essam Khalaf Al-Hussaini,et al.  Estimation in step-stress accelerated life tests for the exponentiated exponential distribution with type-I censoring , 2009, Comput. Stat. Data Anal..

[12]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[13]  W. S. Johnson,et al.  Probabilistic aspects of life prediction , 2004 .

[14]  Chengjie Xiong,et al.  Inferences on a simple step-stress model with type-II censored exponential data , 1998 .

[15]  Efstratios F. Georgopoulos,et al.  Artificial neural networks in spectrum fatigue life prediction of composite materials , 2007 .

[16]  H. K. D. H. Bhadeshia,et al.  Neural Networks in Materials Science , 1999 .

[17]  Jye-Chyi Lu,et al.  Performance of parameter-estimates in step-stress accelerated life-tests with various sample-sizes , 2002, IEEE Trans. Reliab..

[18]  P. C. Gope,et al.  Prediction of Fatigue Lives of Composites Material by Artificial Neural Network , 2007 .

[19]  Guangbin Yang.  Life cycle reliability engineering , 2007 .

[20]  Xiang-kang Yin,et al.  Some Aspects of Accelerated Life Testing by Progressive Stress , 1987, IEEE Transactions on Reliability.

[21]  Giuliano Allegri,et al.  On the inverse power laws for accelerated random fatigue testing , 2008 .

[22]  Thong Ngee Goh,et al.  Analysis of step-stress accelerated-life-test data: a new approach , 1996, IEEE Trans. Reliab..

[23]  Dong-Woo Lee,et al.  A study on fatigue damage modeling using neural networks , 2005 .

[24]  Jae-Youn Kang,et al.  Neural network application in fatigue damage analysis under multiaxial random loadings , 2006 .

[25]  A. A. Aghakouchak,et al.  Prediction of fatigue crack growth rate in welded tubular joints using neural network , 2007 .

[26]  Do Sun Bai,et al.  Optimum simple step-stress accelerated life tests with censoring , 1989 .

[27]  F. Smieja.  Neural network constructive algorithms: Trading generalization for learning efficiency? , 1993 .

[28]  Walter C. Merrill,et al.  A real time neural net estimator of fatigue life , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[29]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[30]  K. L. Edwards,et al.  The use of artificial neural networks in materials science based research , 2007 .

[31]  W. Nelson.  Accelerated Life Testing - Step-Stress Models and Data Analyses , 1980, IEEE Transactions on Reliability.

[32]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[33]  Jack A. Collins,et al.  Failure of materials in mechanical design , 1981 .

[34]  Erwin Kreyszig,et al.  Introductory Mathematical Statistics. , 1970 .

[35]  W. Nelson,et al.  Optimum Simple Step-Stress Plans for Accelerated Life Testing , 1983, IEEE Transactions on Reliability.

[36]  Russell Beale,et al.  Handbook of Neural Computation , 1996 .