Off-Line and On-Line Fatigue Crack Growth Prediction Using Multivariate Gaussian Process

Abstract : Off-line and On-line fatigue crack growth prediction of Aluminum 2024 compact-tension (CT) specimens under variable loading has been modeled, using multivariate Gaussian Process technique. The Gaussian Process model projects the input space to an output space by probabilistically inferring the underlying non-linear function relating input and output. For the off-line prediction the input space of the model is trained with parameters that affect fatigue crack growth, such as number of fatigue cycles, minimum load, maximum load, and load ratio. For the case of online prediction, the model input space is trained using features found from piezoelectric sensor signals rather than training the input space with loading parameters, which are difficult to measure in a real time scenario. Two different algorithms such as Principal Component Analysis (PCA) and Kernel Principal Component Analysis (KPCA) are used to extract the principal features from sensor signals. In both the off-line and on-line case the output space is trained with known associated crack lengths. Once the Gaussian process model is trained, a new output space for which the corresponding crack length or damage state is not known is predicted using the trained Gaussian process model. Concepts are validated through several numerical examples.

[1]  Sankaran Mahadevan,et al.  Stochastic fatigue damage modeling under variable amplitude loading , 2007 .

[2]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[3]  A. Hess,et al.  The Joint Strike Fighter (JSF) PHM concept: Potential impact on aging aircraft problems , 2002, Proceedings, IEEE Aerospace Conference.

[4]  Calyampudi R. Rao The use and interpretation of principal component analysis in applied research , 1964 .

[5]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[6]  J. Newman A crack opening stress equation for fatigue crack growth , 1984 .

[7]  Ilias Maglogiannis,et al.  Neural network-based diagnostic and prognostic estimations in breast cancer microscopic instances , 2006, Medical and Biological Engineering and Computing.

[8]  A. Hess,et al.  Challenges, issues, and lessons learned chasing the "Big P". Real predictive prognostics. Part 1 , 2005, 2005 IEEE Aerospace Conference.

[9]  E. Wolf Fatigue crack closure under cyclic tension , 1970 .

[10]  John F. Mandell,et al.  Comparison of Tensile Fatigue Resistance and Constant Life Diagrams for Several Potential Wind Turbine Blade Laminates , 2009 .

[11]  R. Brook,et al.  Cumulative Damage in Fatigue: A Step towards Its Understanding , 1969 .

[12]  D. Mackay,et al.  Introduction to Gaussian processes , 1998 .

[13]  Jaime Domínguez,et al.  A statistical approach to fatigue life predictions under random loading , 1990 .

[14]  James C. Newman FASTRAN-2: A fatigue crack growth structural analysis program , 1992 .

[15]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[16]  George Vachtsevanos,et al.  Fault prognosis using dynamic wavelet neural networks , 2001, 2001 IEEE Autotestcon Proceedings. IEEE Systems Readiness Technology Conference. (Cat. No.01CH37237).

[17]  Asok Ray,et al.  Fatigue crack growth under variable-amplitude loading: Part II – Code development and model validation , 2001 .

[18]  Asok Ray,et al.  Fatigue crack growth under variable-amplitude loading: Part I – Model formulation in state-space setting , 2001 .

[19]  James C. Newman,et al.  Prediction of Fatigue Crack Growth under Variable-Amplitude and Spectrum Loading Using a Closure Model , 1982 .

[20]  Christopher K. I. Williams Computing with Infinite Networks , 1996, NIPS.

[21]  James A. Harter,et al.  AFGROW Users Guide and Technical Manual , 1999 .