Erosion modelling using Bayesian regulated artificial neural networks

Modelling of the high temperature erosion behaviour of Ni-base alloys using artificial neural networks (ANNs) is presented. Two scenarios have been used: (i) a simple equation-based model and (ii) a comprehensive dataset looking at erosion as a function of particle size, velocity, impact angle and temperature. Common problems associated with ANNs are discussed within the context of erosion modelling. It has been found that the use of multilayer perceptron artificial neural networks for modelling erosion gave unreliable results when trained with traditional algorithms. The more recent Bayesian regularisation algorithm however has proved very successful, yielding both high Pearsonian correlation coefficients (r>0.95) and accuracies averaging better than 90%.

[1]  G. Sundararajan.  The depth of plastic deformation beneath eroded surfaces: The influence of impact angle and velocity, particle shape and material properties , 1991 .

[2]  W. Tabakoff,et al.  Some effects of temperature on the erosion of metals , 1978 .

[3]  G. Sundararajan.  An analysis of the erosion-oxidation interaction mechanisms , 1991 .

[4]  Salvador Pintos,et al.  Artificial neural network modeling of atmospheric corrosion in the MICAT project , 2000 .

[5]  J. Nicholls,et al.  Modelling the influence of surface oxidation on high temperature erosion , 1995 .

[6]  A. Levy,et al.  Erosion-corrosion of 1018 steel eroded at low velocities by CFBC bed material , 1992 .

[7]  Yung Y. Liu,et al.  Oxidation-erosion of metals and alloys: Models, verification and prediction☆ , 1988 .

[8]  Eon O'Mongain,et al.  Singular value decomposition in multispectral radiometry , 1992 .

[9]  Widen Tabakoff,et al.  High temperature erosion study of INCO 600 metal , 1983 .

[10]  D. J. Stephenson,et al.  Monte Carlo modelling of erosion processes , 1995 .

[11]  Robert A. Cottis,et al.  Phenomenological modelling of atmospheric corrosion using an artificial neural network , 1999 .

[12]  P. Crook,et al.  The erosion properties of alloys for the chemical processing industries , 1991 .

[13]  D. Griffin,et al.  The development of a three-dimensional finite element model for solid particle erosion on an alumina scale/MA956 substrate , 2004 .

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

[15]  J. Nicholls,et al.  Modelling erosive wear , 1993 .

[16]  F. Pettit,et al.  Mechanisms in the simultaneous erosion-oxidation attack of nickel and cobalt at high temperature , 1987 .

[17]  Y. Cheng,et al.  Artificial neural network technology for the data processing of on-line corrosion fatigue crack growth monitoring , 1999 .

[18]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[19]  Nigel Maxwell,et al.  Probabilistic modelling of CO2 corrosion laboratory data using neural networks , 2001 .

[20]  J. Stringer,et al.  Observations on the role of oxide scales in high-temperature erosion-corrosion of alloys , 1986 .

[21]  Walter Bogaerts,et al.  SCC susceptibility analysis of stainless steels in nuclear reactor water: a neural network and expert system approach , 1995, Fuzzy Sets Syst..

[22]  Room temperature erosion behaviour of 304, 316 and 410 stainless steels , 1991 .

[23]  G. Mihalakakou,et al.  The total solar radiation time series simulation in Athens, using neural networks , 2000 .

[24]  F. Pettit,et al.  Some principal mechanisms in the simultaneous erosion and corrosion attack of metals at high temperatures , 1991 .

[25]  S. Bahadur,et al.  High-temperature erosion of Haynes and Waspaloy: effect of temperature and erosion mechanisms , 1995 .

[26]  Phil Picton,et al.  Introduction to neural networks , 1994 .

[27]  S. J Gartland,et al.  Neural network methods for corrosion data reduction , 1999 .