Improvement of fracture toughness of directionally solidified Nb-silicide in situ composites using artificial neural network

Abstract An artificial neural network (ANN) was employed to investigate the fracture toughness of directionally solidified Nb-silicide in situ composites. The microstructures of the composites were quantified with a metallographic statistics method. Both microstructural features and composition of the constituent phases were used as the candidate inputs of the artificial neural network model while the fracture toughness of the composites was employed as the outputs. The effects of different inputs on the fracture toughness were investigated and evaluated by the trained network. When all of the candidate inputs were taken into account, outstanding performance of the neural network was achieved. A new alloy with optimized microstructure and fracture toughness was produced according to the prediction of the model. The fracture toughness of the new alloy reached 19.5 MPa m 1/2 , which was 25.5% higher than the best inputted alloy (15.5 MPa m 1/2 ).

[1]  D. Davidson,et al.  Delineating brittle-phase embrittlement and ductile-phase toughening in Nb-based in-situ composites , 2001 .

[2]  Sandhya Samarasinghe,et al.  Neural Networks for predicting fracture toughness of individual wood samples , 2007 .

[3]  K. Chan.  Alloying effects on the fracture toughness of Nb-based silicides and Laves phases , 2005 .

[4]  K. Chan.  A computational approach to designing ductile Nb-Ti-Cr-Al solid-solution alloys , 2001 .

[5]  M. Ashby,et al.  Flow characteristics of highly constrained metal wires , 1989 .

[6]  Maysam F. Abbod,et al.  Hybrid modelling of aluminium–magnesium alloys during thermomechanical processing in terms of physically-based, neuro-fuzzy and finite element models , 2003 .

[7]  Y. Kimura,et al.  Fracture toughness and high temperature strength of unidirectionally solidified Nb–Si binary and Nb–Ti–Si ternary alloys , 2006 .

[8]  A. Bahrami,et al.  A new method in prediction of TCP phases formation in superalloys , 2005 .

[9]  Shubhabrata Datta,et al.  Soft computing techniques in advancement of structural metals , 2013 .

[10]  Michael Ortiz,et al.  A three-dimensional analysis of crack trapping and bridging by tough particles , 1991 .

[11]  Ali Reza Eivani,et al.  Application of artificial neural networks to predict the grain size of nano-crystalline nickel coatings , 2009 .

[12]  H. M. Hosseini,et al.  Using genetic algorithm and artificial neural network analyses to design an Al–Si casting alloy of minimum porosity , 2006 .

[13]  J. Lewandowski,et al.  Ultrahigh-Temperature Nb-Silicide-Based Composites , 2003 .

[14]  S. Al-Alawi,et al.  Prediction of fracture toughness using artificial neural networks (ANNs) , 1997 .

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

[16]  B. Bewlay,et al.  A review of very-high-temperature Nb-silicide-based composites , 2003 .

[17]  K. Chan.  Alloying effects on fracture mechanisms in Nb-based intermetallic in-situ composites , 2002 .

[18]  J. Y. Kang,et al.  Application of artificial neural network for predicting plain strain fracture toughness using tensile test results , 2006 .

[19]  Zhila Amirzadeh,et al.  Development a multi-layer perceptron artificial neural network model to estimate the Vickers hardness of Mn–Ni–Cu–Mo austempered ductile iron , 2012 .

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

[21]  A. Bahrami,et al.  Prediction of porosity percent in Al–Si casting alloys using ANN , 2006 .

[22]  E. Essadiqi,et al.  Development and experimental validation of a neural network model for prediction and analysis of the strength of bainitic steels , 2012 .