Study of correlation between the steels susceptibility to hydrogen embrittlement and hydrogen thermal desorption spectroscopy using artificial neural network

Steels are the most used structural material in the world, and hydrogen content and localization within the microstructure play an important role in its properties, namely inducing some level of embrittlement. The characterization of the steels susceptibility to hydrogen embrittlement (HE) is a complex task requiring always a broad and multidisciplinary approach. The target of the present work is to introduce the artificial neural network (ANN) computing system to predict the hydrogen-induced mechanical properties degradation using the hydrogen thermal desorption spectroscopy (TDS) data of the studied steel. Hydrogen sensitivity parameter (HSP) calculated from the reduction of elongation to fracture caused by hydrogen was linked to the corresponding hydrogen thermal desorption spectra measured for austenitic, ferritic, and ferritic-martensitic steel grades. Correlation between the TDS input data and HSP output data was studied using two ANN models. A correlation of 98% was obtained between the experimentally measured HSP values and HSP values predicted using the developed densely connected layers ANN model. The performance of the developed ANN models is good even for never-before-seen steels. The ANN-coupled system based on the TDS is a powerful tool in steels characterization especially in the analysis of the steels susceptibility to HE.

[1]  F. Goodwin,et al.  Hydrogen Solubility Effects in Galvanized Advanced High Strength Steels , 2016 .

[2]  Barthélémy.  EFFECTS OF PURITY AND PRESSURE ON THE HYDROGEN EMBRITTLEMENT OF STEELS AND OTHER METALLIC MATERIALS , 2009 .

[3]  C. S. Marchi,et al.  Hydrogen compatibility of austenitic stainless steel tubing and orbital tube welds , 2014 .

[4]  Robert LIN,et al.  NOTE ON FUZZY SETS , 2014 .

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

[6]  Yaochu Jin,et al.  Enhancing classification of mass spectrometry imaging data with deep neural networks , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[7]  W. Świątnicki,et al.  Nanocrystalline Steels’ Resistance to Hydrogen Embrittlement , 2015 .

[8]  G. Benamati,et al.  Effect of hydrogen on the ductility reduction of F82H martensitic steel after different heat treatments , 2001 .

[9]  P. Sofronis,et al.  Mechanics of the hydrogendashdislocationdashimpurity interactions-I. Increasing shear modulus , 1995 .

[10]  Young Hwan Kim,et al.  Hydrogen Embrittlement Behavior of 430 and 445NF Ferritic Stainless Steels , 2013, Metallurgical and Materials Transactions A.

[11]  J. Clum.  The role of hydrogen in dislocation generation in iron alloys , 1975 .

[12]  E. Quadrini.  Study of the effect of heat treatment on hydrogen embrittlement of AISI 4340 steel , 1989 .

[13]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[14]  H. K. Birnbaum,et al.  Hydrogen embrittlement of Nb I—Macroscopic behavior at low temperatures☆ , 1977 .

[15]  Dragan A. Cirovic,et al.  Feed-forward artificial neural networks : applications to spectroscopy , 1997 .

[16]  K. Sieradzki,et al.  Stress-corrosion cracking , 1987 .

[17]  Tohid Azimzadegan,et al.  An artificial neural-network model for impact properties in X70 pipeline steels , 2012, Neural Computing and Applications.

[18]  Shuai Li,et al.  Mining λ-Maximal Cliques from a Fuzzy Graph , 2016 .

[19]  Yuriy Yagodzinskyy,et al.  Role of retained austenite in hydrogen trapping and hydrogen-assisted fatigue fracture of high-strength steels , 2019, Materials Science and Engineering: A.

[20]  H. Birnbaum,et al.  Effects of hydrogen and carbon on thermally activated deformation in nickel , 1992 .

[21]  H. Remes,et al.  Hydrogen effects on mechanical properties of 18% Cr ferritic stainless steel , 2017 .

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

[23]  Petros Athanasios Sofronis,et al.  Hydrogen-enhanced localized plasticity—a mechanism for hydrogen-related fracture , 1993 .

[24]  M. Nakamura,et al.  Hydrogen thermal desorption relevant to delayed-fracture susceptibility of high-strength steels , 2001 .

[25]  董瀚,et al.  Hydrogen Absorption and Desorption during Heat Treatment of AISI 4140 Steel , 2014 .

[26]  D. V. Rooyen.  Stress Corrosion Cracking , 1960 .

[27]  François Chollet,et al.  Deep Learning with Python , 2017 .

[28]  S. Lynch.  Hydrogen embrittlement phenomena and mechanisms , 2012 .

[29]  Hideo Tanaka,et al.  Fuzzy regression analysis using neural networks , 1992 .

[30]  T. Thankachan,et al.  Artificial neural network to predict the degraded mechanical properties of metallic materials due to the presence of hydrogen , 2017 .

[31]  J. Furtado,et al.  Fatigue crack initiation and growth in a CrMo steel under hydrogen pressure , 2015 .

[32]  A. R. Troiano.  The Role of Hydrogen and Other Interstitials in the Mechanical Behavior of Metals , 2016, Metallography, Microstructure, and Analysis.

[33]  H. Birnbaum,et al.  Hydrogen embrittlement of α titanium: In situ tem studies , 1988 .

[34]  N. Lewis,et al.  Stress Corrosion Crack Growth Rate Testing and Analytical Electron Microscopy of Alloy 600 as a Function of Pourbaix Space and Microstructure , 2000 .

[35]  B. M. Oliver,et al.  Surprisingly Large Generation and Retention of Helium and Hydrogen in Pure Nickel Irradiated at High Temperatures and High Neutron Exposures , 2004 .

[36]  R. Nishimura,et al.  On the Stress Corrosion Cracking and Hydrogen Embrittlement Behavior of Austenitic Stainless Steels in Boiling Saturated Magnesium Chloride Solutions , 2012 .

[37]  E. Izhikevich,et al.  Weakly connected neural networks , 1997 .

[38]  R. A. Oriani,et al.  Equilibrium aspects of hydrogen-induced cracking of steels , 1974 .

[39]  H. Hänninen,et al.  Hydrogen Sensitivity of Different Advanced High Strength Microstructures (HYDRAMICROS) , 2011 .

[40]  R. Ray,et al.  ‘Back‐annealing’ of cold rolled steels through recovery and/or partial recrystallisation , 2011 .

[41]  Doreswamy,et al.  Performance Analysis Of Neural Network Models For Oxazolines And Oxazoles Derivatives Descriptor Dataset , 2013, ArXiv.

[42]  N. Lewis,et al.  The Mechanism and Modeling of Intergranular Stress Corrosion Cracking of Nickel-Chromium-Iron Alloys Exposed to high Purity Water , 2005 .

[43]  S. Lynch.  Metallographic contributions to understanding mechanisms of environmentally assisted cracking , 1989 .

[44]  Y. Sakamoto,et al.  Effect of Heat Treated Structure on Diffusion of Hydrogen in Martensitic Type 403 Stainless Steel , 1977 .

[45]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[46]  Nikhil Ketkar,et al.  Deep Learning with Python , 2017 .

[47]  M. Nagumo.  Hydrogen related failure of steels – a new aspect , 2004 .

[48]  Shuai Li,et al.  Dynamic Fuzzy Logic Control of Genetic Algorithm Probabilities , 2014, J. Comput..

[49]  T. Lui,et al.  Decrease in Hydrogen Embrittlement Susceptibility of 10B21 Screws by Bake Aging , 2016 .