Machine learning based fatigue life prediction with effects of additive manufacturing process parameters for printed SS 316L

Abstract In aerospace engineering, many additive manufacturing (AM) metal parts subject to fatigue loadings, resulting in their fatigue failure. Therefore, it is essential to develop an advanced approach for fatigue issues. Although some theoretical methods are used for fatigue analysis of AM metal parts, their implementations are time-consuming. Furthermore, these methods cannot directly consider the effects of AM parameters. In this study, a platform is developed for a data-driven analysis of continuum damage mechanics (CDM)-based fatigue life prediction of AM stainless steel (SS) 316L, in which the effects of AM process parameters (including laser power P, scan speed v, hatch space h, powder layer thickness t) are considered. Here, three typical ML models: an artificial neural network (ANN), a random forest (RF), and a support vector machine (SVM), are trained effectively by a database produced by the CDM technique, and then further comparisons are made between the predicted results and published experimental data to verify the proposed platform. Finally, detailed parametric studies using the ML models are conducted to investigate some of the significant characteristics.

[1]  Markus Bambach,et al.  Study of the effect of heat treatment on fatigue crack growth behaviour of 316L stainless steel produced by selective laser melting , 2018 .

[2]  Tadeusz Łagoda,et al.  Lifetime of semi-ductile materials through the critical plane approach , 2014 .

[3]  W. Schneller,et al.  Effect of HIP Treatment on Microstructure and Fatigue Strength of Selectively Laser Melted AlSi10Mg , 2019, Journal of Manufacturing and Materials Processing.

[4]  T. Uchida,et al.  Influence of defects, surface roughness and HIP on the fatigue strength of Ti-6Al-4V manufactured by additive manufacturing , 2018, International Journal of Fatigue.

[5]  Luca Susmel,et al.  A critical distance/plane method to estimate finite life of notched components under variable amplitude uniaxial/multiaxial fatigue loading , 2012 .

[6]  Andy Fourie,et al.  An intelligent modelling framework for mechanical properties of cemented paste backfill , 2018, Minerals Engineering.

[7]  Jixiong Zhang,et al.  Compaction property prediction of mixed gangue backfill materials using hybrid intelligence models: A new approach , 2020, Construction and Building Materials.

[8]  Nima Shamsaei,et al.  Surface roughness effects on the fatigue strength of additively manufactured Ti-6Al-4V , 2018, International Journal of Fatigue.

[9]  David Hardacre,et al.  High cycle fatigue and ratcheting interaction of laser powder bed fusion stainless steel 316L: Fracture behaviour and stress-based modelling , 2019, International Journal of Fatigue.

[10]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[11]  Markus J. Buehler,et al.  De novo composite design based on machine learning algorithm , 2018 .

[12]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[13]  Waseem Haider,et al.  Additively manufactured 316L stainless steel with improved corrosion resistance and biological response for biomedical applications , 2019, Additive Manufacturing.

[14]  Filippo Berto,et al.  Effect of post-treatments on the fatigue behaviour of 316L stainless steel manufactured by laser powder bed fusion , 2019, International Journal of Fatigue.

[15]  Ankit Agrawal,et al.  An online tool for predicting fatigue strength of steel alloys based on ensemble data mining , 2018 .

[16]  S. Beretta,et al.  Fatigue strength assessment of “as built” AlSi10Mg manufactured by SLM with different build orientations , 2020 .

[17]  Yang Shen,et al.  Phase-field modeling and machine learning of electric-thermal-mechanical breakdown of polymer-based dielectrics , 2019, Nature Communications.

[18]  Michael Kaliske,et al.  Crack propagation in pneumatic tires: Continuum mechanics and fracture mechanics approaches , 2012 .

[19]  Uwe Zerbst,et al.  Review on fracture and crack propagation in weldments - A fracture mechanics perspective , 2014 .

[20]  Meng Zhang,et al.  Predictive models for fatigue property of laser powder bed fusion stainless steel 316L , 2018 .

[21]  Grace X. Gu,et al.  Machine learning for composite materials , 2019, MRS Communications.

[22]  S. Carmignato,et al.  Low- and high-cycle fatigue resistance of Ti-6Al-4V ELI additively manufactured via selective laser melting: Mean stress and defect sensitivity , 2018 .

[23]  Murat Inalpolat,et al.  Wind Turbine Blade Damage Detection Using Supervised Machine Learning Algorithms , 2017 .

[24]  Bernhard Mueller,et al.  Additive Manufacturing Technologies – Rapid Prototyping to Direct Digital Manufacturing , 2012 .

[25]  Zhixin Zhan,et al.  Development of a novel fatigue damage model with AM effects for life prediction of commonly-used alloys in aerospace , 2019, International Journal of Mechanical Sciences.

[26]  Zhixin Zhan,et al.  Continuum damage mechanics-based approach to the fatigue life prediction for 7050-T7451 aluminum alloy with impact pit , 2016 .

[27]  A. Montagne,et al.  Mechanical and corrosion characterization of industrially treated 316L stainless steel surfaces , 2020 .

[28]  Meng Zhang,et al.  Fatigue and fracture behaviour of laser powder bed fusion stainless steel 316L: Influence of processing parameters , 2017 .

[29]  Xiaoyan Zeng,et al.  Fatigue performances of selective laser melted Ti-6Al-4V alloy: Influence of surface finishing, hot isostatic pressing and heat treatments , 2019, International Journal of Fatigue.

[30]  Petrus Christiaan Pistorius,et al.  Fatigue life prediction for AlSi10Mg components produced by selective laser melting , 2019, International Journal of Fatigue.

[31]  Zijian Mao,et al.  Remaining Useful Life Estimation of Aircraft Engines Using a Modified Similarity and Supporting Vector Machine (SVM) Approach , 2017 .

[32]  Stephen C. H. Leung,et al.  Vertical bagging decision trees model for credit scoring , 2010, Expert Syst. Appl..

[33]  Koichi Maekawa,et al.  Remaining fatigue life assessment of in-service road bridge decks based upon artificial neural networks , 2018, Engineering Structures.

[34]  Andrey Koptyug,et al.  Additive manufacturing of 316L stainless steel by electron beam melting for nuclear fusion applications , 2017 .

[35]  Frank Walther,et al.  Effects of Defects in Laser Additive Manufactured Ti-6Al-4V on Fatigue Properties , 2014 .

[36]  A. Fatemi,et al.  Fatigue of additive manufactured Ti-6Al-4V, Part II: The relationship between microstructure, material cyclic properties, and component performance , 2020 .

[37]  Du-Rim Eo,et al.  Inclusion evolution in additive manufactured 316L stainless steel by laser metal deposition process , 2018, Materials & Design.

[38]  Sungzoon Cho,et al.  Approximating support vector machine with artificial neural network for fast prediction , 2014, Expert Syst. Appl..

[39]  Chaofang Dong,et al.  Bio-functional and anti-corrosive 3D printing 316L stainless steel fabricated by selective laser melting , 2018, Materials & Design.

[40]  Wenku Shi,et al.  Rubber fatigue life prediction using a random forest method and nonlinear cumulative fatigue damage model , 2020, Journal of Applied Polymer Science.

[41]  Duanjun Xu,et al.  Damage mode identification of adhesive composite joints under hygrothermal environment using acoustic emission and machine learning , 2019, Composite Structures.

[42]  Abhishek Yadav,et al.  pplication of artificial neural network for predicting crack growth irection in multiple cracks geometry , 2015 .

[43]  Kazem Reza Kashyzadeh,et al.  Fatigue behavior prediction and analysis of shot peened mild carbon steels , 2018, International Journal of Fatigue.

[44]  A. du Plessis,et al.  Killer notches: The effect of as-built surface roughness on fatigue failure in AlSi10Mg produced by laser powder bed fusion , 2020, Additive Manufacturing.

[45]  Yi Zhang,et al.  Modeling of solidification microstructure evolution in laser powder bed fusion fabricated 316L stainless steel using combined computational fluid dynamics and cellular automata , 2019, Additive Manufacturing.

[46]  Chola Elangeswaran,et al.  Microstructural analysis and fatigue crack initiation modelling of additively manufactured 316L after different heat treatments , 2020 .

[47]  Li Ma,et al.  A comparison of random forest and support vector machine approaches to predict coal spontaneous combustion in gob , 2019, Fuel.

[48]  Zhiyong Chen,et al.  Fatigue life prediction for vibration isolation rubber based on parameter-optimized support vector machine model , 2018, Fatigue & Fracture of Engineering Materials & Structures.

[49]  Hamid Eskandari-Naddaf,et al.  Linear and non-linear SVM prediction for fresh properties and compressive strength of high volume fly ash self-compacting concrete , 2020 .

[50]  Qingchun Meng,et al.  A damage mechanics approach to fretting fatigue life prediction with consideration of elastic–plastic damage model and wear , 2015 .

[51]  F. Berto,et al.  Fatigue strength of blunt V-notched specimens produced by selective laser melting of Ti-6Al-4V , 2017, Theoretical and Applied Fracture Mechanics.

[52]  V. Vishwakarma,et al.  Biocompatible Zirconia‐Coated 316 stainless steel with anticorrosive behavior for biomedical application , 2018, Ceramics International.

[53]  V. Rodriguez-Galiano,et al.  Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines , 2015 .

[54]  L. Malcher,et al.  An improved damage evolution law based on continuum damage mechanics and its dependence on both stress triaxiality and the third invariant , 2014 .

[55]  Fakhreddine Dammak,et al.  One-equation integration algorithm of a generalized quadratic yield function with Chaboche non-linear isotropic/kinematic hardening , 2015 .

[56]  Do Kyun Kim,et al.  A simplified method to predict fatigue damage of TTR subjected to short-term VIV using artificial neural network , 2018, Adv. Eng. Softw..

[57]  William E. Frazier,et al.  Metal Additive Manufacturing: A Review , 2014, Journal of Materials Engineering and Performance.

[58]  Moncef L. Nehdi,et al.  Machine learning prediction of mechanical properties of concrete: Critical review , 2020, Construction and Building Materials.

[59]  Pierre Charrier,et al.  Fatigue life prediction of rubber-like materials under multiaxial loading using a continuum damage mechanics approach: Effects of two-blocks loading and R ratio , 2012 .

[60]  Mario Guagliano,et al.  On the fatigue strength enhancement of additive manufactured AlSi10Mg parts by mechanical and thermal post-processing , 2018 .

[61]  Torgeir Welo,et al.  Fatigue of additively manufactured 316L stainless steel: The influence of porosity and surface roughness , 2019, Fatigue & Fracture of Engineering Materials & Structures.

[62]  Diego A. Gómez-Gualdrón,et al.  Structure-Mechanical Stability Relations of Metal-Organic Frameworks via Machine Learning , 2019, Matter.

[63]  Mostafa Yakout,et al.  A study of thermal expansion coefficients and microstructure during selective laser melting of Invar 36 and stainless steel 316L , 2018, Additive Manufacturing.

[64]  R. Poprawe,et al.  Laser additive manufacturing of metallic components: materials, processes and mechanisms , 2012 .

[65]  Frank Walther,et al.  Microstructural damage and fracture mechanisms of selective laser melted Al-Si alloys under fatigue loading , 2020 .

[66]  L. Airoldi,et al.  A continuum damage mechanics model for pit-to-crack transition in AA2024-T3 , 2015 .

[67]  D. Varas,et al.  The influence of laminate stacking sequence on ballistic limit using a combined Experimental/FEM/Artificial Neural Networks (ANN) methodology , 2018 .

[68]  P. Withers,et al.  The effect of manufacturing defects on the fatigue life of selective laser melted Ti-6Al-4V structures , 2020 .

[69]  Yanchun Zhang,et al.  Epileptic seizure detection in EEG signals using tunable-Q factor wavelet transform and bootstrap aggregating , 2016, Comput. Methods Programs Biomed..

[70]  Hui Li,et al.  The State of the Art of Data Science and Engineering in Structural Health Monitoring , 2019, Engineering.

[71]  N. A. Fellows,et al.  Artificial neural network for random fatigue loading analysis including the effect of mean stress , 2018, International Journal of Fatigue.

[72]  S. S. Matin,et al.  Variable selection and prediction of uniaxial compressive strength and modulus of elasticity by random forest , 2017, Appl. Soft Comput..

[73]  Guian Qian,et al.  Very-high-cycle fatigue behavior of AlSi10Mg manufactured by selective laser melting: Effect of build orientation and mean stress , 2020 .

[74]  Ehsan Toyserkani,et al.  A critical review of powder-based additive manufacturing of ferrous alloys: Process parameters, microstructure and mechanical properties , 2018 .

[75]  Reza Hojjati-Talemi,et al.  Prediction of fretting fatigue crack initiation in double lap bolted joint using Continuum Damage Mechanics , 2015 .

[76]  Dallas N. Little,et al.  A continuum damage mechanics framework for modeling micro-damage healing , 2012 .

[77]  Wei Wang,et al.  Selective laser melting of AlSi10Mg alloy: Process optimisation and mechanical properties development , 2015, Materials & Design (1980-2015).

[78]  P. Mengucci,et al.  Fatigue life and microstructure of additive manufactured Ti6Al4V after different finishing processes , 2019, Materials Science and Engineering: A.

[79]  Stefano Beretta,et al.  Fatigue properties of AlSi10Mg obtained by additive manufacturing: Defect-based modelling and prediction of fatigue strength , 2017 .