Using deep neural network with small dataset to predict material defects

Hot crack prevention in materials production and processing is an essential prerequisite for welded component safety. The causes of hot cracking can ultimately be attributed to the occurrence of metallurgical effects and to structural loads. More than 140 hot cracking test procedures have hitherto been developed for determining the hot cracking resistance. In principle, they are divided in self-restraint and externally loaded hot cracking tests with diverse process variants. Only some of the hot cracking tests are international standardized. Although various factors are known that encourage or prevent hot cracking, it is often not possible even with defined welding conditions to draw immediate conclusions about the hot cracking resistance of a welded component alone from a metallurgical composition of the base and filler materials. Based on an evaluation of the existing theories relating to hot cracking susceptibility assessment, this study summarizes the major hot cracking test procedures and highlights the application limits of the test procedures by presenting overviews along with explanations. It shows that weld hot cracking tests can generally be used to rank materials, welding consumables, and welding conditions. The evaluation of hot cracking test results and of their transferability among one another and to real components always requires consideration of the close relationships between metallurgy, welding process, and parameters, respectively, and prevailing restraint conditions.

Cold cracking tests—an overview of present technologies and applications

Superalloys and in particular the precipitation hardened Ni-based superalloys have
always been used extensively in the hot sections of jet engines. Large hot structural
engine components with complex geometry have preferably been cast as single piece
components since the large scale vacuum investment casting process became
available about fifty years ago. However, a recent trend is to cast smaller pieces which
can be joined with sheet or forged parts to fabricate structural components. The
rationale for this fabrication strategy is the possibility to save weight by the use of higher
strength wrought material, where geometry allows, and join these wrought parts with
cast material where complex geometry is needed and where the demand for strength is
moderate. One of the major challenges using this strategy is the obvious fact that
numerous welds must be made which requires the fundamental understanding, not
least metallurgical, of how different materials may be joined by specific welding
processes.
The main objective of this research has, for this reason, been to examine and interpret
the weldability of precipitation hardened superalloys from a metallurgical standpoint.
Two newly developed superalloys Allvac® 718PlusTM and Haynes® 282® are compared
with the two well established Alloy 718 and Waspaloy. The understanding of the
influence of secondary phases such as carbides and δ phase in the microstructure was
addressed by systematic hot ductility testing (Gleeble) and by weldability testing
(Varestraint). The effect of secondary phases were also analysed through practical
welding as by electron beam welding (EBW), and by gas tungsten arc welding (GTAW).
The research showed that all the techniques used (Varestraint testing, Gleeble testing,
DSC thermal analysis and welding (GTAW repair and EBW)) in studying the weldability
independently provided important knowledge and most importantly that a combination of
the results from these different techniques were necessary for the understanding of the
weldability of these four alloys. From a microstructural point of view it has been possible
to show that δ phase contrary to what has generally been assumed improves the
weldability due to its ability to inhibit grain growth and to assist in the healing of cracks.
For future research, a new modified weldability testing method was developed where it
is possible to perform Varestraint, Transvarestraint and spot-varestraint testing at ram
speeds from 15 to 300 mm/s using GTAW, plasma arc welding and laser welding.

https://publications.lib.chalmers.se/records/fulltext/140316.pdf

Weldability of Precipitation Hardening Superalloys – Influence of Microstructure

3 FOREWORD 4 CONTENTS 5 LIST OF SYMBOLS 7 ORIGINAL FEATURES OF THIS DISSERTATION 9 INTRODUCTION 11 Chapter 1 GENERAL ASPECTS OF SOLIDIFICATION 14 1.1 Solidification basics 14 1.2 Descriptive classification vs. "Cases" 28 1.3 Growth modes 28 Chapter 2 SOLIDIFICATION RESEARCH IN THE 20 CENTURY 29 2.1 Equilibrium solidification; Case 1 29 2.2 Start of modern solidification theory; Gulliver and Case 2 29 2.3 Scheil during WWII 30 2.4 Bell Laboratories; Burton, Primm & Slichter, Pfann's Cases 31 2.5 University of Toronto;-1950 32 2.6 MIT; Flemings and Mullins & Sekerka 35 2.7 RPI; Savage 36 2.8 Lausanne EPFL; Kurz 39 2.9 David & Vitek 1989; NEGS to EGS transformation 42 2.10 Tokyo University; Koseki 43 2.11 Osaka University; Nishimoto, Mori 44 2.12 St. Petersburg State Polytechnic University 45 2.13 Inverse modeling of temperature field 45 2.14 Paton institute; Demchenkp . 46 2.15 Phase-Field simulation 47 2.16 Bimetallic surfaces: Special phase diagrams and anomalous nano-particles 48 Chapter 3 THE FOUR CASES OF SOLIDIFICATION 49 3.1 Case 1: Equilibrium solidification' ( 49 3.2 Case 2: No diffusion in solid, total mixing in liquid 49 3.3 Case 3: No diffusion in solid, partial diffusion in liquid 50 3.4 Case 4: Splat cooling ' 50 Chapter 4 INTERMEDIATE SUB-CASES v 51 4.1 Sub-Cases below Case 3 51 4.2 Sub-Cases above Case 3: Mullins & Sekerka / Lausanne / Solute Trapping 53 Chapter 5 WELD SOLIDIFICATION CONTINUUM AND ITS MODELING 55 5.1 Rate-Gradient analyses ._, 55 5.2 Geometric morphology-model 55 5.3 Solid solute profile-model: One Case 56 5.4 Weld Solidification Continuum Model Frame a tool for modeling 56 5.5 Discussion of the proposed Model Frame 60 5.6 The melting stage and Melting/ Solidification(M/S-) model 62 5.7 About the Model Frame, Cases, Sub-Cases, Sub-Case Variables and the Lausanne and RPI approaches 65 Chapter 6 EXPERIMENTS ON PURE AND DOPED Cu 67 6.1 Materials and tests 67 6.2 Metallographic observations 71 6.3 Hot cracking 74 6.4 About the experimental method 75 Chapter 7 DISCUSSION 76 Chapter 8 SUMMARY OF THE DISSERTATION 77 REFERENCES 79 APPENDIXES 84 Appendixes 1... 10: No dope, Cu 85 Appendixes 11... 22: B i-dope 98 Appendixes 23...27: La-dope 110 Appendixes 28...31: Li-dope 115 Appendixes 32...33: P-dope 118 Appendixes 34...35 Pb-dope 121 Appendix 36. Ambiguities in the definitions of some central concepts 125 Appendix 37. The dismissal of the cellular dendritic growth 126 Appendix 38. The Melting/Solidification(M/S-) model 127 Appendix 39. Pool Shape 139 Appendix 40. Joining Case 2 to Case 1 with added solid diffusion, Sub-Case 2(-)Ds 141 Appendix 41. Visualization of the Cases, Sub-Cases and operation paths of Cases 2 and 3 from solidification start to its end 142 Appendix 42. The Stagnant Layer and the Concentration Gradient Width 144 Appendix 43. The Lausanneand RPI-approaches at cell centerline 147

/pdf/fusion-weld-metal-solidification-continuum-from-weld-4mrto59tf5.pdf

Fusion weld metal solidification:Continuum from weld interface to centerline

Hot cracks appear when thermal shrinkage together with deformation caused by restraint cannot be accommodated by plastic deformation. This happens during welding to such alloys, which segregate on heating and cooling at near-solidus temperatures, in particular when low-melting and mechanically weak phases form and occur over a wide range of temperatures. To check for susceptibility to the liquation cracking caused by the low-melting, weak phases, hot tensile testing can be used in combination with a thermal cycle resembling that of real welding. This procedure, which can be executed on a Gleeble™1 thermal-mechanical simulator, comprises tensile testing of a number of cylindrical samples at the temperatures below solidus and determining their hot strength and ductility. For measuring of the brittle temperature range (BTR), the nil strength temperature (NST) is determined and used as the peak point, down from which the ductility recovery temperature (DRT) is searched for. The ductility is measured after the tensile test as a reduction in area at fracture. An alternative to the hot tensile test during the simulated welding cycle is the straininduced crack opening (SICO) test, in which a rod-like sample mounted in "cold" copper jaws of the Gleeble is heated by electric current and then compressed till formation of a bulge in its uniformly heated central portion and appearance of cracks due to secondary tensile strain developed along the maximum perimeter of this bulge. Next to the studies of liquation cracking and ductility-dip cracking of the reheat-type, the Gleeble procedures can be also used to determine sensitivity to solidification cracking and for this the samples are melted and solidified in a controlled manner before the hot tensile testing or the SICO testing. The developed routines of the Gleeble testing allow accurate determination of temperatures at which the cracks occur as well as measurement of critical strains to fracture and strain rates which are associated with the hot cracking. At an appropriate geometry of samples and optimum setting of the experiments, the hot cracks generated in the samples have sizes comparable to those that occur in heat-affected zones of real welds or in weld metals.

Testing for Susceptibility to Hot Cracking on Gleeble™ Physical Simulator

The weldability of the modified 316 stainless steel was evaluated by the Gleeble hot ductility test and two hot cracking test methods (Varestraint and Sigmajig). The fusion zone and weld metal heat-affected zone (HAZ) hot cracking susceptibilities of the modified 316 stainless steel are similar to conventional fully austenitic 316 stainless steels and greater than the conventional 316 materials that have a primary ferritic solidification mode. The Gleeble hot ductility test results correlate with the base metal HAZ hot cracking results from the Varestraint test and indicate that the modified 316 materials show a considerably higher base metal HAZ hot cracking susceptibility as contrasted to nuclear grade 316 stainless steels. Varestraint test results and Sigmajig test results and Sigmajig test results for the tested materials showed good correlations. The sensitivity of the base metal to HAZ liquation cracking has been successfully predicted by using a newly developed hot ductility criterion, the ratio of ductility recovery (RDR). An excellent correlation between the Gleeble Test criterion RDR and the Varestraint Test criteria (TCL, MCL and CHL) has been found.

T.P.S. Gill

Papers

Hot ductility and hot cracking behavior of modified 316 stainless steels designed for high-temperature service