Intelligent Modeling Combining Adaptive Neuro Fuzzy Inference System and Genetic Algorithm for Optimizing Welding Process Parameters

Modified 9Cr-1Mo ferritic steel is used as a structural material for steam generator components of power plants. Generally, tungsten inert gas (TIG) welding is preferred for welding of these steels in which the depth of penetration achievable during autogenous welding is limited. Therefore, activated flux TIG (A-TIG) welding, a novel welding technique, has been developed in-house to increase the depth of penetration. In modified 9Cr-1Mo steel joints produced by the A-TIG welding process, weld bead width, depth of penetration, and heat-affected zone (HAZ) width play an important role in determining the mechanical properties as well as the performance of the weld joints during service. To obtain the desired weld bead geometry and HAZ width, it becomes important to set the welding process parameters. In this work, adaptative neuro fuzzy inference system is used to develop independent models correlating the welding process parameters like current, voltage, and torch speed with weld bead shape parameters like depth of penetration, bead width, and HAZ width. Then a genetic algorithm is employed to determine the optimum A-TIG welding process parameters to obtain the desired weld bead shape parameters and HAZ width.     

Effect of Arc Welding Processes on the Weld Attributes of Type 316LN Stainless Steel Weld joint

The present study aims at understanding the effect of various arc welding processes on the evolution of microstructure, mechanical properties, residual stresses and distortion in 9 mm thick type 316LN austenitic stainless steel weld joints. Weld joints of type 316LN stainless steel were fabricated by three different arc welding processes which were commonly employed in the nuclear industry. All the weld joints passed radiographic examination. Microstructural characterization was done using optical and scanning electron microscope. Volume fraction of δ-ferrite was lowest in the A-TIG weld joint. The A-TIG welded joint exhibited adequate strength and maximum impact toughness values in comparison to that of weld joints made by SMAW and FCAW processes. The A-TIG weld joint was found to exhibit lowest residual stresses and distortion compared to that of other welding processes. This was attributed to lower weld metal volume and hence reduced shrinkage in the A-TIG weld joint compared to that of weld joints made by FCAW and SMAW processes which involved v-groove with filler metal addition. Therefore, type 316LN stainless steel A-TIG weld joint consisting of lower δ-ferrite, adequate strength, high impact toughness, lower residual stresses and distortion was suited better for elevated temperature service compared to that of SMAW and FCAW weld joints.     

Adaptive Neuro-Fuzzy Inference System (ANFIS)-Based Models for Predicting the Weld Bead Width and Depth of Penetration from the Infrared Thermal Image of the Weld Pool

Type 316 LN stainless steel is the major structural material used in the construction of nuclear reactors. Activated flux tungsten inert gas (A-TIG) welding has been developed to increase the depth of penetration because the depth of penetration achievable in single-pass TIG welding is limited. Real-time monitoring and control of weld processes is gaining importance because of the requirement of remoter welding process technologies. Hence, it is essential to develop computational methodologies based on an adaptive neuro fuzzy inference system (ANFIS) or artificial neural network (ANN) for predicting and controlling the depth of penetration and weld bead width during A-TIG welding of type 316 LN stainless steel. In the current work, A-TIG welding experiments have been carried out on 6-mm-thick plates of 316 LN stainless steel by varying the welding current. During welding, infrared (IR) thermal images of the weld pool have been acquired in real time, and the features have been extracted from the IR thermal images of the weld pool. The welding current values, along with the extracted features such as length, width of the hot spot, thermal area determined from the Gaussian fit, and thermal bead width computed from the first derivative curve were used as inputs, whereas the measured depth of penetration and weld bead width were used as output of the respective models. Accurate ANFIS models have been developed for predicting the depth of penetration and the weld bead width during TIG welding of 6-mm-thick 316 LN stainless steel plates. A good correlation between the measured and predicted values of weld bead width and depth of penetration were observed in the developed models. The performance of the ANFIS models are compared with that of the ANN models.     

Intelligent Modeling Using Adaptive Neuro Fuzzy Inference System (ANFIS) for Predicting Weld Bead Shape Parameters During A-TIG Welding of Reduced Activation Ferritic-Martensitic (RAFM) Steel

Reduced-activated ferritic-martensitic steels are considered to be the prime candidate for structural material of the fusion power plant reactor design. Tungsten inert gas (TIG) welding is preferred for welding of those structural materials. However, the depth of penetration achievable during autogenous TIG welding is very limited and hence productivity is poor. Therefore, activated-flux tungsten inert gas (A-TIG) welding, a new variant of TIG welding process has been developed in-house to increase the depth of penetration in single pass welding. In structural materials produced by A-TIG welding process, weld bead width, depth of penetration and HAZ width decide the mechanical properties and in turn the performance of the weld joints during service. To obtain the desired weld bead geometry, HAZ width and make a reliable quality weld, it becomes important to develop predictive tools using soft computing techniques. In this work, adaptive neuro fuzzy inference system is used to develop independent models correlating the welding parameters like current, voltage and torch speed with bead shape parameters like weld bead width, depth of penetration, and HAZ width. During ANFIS modeling, various membership functions were used. Triangular membership function provided the minimum RMS error for prediction and hence, ANFIS model with triangular membership functions were chosen for predicting for weld bead shape parameters as a function of welding process parameters.     

A Comparison of Creep Rupture Strength of Ferritic/Austenitic Dissimilar Weld Joints of Different Grades of Cr-Mo Ferritic Steels

Evaluations of creep rupture properties of dissimilar weld joints of 2.25Cr-1Mo, 9Cr-1Mo, and 9Cr-1MoVNb steels with Alloy 800 at 823 K were carried out. The joints were fabricated by a fusion welding process employing an INCONEL 182 weld electrode. All the joints displayed lower creep rupture strength than their respective ferritic steel base metals, and the strength reduction was greater in the 2.25Cr-1Mo steel joint and less in the 9Cr-1Mo steel joint. Failure location in the joints was found to shift from the ferritic steel base metal to the intercritical region of the heat-affected zone (HAZ) of the ferritic steel (type IV cracking) with the decrease in stress. At still lower stresses, the failure in the joints occurred at the ferritic/austenitic weld interface. The stress-life variation of the joints showed two-slope behavior and the slope change coincided with the occurrence of ferritic/austenitic weld interface cracking. Preferential creep cavitation in the soft intercritical HAZ induced type IV failure, whereas creep cavitation at the interfacial particles induced ferritic/austenitic weld interface cracking. Micromechanisms of the type IV failure and the ferritic/austenitic interface cracking in the dissimilar weld joint of the ferritic steels and relative cracking susceptibility of the joints are discussed based on microstructural investigation, mechanical testing, and finite element analysis (FEA) of the stress state across the joint.     

An assessment of creep deformation and fracture behavior of 2.25Cr-1Mo similar and dissimilar weld joints

The evaluation of the creep deformation and fracture behavior of a 2.25Cr-1Mo steel base metal, a 2.25Cr-1Mo/2.25Cr-1Mo similar weld joint, and a 2.25Cr-1Mo/Alloy 800 dissimilar weld joint at 823 K over a stress range of 90 to 250 MPa has been carried out. The specimens for creep testing were taken from single-V weld pads fabricated by a shielded metal arc-welding process using 2.25Cr-1Mo steel (for similar-joint) and INCONEL 182 (for dissimilar-joint) electrodes. The weld pads were subsequently given a postweld heat treatment (PWHT) of 973 K for 1 hour. The microstructure and microhardness of the weld joints were evaluated in the as-welded, postweld heat-treated, and creep-tested conditions. The heat-affected zone (HAZ) of similar weld joint consisted of bainite in the coarse-prior-austenitic-grain (CPAG) region near the fusion line, followed by bainite in the fine-prior-austenitic-grain (FPAG) and intercritical regions merging with the unaffected base metal. In addition to the HAZ structures in the 2.25Cr-1Mo steel, the dissimilar weld joint displayed a definite INCONEL/2.25Cr-1Mo weld interface structure present either as a sharp line or as a diffuse region. A hardness trough was observed in the intercritical region of the HAZ in both weld joints, while a maxima in hardness was seen at the weld interface of the dissimilar weld joint. Both weld joints exhibited significantly lower rupture lives compared to the 2.25Cr-1Mo base metal. The dissimilar weld joint exhibited poor rupture life compared to the similar weld joint, at applied stresses lower than 130 MPa. In both weld joints, the strain distribution across the specimen gage length during creep testing varied significantly. During creep testing, localization of deformation occurred in the intercritical HAZ. In the similar weld joint, at all stress levels investigated, and in the dissimilar weld joint, at stresses ≥150 MPa, the creep failure occurred in the intercritical HAZ. The fracture occurred by transgranular mode with a large number of dimples. At stresses below 150 MPa, the failure in the dissimilar weld joint occurred in the CPAG HAZ near to the weld interface. The failure occurred by extensive intergranular creep cavity formation.     

Influence of high-temperature exposure on the microstructure and mechanical properties of dissimilar metal welds between modified 9Cr-1Mo steel and alloy 800

Transition joints between ferritic steel and austenitic stainless steel are commonly encountered in high-temperature components of power plants. Service failures in these are known to occur as a result, mainly, of thermal stresses due to expansion coefficient differentials. In order to mitigate the problem, a trimetallic configuration involving an intermediate piece of a material such as Alloy 800 between the ferritic and austenitic steels has been suggested. In our work, modified 9Cr-1Mo steel and 316LN stainless steel are used as the ferritic and austenitic components and the thermal behavior of the joints between modified 9Cr-1Mo steel and Alloy 800 is described in this article. The joints, made using the nickel-base filler material INCONEL 82/182 (INCONEL 82 for the root pass by gas-tungsten arc welding and INCONEL 182 for the filler passes by shielded-metal arc welding), were aged at 625 °C for periods up to 5000 hours. The microstructural changes occurring in the weld metal as well as at the interfaces with the two parent materials are characterized in detail. Results of across-the-weld hardness surveys and cross-weld tension tests and weld metal Charpy impact tests are correlated with the structural changes observed. Principally, the results show that (1) the tendency for carbon to diffuse from the ferritic steel into the weld metal is much less pronounced than when 2.25Cr-1Mo steel is used as the ferritic part; and (2) intermetallic precipitation occurs in the weld metal for aging durations longer than 2000 hours, but the weld metal toughness still remains adequate in terms of the relevant specification.     

Optimization of Welding Parameters,Influence of Activating Flux and Investigation on the Mechanical and Metallurgical Properties of Activated TIG Weldments of AISI 316 L Stainless Steel

This research investigation articulates the joining of AISI 316 L austenitic stainless steel plates of thickness 5 mm by activated tungsten inert gas (A-TIG) welding. Prior to the welding, the optimization of process parameters and the selection of suitable flux have been carried out to join the plates in a single pass welding. The experimental results show that the complete weld penetration can be achieved by using activating flux. The microscopic study divulges the presence of delta ferrite, sigma phase and various forms of austenite in the weld zone. Fischer Feritscope result indicates that the delta ferrite content in the weld is higher (7.8 FN) than the base metal (1.3 FN) which results in superior mechanical properties of the weld. Field Emission-Scanning Electron Microscope (FE-SEM) fractography reveals that the failure of weldments occurs in ductile mode. 180° bend test study reveals the good ductility of the joint.     

An Improved Theoretical Model for A-TIG Welding Based on Surface Phase Transition and Reversed Marangoni Flow

It is experimentally shown that a thin layer of silica flux leads to an increased depth of weld penetration during activated TIG (=A-TIG) welding of Armco iron. The oxygen-content is found higher in the solidified weld metal and it is linked to the increased depth of penetration through the reversed Marangoni convection. It is theoretically shown for the first time that the basic reason of the reversed Marangoni convection is the phenomenon called ??surface phase transition?? (SPT), leading to the formation of a nano-thin FeO layer on the surface of liquid iron. It is shown that the ratio of dissolved oxygen in liquid iron to the O-content of the silica flux is determined by the wettability of silica particles by liquid iron. It is theoretically shown that when the silica flux surface density is higher than 15 µg/mm², reversed Marangoni flow will take place along more than 50 pct of the melted surface. Comparing the SPT line with the dissociation curves of a number of oxides, they can be positioned in the following order of their ability to serve as a flux for A-TIG welding of steel: anatase-TiO₂ (best)-rutile-TiO₂ (very good)-silica-SiO₂ (good)-alumina-Al₂O₃ (does not work). Anatase (and partly rutile) are self-regulating fluxes, as they provide at any temperature just as much dissolved oxygen as needed for the reversed Marangoni convection, and not more. On the other hand, oxygen can be over-dosed if silica, and other, less stable oxides (such as iron oxides) are used.     

Effect of Application of Short and Long Holds on Fatigue Life of Modified 9Cr-1Mo Steel Weld Joint

Modified 9Cr-1Mo steel is a heat-treatable steel and hence the microstructure is temperature sensitive. During welding, the weld joint (WJ) is exposed to various temperatures resulting in a complex heterogeneous microstructure across the weld joint, such as the weld metal, heat-affected zone (HAZ) (consisting of coarse-grained HAZ, fine-grained HAZ, and intercritical HAZ), and the unaffected base metal of varying mechanical properties. The overall creep–fatigue interaction (CFI) response of the WJ is hence due to a complex interplay between various factors such as surface oxides and stress relaxation (SR) occurring in each microstructural zone. It has been demonstrated that SR occurring during application of hold in a CFI cycle is an important parameter that controls fatigue life. Creep–fatigue damage in a cavitation-resistant material such as modified 9Cr-1Mo steel base metal is accommodated in the form of microstructural degradation. However, due to the complex heterogeneous microstructure across the weld joint, SR will be different in different microstructural zones. Hence, the damage is accommodated in the form of preferential coarsening of the substructure, cavity formation around the coarsened carbides, and new surface formation such as cracks in the soft heat-affected zone.     

含铝304和316L奥氏体不锈钢热轧板材焊接性能

 对加Al质量分数为4%的304、2%的316L不锈钢热轧板材的焊接性能进行了研究。采用手工氩弧焊（TIG）的焊接方法,利用光学显微镜对焊缝的显微组织进行分析,利用电子探针（EMPA）分析焊接母材的元素分布,并对焊接接头进行力学性能测试。组织和力学性能的研究结果表明：含铝304和含铝316L合金热轧板分别选用ER308L,ER316L作为焊接材料,经TIG焊接后,焊缝无裂纹、气孔等缺陷,接头具有良好的强度和塑性,焊接接头力学性能接近于其母材;热影响区组织与母材组织基本一致,焊缝与母材熔合良好,组织良好,加铝304和316L不锈钢具有良好的焊接性能。     

Investigation of Hot Cracking Behavior in Transverse Mechanically Arc Oscillated Autogenous AA2014 T6 TIG Welds

Hot cracking studies on autogenous AA2014 T6 TIG welds were carried out. Significant cracking was observed during linear and circular welding test (CWT) on 4-mm-thick plates. Weld metal grain structure and amount of liquid distribution during the terminal stages of solidification were the key cause for hot cracking in aluminum welds. Square-wave AC TIG welding with transverse mechanical arc oscillation (TMAO) was employed to study the cracking behavior during linear and CWT. TMAO welds with amplitude?=?0.9?mm and frequency?=?0.5?Hz showed significant reduction in cracking tendency. The increase in cracking resistance in the arc-oscillated weld was attributed to grain refinement and improved weld bead morphology, which improved the weld metal ductility and uniformity, respectively, of residual tensile stresses that developed during welding. The obtained results were comparable to those of reported favorable results of electromagnetic arc oscillation.     

Q235A碳钢活性A—TIG点焊的焊接性研究

对Q235A碳钢A—TIG点焊进行了工艺性的研究,讨论了活性剂对焊点成形。结果表明,使用活性剂后能显著增加焊点熔深。焊点表面成形良好,提高了焊接接头力学性能。焊接电流、点焊时间和弧长均对焊接熔深的增加产生影响。     

Effect of Oxide Fluxes on Depth of Penetration in Flux Bounded Tungsten Inert Gas Welding of AISI 304L Stainless Steel

Flux Bounded Tungsten Inert Gas (FBTIG) welding is a modified TIG welding process in which increased depth of penetration (DoP) can be achieved by laying thin flux coatings on either side of the weld centerline. The effect of three single component fluxes viz., SiO₂, TiO₂ and Cr₂O₃ on bead geometry of autogenous melt runs in AISI 304L stainless steel for the gap between the flux layers varying from 2 to 7 mm, is studied. Results show that DoP can be improved significantly in FBTIG process using single component fluxes. Nature of the flux and the gap between the flux layers influence the weld bead geometry. Among the three fluxes used, SiO₂ is more efficient in improving the DoP. Arc constriction is the predominant mechanism operative in improving the DoP in FBTIG welding. Possibility of change in solidification mode in FBTIG weld metals of stainless steels is highlighted.     

Microstructure,Properties and Corrosion Characterization of Welded Joint for Composite Pipe Using a Novel Welding Process

In this paper, a novel process welding for composite pipe, firstly overlaid by SMAW in composite pipe end and subsequently butted by TIG, can greatly improve the joints' comprehensive properties. Mechanical, corrosion tests and microstructure observation were carried out on welded joints. The results show that base X65 is composed of pearlite and ferrite and the weld is composed of dendritic austenite. The microstructure of HAZ in X65 has an upper bainite with coarse grains. The overlaying layer contains single-phase dendritic austenite, which has an apparent phenomenon of competitive growth similar to the weld, with solid subgrain boundary, solidified grain boundary and migrated grain boundary. By comparing the conventional welding process with the novel welding process, the welded joint shows better properties in mechanics and corrosion, showing the advantages in composite pipe.     

Comparison of microstructure and properties between joints of FSW and TIG 316L austenitic stainless steel

FSW and TIG were conducted on 316L stainless steel.Variation during microstructure and properties in joints obtained by different welding methods was studied.The results show that the effect of severe mechanical stirring and intense plastic deformation creat a fine recrystallized grain in the welding joint during FSW.As for TIG,the temperature of welding joint exceeds the melting point of welded material itself.The entire welding process belongs to the solidification of a small molten pool;and the microstructure of the joint takes on a typical casting structure.When the welding parameters were selected appropriately,the average ultimate tensile strength of FSW joints can reach 493 MPa,which is 83.6%of base metal;the average elongation is 52.1%of base metal.The average ultimate tensile strength of TIG joints is 475 MPa, which is 80.5%of base metal;the average elongation is 40.8%of base metal.The tensile test of FSW joints is superior to the TIG joints.The microhardness of FSW joint compared to base metal and TIG joint having a significant improvement,which arel95.5 HV,159.7 HV and 160.7 HV,respectively;grain refinement strengthening plays an important role in enhancing the microhardness.The electrochemical corrosion tests show that the joint of FSW 316L austenitic stainless steel has a good corrosion resistance.     

Fracture toughness of modified P91 weldments

There are efforts to develop modified P91 steel (9Cr-1Mo-V) consumables to optimize strength and fracture toughness in weldments for similar and dissimilar welding of 9Cr-1Mo (modified P91) for both new construction and replacement of serviced components. Fracture toughness is an important consideration which plays a vital role in determining the performance and life of the materials under the given service conditions. Toughness characterization was done by the Crack Tip Opening Displacement (CTOD) method. Welding results in a variety of non-equilibrium microstructures in the HAZ of 9Cr-lMo-V, modified P91 steel. These variations of microstructures from wrought base material through transformed HAZ to cast weld metal, may give rise to considerable inhomogeneity with respect to tensile & creep strength and ductility across the weld joints. However the mechanical properties of the individual regions of HAZ are difficult to obtain because of the small extent over which each region exists. Welded joints are used as structural parts of boilers and pressure vessels working at high temperatures, hence the main requirement is creep resistance. In the present investigation, the fracture toughness characteristics of base metal and weld metal have been evaluated by CTOD method as per the standard BS 7448. The fracture surfaces of the CTOD tested specimens were examined under Scanning Electron Microscope (SEM). Fractographic studies revealed the mode of failure and the characteristics of the fracture surface.     

CO2 laser beam welding of 6061-T6 aluminum alloy thin plate

Laser beam welding is an attractive welding process for age-hardened aluminum alloys, because its low heat input minimizes the width of weld fusion and heat-affected zones (HAZs). In the present work, 1-mm-thick age-hardened Al-Mg-Si alloy, 6061-T6, plates were welded with full penetration using a 2.5-kW CO₂ laser. Fractions of porosity in the fusion zones were less than 0.05 pct in bead-on-plate welding and less than 0.2 pct in butt welding with polishing the groove surface before welding. The width of a softened region in the-laser beam welds was less than 1/4 times that of a tungsten inert gas (TIG) weld. The softened region is caused by reversion of strengthening β″ (Mg₂Si) precipitates due to weld heat input. The hardness values of the softened region in the laser beam welds were almost fully recovered to that of the base metal after an artificial aging treatment at 448 K for 28.8 ks without solution annealing, whereas those in the TIG weld were not recovered in a partly reverted region. Both the bead-on-plate weld and the butt weld after the postweld artificial aging treatment had almost equivalent tensile strengths to that of the base plate.