Quality Prediction and Control in Wire Arc Additive Manufacturing via Novel Machine Learning Framework

Wire arc additive manufacturing (WAAM) is capable of rapidly depositing metal materials thus facilitating the fabrication of large-shape metal components. However, due to the multi-process-variability in the WAAM process, the deposited shape (bead width, height, depth of penetration) is difficult to predict and control within the desired level. Ultimately, the overall build will not achieve a near-net shape and will further hinder the part from performing its functionality without post-processing. Previous research primarily utilizes data analytical models (e.g., regression model, artificial neural network (ANN)) to forwardly predict the deposition width and height variation based on single or cross-linked process variables. However, these methods cannot effectively determine the optimal printable zone based on the desired deposition shape due to the inability to inversely deduce from these data analytical models. Additionally, the process variables are intercorrelated, and the bead width, height, and depth of penetration are highly codependent. Therefore, existing analysis cannot grant a reliable prediction model that allows the deposition (bead width, height, and penetration height) to remain within the desired level. This paper presents a novel machine learning framework for quantitatively analyzing the correlated relationship between the process parameters and deposition shape, thus providing an optimal process parameter selection to control the final deposition geometry. The proposed machine learning framework can systematically and quantitatively predict the deposition shape rather than just qualitatively as with other existing machine learning methods. The prediction model can also present the complex process-quality relations, and the determination of the deposition quality can guide the WAAM to be more prognostic and reliable. The correctness and effectiveness of the proposed quantitative process-quality analysis will be validated through experiments.

Arc Welding-Laser Shock Forging Process for Improving the Mechanical Properties of the Fe-Cr-C Cladded Layer

While parts can be repaired via arc welding (AW), it is usually necessary to add some types of excitation method to improve the mechanical properties of the cladded layer. Here, the arc welding-laser shock forging (AW-LSF) was used to repair Q235 steel pipes (Fe-Cr-C alloy was used as the cladding material). The effects of the welding current (WC), welding speed (WS), and laser shock frequency (LSF) on the geometry and microhardness of the weld bead were studied. The AW-LSF and AW repair processes were compared. The results demonstrate that the bead width (W) and penetration depth (D) increase with the WC, while the weld height (H) decreases with the WC. The H, W, and D all decrease with the WS; W and D increase with the LSF; and H decreases with the LSF. As the WC increases, the hardness of the fusion zone (FZ) and partial fusion zone (PFZ) decreases significantly, while the hardness of the heat-affected zone (HAZ) remains nearly unchanged. As the WS increases, the hardness of the PFZ decreases, while the hardness of the FZ and HAZ remains nearly unchanged. With the increase of the LSF, the hardness of the PFZ, FZ, and HAZ increases. Compared with AW, the AW-LSF can reduce the cladded layer crystal grain size, increase the hardness, and improve the sliding wear resistance.

Numerical Study of the Effect of Workpiece Thickness on the Interfacial Behavior of a Molten Aluminum Droplet on a Zinc-coated Steel Sheet

In brazing, the interfacial conditions between the molten filler material and the solid workpiece are important, yet they cannot be observed experimentally. A two-dimensional axisymmetric simulation was conducted to analyze the behavior of a single droplet of molten aluminum on zinc-coated steel sheet as a simplified brazing process. The simulation models were verified through a comparison with experimental results in terms of bead shape, zinc distribution, and molten metal behavior. The results show that Young’s equation was not valid in explaining the wetting behavior because of the instant solidification. In this respect, the effects of the workpiece thickness and wetting angle on the bead width were negligible. Two periods of time, namely the times for the temperature difference and solidification, and their ratio (interface number) were defined to analyze the temperature behavior at the interface over time as well as the effects of workpiece thickness. The interfacial temperature behaviors tended to be divided into three regions: linear (or inversely proportional), singular, and convergence. The interface number converged to a value of one with the increase in the thickness.

Study on temperature- microstructure- stress fields of thick-walled plate welded by hybrid laser arc welding

The 25mm DH36 steel was welded by hybrid laser arc welding (HLAW), and a sequence coupled thermal-metallurgical-mechanical (TMM) model was developed based on SYSWELD. The temperature-microstructure-stress fields are predicted by simulation verified by experiment. The ratio between the arc and laser energy showed a significant effect on weld profile. The laser provided the main power and ensured deep penetration, and the arc power showed a dominant effect on the bead width of the hybrid weld during HLAW. For the hybrid welding of a thick-walled plate, the microstructure and thermal cycles varied along with the thickness. The weld profile and microstructure were experimentally characterized. The 3-pass welding procedure produced larger welding residual stress than the 9-pass welding procedure, and the process stability is poorer than the 3-pass welding process. Overall, numerical results matched well with experimental results.

Design and Development of Submerged Arc Welding Acidic Flux

An acidic flux was intended and developed with the variation of some flux constituents. The basicity index of the flux was kept as 1.84. It was designed to weld the mild steel plates on submerged arc welding machine. A study was done with developed flux on two-level factorial design. Voltage and current were the controlled parameters along with feed rate, nozzle distance and creep feed as uncontrolled parameters selected for experimentation. Eight experiments were performed. Weld bead width and Hardness were the responses measured. Design expert software was used the do the analysis. Finally, it can be determined that travel speed was the most momentous factor for the hardness and weld bead dimensions of the joint.

Experimental and Numerical Analysis on TIG Arc Welding of Stainless Steel Using RSM Approach

This study involves the validating of thermal analysis during TIG Arc welding of 1.4418 steel using finite element analyses (FEA) with experimental approaches. 3D heat transfer simulation of 1.4418 stainless steel TIG arc welding is implemented using ABAQUS software (6.14, ABAQUS Inc., Johnston, RI, USA), based on non-uniform Goldak’s Gaussian heat flux distribution, using additional DFLUX subroutine written in the FORTRAN (Formula Translation). The influences of the arc current and welding speed on the heat flux density, weld bead geometry, and temperature distribution at the transverse direction are analyzed by response surface methodology (RSM). Validating numerical simulation with experimental dimensions of weld bead geometry consists of width and depth of penetration with an average of 10% deviation has been performed. Results reveal that the suggested numerical model would be appropriate for the TIG arc welding process. According to the results, as the welding speed increases, the residence time of arc shortens correspondingly, bead width and depth of penetration decrease subsequently, whilst simultaneously, the current has the reverse effect. Finally, multi-objective optimization of the process is applied by Derringer’s desirability technique to achieve the proper weld. The optimum condition is obtained with 2.7 mm/s scanning speed and 120 A current to achieve full penetration weld with minimum fusion zone (FZ) and heat-affected zone (HAZ) width.

Characterization of dissimilar aluminum-copper material joining by controlled dual laser beam

Laser technology has many advantages in welding for the manufacture of EV battery packs. Aluminum (Al) and copper (Cu) are welded using a dual laser beam, suggesting the optimum power distribution for the core and ring beams. Due to the very high reflectance of Cu and Al exposed to near-infrared lasers, the material absorbs a very small amount of energy. Compared to single beam laser welding, dual beam welding has significantly improved surface quality by controlling surface solidification. The study focused on the quality of weld surface beads, weld properties and tensile strength by varying the output ratio of the core beam to the ring beam. Optimal conditions of Al6061 were a 700 W core beam, a 500 W ring beam and 200 mm/s of weld speed. For the C1020P, the optimum conditions were a center beam of 2500 W, a ring beam of 3000 W and a welding speed of 200 mm/s. In laser lap welding of Al-Al and Al-Cu, the bead width and the interfacial bead width of the joint increased as the output increased. The penetration depth did not change significantly, but small pores were formed at the interface of the junction. Tensile tests were performed to demonstrate the reliability of the weld zone, and computer simulations provided analysis of the heat distribution for optimal heat input conditions.

Parametric Optimization of the GMAW Welding Process in Thin Thickness of Austenitic Stainless Steel by Taguchi Method

In the present work, an analysis of different welding parameters was carried out on the welding of stainless-steel thin thickness tubes by the Gas Metal Arc Welding (GMAW) process. The influence of three main parameters, welding voltage, movement angle, and welding current in the quality of the welds, was studied through a specifically designed experimental process based on the establishment of three different levels of values for each of these parameters. Weld quality is evaluated using destructive testing (macrographic analysis). Specifically, the width and root penetration of the weld bead were measured; however, some samples have been disregarded due to welding defects outside the permissible range or caused by excessive melting of the base metals. Data are interpreted, discussed, and analyzed using the Taguchi method and ANOVA analysis. From the analysis of variance, it was possible to identify the most influential parameter, the welding voltage, with a contribution of 43.55% for the welding penetration and 75.26% for the bead width, which should be considered in the designs of automatic welding processes to improve the quality of final welds.

In-Line Height Measurement Technique for Directed Energy Deposition Processes

Directed energy deposition (DED) is a family of additive manufacturing technologies. With these processes, metal parts are built layer by layer, introducing dynamics that propagate in time and layer-domains, which implies additional complexity and consequently, the resulting part quality is hard to predict. Control of the deposit layer thickness and height is a critical issue since it impacts on geometrical accuracy, process stability, and the overall quality of the product. Therefore, online feedback height control for DED processes with proper sensor strategies is required. This work presents a novel vision-based triangulation technique through an off-axis located CCD camera synchronized with a 640 nm wavelength pulsed illumination laser. Image processing and machine vision techniques allow in-line height measurement right after metal solidification. The linearity and the precision of the proposed setup are validated through off-and in-process trials in the laser metal deposition (LMD) process. Besides, the performance of the developed in-line inspection system has also been tested for the Arc based DED process and compared against experimental weld bead characterization data. In this last case, the system additionally allowed for the measurement of weld bead width and contact angles, which are critical in first runs of multilayer buildups.