Bead Geometry Prediction in Laser-Wire Additive Manufacturing Process Using Machine Learning: Case of Study

In Laser Wire Additive Manufacturing (LWAM), the final geometry is produced using the layer-by-layer deposition (beads principle). To achieve good geometrical accuracy in the final product, proper implementation of the bead geometry is essential. For this reason, the paper focuses on this process and proposes a layer geometry (width and height) prediction model to improve deposition accuracy. More specifically, a machine learning regression algorithm is applied on several experimental data to predict the bead geometry across layers. Furthermore, a neural network-based approach was used to study the influence of different deposition parameters, namely laser power, wire-feed rate and travel speed on bead geometry. To validate the effectiveness of the proposed approach, a test split validation strategy was applied to train and validate the machine learning models. The results show a particular evolutionary trend and confirm that the process parameters have a direct influence on the bead geometry, and so, too, on the final part. Several deposition parameters have been found to obtain an accurate prediction model with low errors and good layer deposition. Finally, this study indicates that the machine learning approach can efficiently be used to predict the bead geometry and could help later in designing a proper controller in the LWAM process.

Representation of gas metal arc pulsed welding process behavior on bead geometry: a study of leading variables

Gas metal arc welding is one of the most influential processes in the production and repair of structures and equipment; therefore, the need to improve the productivity and quality of welded joints has led to the development of techniques for good control of welding parameters. Also, the development of semi-automatic welding processes led to the control of one of the variables such as pulsed current; this technique is characterized by a lower heat input and lower energy expenditure, which directly influences the structural quality of the welded joint and the geometry of the weld bead. This work focused on evaluating the effects of various welding operating parameters using the central composite design tool based on the response surface methodology; next, the experimental development employed an inverter type power source for weld depositions, a commercial grade Stargold clean 96% Ar and 4% CO2 shielding gas at the rate of 15 L/min stationary arc, a 1.2 mm metal cored wire for welding deposit and a carbon steel base plate with a thickness of 6 mm. During the welding process, the torch was kept at a 90° inclination and a 16 mm stroke. To examine the adequacy of the empirical models and the significance of the regression coefficients, the variance analysis was employed. Consequently, the graphs were obtained through the determination of the model; from the statistical results obtained, it was shown that the above models were adequate to predict the weld width, bead height, and penetration within the range of variables studied. Furthermore, it was observed that the wire feed rate it has a very marked effect on weld bead geometry, followed by frequency pulse and peak current; finally, the effectiveness of employing these methodologies for the management of variables attributing to the execution of welding tasks with higher accuracy was demonstrated.

Experimental Investigation on Bead Geometry Parameter and Mechanical Property of Part Fabricated by Wire Arc Additive Manufacturing

In additive manufacturing process, wire arc additive manufacturing process (WAAM) is a technique which can produce a metal 3D printed part. In Industries product are produced by wasting one third of its material, from this process time consumption and material wastage is more comparing in Subtractive Manufacturing over Additive Manufacturing. Additive Manufacturing stepped from 1925 in manufacturing industry and it has gained its remarkable growth in past few decades, as of now metal 3D oriented parts have come to play a major role in aerospace industry. This research work focused on Gas Metal Arc Welding (GMAW) welding. It has high deposition rate, ultimate build volume and good structural integrity compare with other additive manufacturing process. MACH3 controller is used to control the welding torch motion for addition of material by 3 axis movement (X, Y and Z). To identify the correct parameters for metal part we have done numbers of samples by changing values in the MIG machine from that we finalize the three parameters through visualizes on the printed materials after that a wall like structure is built and post processing like cutting the materials from base plate, grinding the uneven surface on printed materials. The printed materials are ready for material testing like bead geometry analysis of various parameter and tensile testing to identify the printed material strength, elongation, stress and strain.

Grey-Based Taguchi Multiobjective Optimization and Artificial Intelligence-Based Prediction of Dissimilar Gas Metal Arc Welding Process Performance

The quality of a welded joint is determined by key attributes such as dilution and the weld bead geometry. Achieving optimal values associated with the above-mentioned attributes of welding is a challenging task. Selecting an appropriate method to derive the parameter optimality is the key focus of this paper. This study analyzes several versatile parametric optimization and prediction models as well as uses statistical and machine learning models for further processing. Statistical methods like grey-based Taguchi optimization is used to optimize the input parameters such as welding current, wire feed rate, welding speed, and contact tip to work distance (CTWD). Advanced features of artificial neural network (ANN) and adaptive neuro-fuzzy interface system (ANFIS) models are used to predict the values of dilution and the bead geometry obtained during the welding process. The results corresponding to the initial design of the welding process are used as training and testing data for ANN and ANFIS models. The proposed methodology is validated with various experimental results outside as well as inside the initial design. From the observations, the prediction results produced by machine learning models delivered significantly high relevance with the experimental data over the regression analysis.

Optimizing the Mean and Variance of Bead Geometry in the Wire + Arc Additive Manufacturing Using a Desirability Function Method

Wire + arc additive manufacturing (WAAM) is an arc welding process that uses non-consumable tungsten electrodes to produce the weld. The material used in this study is a titanium, carbon, zirconium, and molybdenum (TZM) alloy that is physically and chemically stable and has good performance for use as a welding and high-temperature heating element. However, the price is higher than that of other materials. Because welding cannot be modified after manufacturing, economic losses are high in the case of a defective product. Therefore, it is important to find the best welding settings for the target bead geometry during welding. In this study, welding experiments are designed based on a central composite design, and single-layer WAAM is performed using a TZM material. Consequently, we obtain 17 beads and measure the height, width, as well as left and right toe angles, which represent the geometry of the beads. Based on the measured geometry, we obtain the optimal settings for the WAAM parameters whereat the mean of each geometry is close to its target value and its variance is minimized by using a desirability function method. Furthermore, we conduct additional experiments to validate the optimal settings that we obtain. We compare the predicted and actual geometry values and find that they are quite close. This result indicates that valid optimal settings for the process parameters can be obtained via the proposed method.