Modelling weld bead geometry using neural networks for GTAW of austenitic stainless steel

Ghanty, P.; Paul, Satyam; Mukherjee, D.; Vasudevan, M.; Pal, Nikhil R.; Bhaduri, A.K.

doi:10.1179/174329307x238399

Cited by 24 publications

(18 citation statements)

References 25 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sudhakaran and Sakthivel [26] developed neural network models for predicting bead parameters in the GTAW process, such as depth of penetration, bead width, and depth to width ratio. Ghanty et al [27] also succeeded in using a backpropagation ANN to predict weld bead geometry confirming the method's efficiency. Genetic algorithm (GA) is attracting many researchers' attention to solve optimization problems since traditional optimization methods frequently end up in local minima.…”

Section: Introductionmentioning

confidence: 86%

Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm

Tomaz

Colaço

Sarfraz

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Gas tungsten arc welding (GTAW) technology is widely used in industry and has advantages, including high precision, excellent welding quality, and low equipment cost. However, the inclusion of a large number of process parameters hinders its application on a wider scale. Therefore, there is a need to implement the prediction and optimization models that effectively enhance the process performance of the GTAW process in different applications. In this study, a five-factor five-level central composite design (CCD) matrix was used to conduct GTAW experiments. AISI 1020 steel blank was used as a substrate; UTP AF Ledurit 60 and UTP AF Ledurit 68 were used as the materials of two tubular wires. Further, an artificial neural network (ANN) was used to simulate the GTAW process and then combined with a genetic algorithm (GA) to determine welding parameters that can provide an optimal weld. In welding experiments, five different welding current levels, welding speed, distance to the nozzle, angle of movement, and frequency of the wire feed pulses were used. Using GA, optimal welding parameters were determined: welding current = 222 A, welding speed = 25 cm/min, nozzle deflection distance = 8 mm, travel angle = 25°, wire feed pulse frequency = 8 Hz. The determination coefficient (R2) and RMSE value of all response parameters are satisfactory, and the R2 of all the data remained higher than 0.65.

show abstract

Section: Introductionmentioning

confidence: 86%

Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm

Tomaz

Colaço

Sarfraz

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…on the weld quality using SVR, ANN etc., where SVR was reported to perform the best. MLP and case-based reasoning algorithms were used to predict the different welding defects by Liao et al 37 Ghanty et al 38 studied the effect of GTAW process parameters on the weld geometry of SS 316LN using MLP and radial basis function neural networks. Wang and Liao 39 observed MLP to outperform the fuzzy k-nearest neighbor during the detection of welding defects using radiographic images.…”

Section: Literature Reviewmentioning

confidence: 99%

Prediction of residual stress in electron beam welding of stainless steel from process parameters and natural frequency of vibrations using machine-learning algorithms

Das

Pratihar

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

In the present study, machine learning algorithms have been used to predict residual stress during electron beam welding of stainless steel using the information of input process parameters and natural frequency of vibrations. Accelerating voltage, beam current and welding speed have been considered as input process parameters. Both residual stress and natural frequencies of vibration of the weld obtained using each set of the input parameters are measured experimentally. A number of machine learning algorithms, namely M5 algorithm-based Model Trees Regression, Random forest, Support Vector Regression, Reduced Error Pruning Tree, Multi-layer perceptron, Instance-based k-nearest neighbor algorithm, and Locally weighted learning have been used for the said purpose. Support vector regression and Locally weighted learning are found to perform consistently good and bad, respectively. The predicted welding residual stresses have been validated experimentally through X-ray diffraction (XRD) and good agreements are obtained. In addition, statistical tests are conducted, and the estimated reliability values of the employed models are analyzed through Monte-Carlo simulations.

show abstract

“…Apart from using polynomial equation in the works mentioned before, advance artificial intelligent (AI) methods were also employed to obtain reliable results. Ghanty et al [12] employed two types of neural networks, which were respectively multilayer perceptron (MLP) and radial basis function (RBF) neural networks, to map four important features, which were welding current, voltage, vertex angle and torch speed, into the bead width, penetration depth and bead area, and 45 experiments were conducted to collect the training data. They also used the same methods to predict weld bead geometry using features derived from the infrared thermal video [13].…”

Section: Introductionmentioning

confidence: 99%

Exploration of Weld Bead Forming Rule during Double-Pulsed GMAW Process Based on Grey Relational Analysis

et al. 2019

View full text Add to dashboard Cite

Weld bead forming rule is very important during double-pulsed gas metal arc welding (DP-GMAW) process, and this process has more advantages than that of conventional arc welding process. This work employed grey rational analysis to explore the weld bead forming rule. Since the latest twinpulse XT DP control process was employed, the parameters adjustment was easier than that of conventional operation. The grey relational analyses between five main process parameters, which were average welding current, welding speed, twin pulse relation, twin pulse frequency together with twin pulse current change in percent, and three key characteristic parameters, which were bead width, bead height and penetration, were conducted to explore the weld bead forming rule. To accurately calculate the grey relational degree, the negative relevancies were transformed to positive ones. According to calculations and corresponding analyses, it can be concluded that the effects of average welding current and welding speed on the weld bead forming and key characteristic parameters of the weld bead were higher than that of other process parameters. Moreover, the relevancies between key characteristic parameters of the weld bead, and process parameters which included twin pulse relation, average welding current and twin pulse current change in percent were positive, while the relevancies between key characteristic parameters and other two process parameters were negative. The work can supply a new method to evaluate the effects of process parameters during the DP-GMAW process on the weld bead forming or other process characteristics, and references for parameters selection and process optimization.

show abstract

Modelling weld bead geometry using neural networks for GTAW of austenitic stainless steel

Cited by 24 publications

References 25 publications

Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm

Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm

Prediction of residual stress in electron beam welding of stainless steel from process parameters and natural frequency of vibrations using machine-learning algorithms

Exploration of Weld Bead Forming Rule during Double-Pulsed GMAW Process Based on Grey Relational Analysis

Contact Info

Product

Resources

About