scholarly journals Improved Welding Quality Prediction for Metal Inert Gas Welding using Artificial Intelligence

Author(s):  
Mohmmad Qamar ◽  
Dharmendra Kumar Singh

Welding is widely used by manufacturing engineers and production personnel to quickly and effectively set up manufacturing processes for new products. The MIG welding parameters are the most important factors affecting the quality, productivity and cost of welding. This paper presents the influence of welding parameters like welding current, welding voltage, Gas flow rate, wire feed rate, etc. on weld strength, ultimate tensile strength, and hardness of weld joint, weld pool geometry of various metal material during welding. By using DOE method, the parameters can be optimize and having the best parameters combination for target quality. The analysis from DOE method can give the significance of the parameters as it give effect to change of the quality and strength of product.

2013 ◽  
Vol 651 ◽  
pp. 355-360 ◽  
Author(s):  
Yi Jiang ◽  
Ming Liu ◽  
Yao Hui Lu ◽  
Bin Shi Xu

Variable polarity plasma arc welding has been widely used to manufacture industries. The effects of welding current and plasma gas flow as the most important parameters on variable polarity plasma arc pressure were discussed experimentally. To welding current, two experimental were designed to discuss the effects of straight polarity current and reversed polarity current on arc pressure respectively. It could be concluded that arc pressure is quadratic with welding current. To plasma gas flow, both experimental and numerical analysis are used to discuss the mechanisms of plasma gas flow to arc pressure, and it could be conclude that arc pressure is quadratic with plasma gas flow rather than linear.


2020 ◽  
Vol 8 (4) ◽  
Author(s):  
Neeraj Sharma ◽  
◽  
Wathiq Sleam Abduallah ◽  
Manish Garg ◽  
Rahul Dev Gupta ◽  
...  

Tungsten Inert Gas welding is a fusion welding process having very wide industrial applicability. In the present study, an attempt has been made to optimize the input process variables (electrode diameter, shielding gas, gas flow rate, welding current, and groove angle) that affect the output responses, i.e., hardness and tensile strength at weld center of the weld metal SS202. The hardness is measured using Vicker hardness method; however, tensile strength is evaluated by performing tensile test on welded specimens. Taguchi based design of experiments was used for experimental planning, and the results were studied using analysis of variance. The results show that, for tensile strength of the welded specimens, welding current and electrode diameter are the two most significant factors with P values of 0.002 and 0.030 for mean analysis, whereas higher tensile strength was observed when the electrode diameter used was 1.5 mm, shielding gas used was helium, gas flow rate was 15 L/min, welding current was 240A, and a groove angle of 60o was used. Welding current was found to be the most significant factor with a P value of 0.009 leading to a change in hardness at weld region. The hardness at weld region tends to decrease significantly with the increase in welding current from 160-240A. The different shielding gases and groove angle do not show any significant effect on tensile strength and hardness at weld center. These response variables were evaluated at 95% confidence interval, and the confirmation test was performed on suggested optimal process variable. The obtained results were compared with estimated mean value, which were lying within ±5%.


Author(s):  
Rajesh Singh ◽  
Gaurav Yadav

This paper reports on process parameter selection for optimizing the weld pool geometry in the metal inert gas welding of High strength low alloy (HSLA) steel. The experimental studies were conducted under varying Voltage, flow rate, stick out and wire feed speed. The settings of welding parameters were determined by using the Taguchi experimental design method. The level of importance of the welding parameters on the weld pool geometry is determined by using analysis of variance (ANOVA). The optimum welding parameter combination was obtained by using the analysis of signal-to-noise (S/N) ratio. The confirmation tests indicated that it is possible to optimize the weld pool geometry significantly by using the Taguchi method. The experimental results confirmed the validity of the used Taguchi method for enhancing the welding performance and optimizing the welding parameters in the metal inert gas welding process.


2011 ◽  
Vol 480-481 ◽  
pp. 53-58
Author(s):  
De Xin Sun ◽  
Shi Jun Luo ◽  
Hong Zhuang Zhang ◽  
Da Qian Sun

Through the metal inert gas welding (MIG) experiment, the effects of the different welding parameters on the microstructure, the weld configuration and the mechanical properties of the joint of the magnesium (Mg) alloy AZ31B were analyzed. The results indicate that with the increase in the welding current, the microstructure change of the weld is characterized by the grain coarsening, and the microstructure change of the heat affected zone is characterized by the grain coarsening and the broadening of the heat affected zone. An exorbitant welding current is inimical to the weld configuration. With the increase in the welding speed, the welding linear energy decreases, inducing the formation of the finer equiaxed grains in the weld. Moreover, the grains in the heat affected zone are also with the trend of the refinement, and thus the mechanical properties of the joint increase. The optimal welding current and speed in our experiment are 160-170A and 400-450mm/min, respectively.


2017 ◽  
Vol 16 (1) ◽  
Author(s):  
Gilang Sigit Saputro ◽  
Triyono . ◽  
Nurul Muhayat

Tungsten Inert Gas welding of galvanized steel-aluminium useful for weight reduction, improve perform and reduce cost production. The effect of welding parameters, welding current and shielding gas flow rate on the intermetallic formation and hardness of dissimilar metals weld joint between galvanized steel and aluminium by using AA 5052 filler was determined. In this research, welding speed was consistent kept. The welding parameters were obtained by using welding currents of 70, 80 and 90 A, shielding gas flow rate of 10, 12 and 14 litre/min. The intermetallic layer thickness increased by welding currents of 70 A to 80 A, but then it dropped on 90 A. The higher of a shielding gas flow rate, the lower the thickness of the intermetallic layer. The higher of a welding current, the lower the hardness of weld. The higher of a shielding gas flow rate, the greater the hardness of weld. As a result,the maximum hardness by current variation of 70 A and a shielding gas flow rate of 14 Litre/min was 100.9 HVN.


2019 ◽  
Vol 14 (4) ◽  
Author(s):  
Karthimani T ◽  
Babu N

This works aims at the analysis and optimization of joining similar grades of stainless steel by TIG welding. TIG welding may use a filler material. There is a variant in the process which does not require filler material. Such process is known as Autogenous TIG welding process. The parameters like current, welding speed and gas flow rate are the variables in the study. The objective of this research is to determine the influence of various welding parameters on the weld bead of 316 SS by using Taguchi technique. A plan of experiments based on Taguchi technique method has been carried out. Orthogonal array, signal to noise (S/N) Ratio, Analysis of variance (ANOVA) are employed for studying the welding characteristics of material & to optimize the weld parameters. The result obtained are the output from each parameter, through which optimal parameters are found out for maximum tensile strength. It is found that -welding current followed by welding speed are major parameters influencing mechanical properties of welded joint


2011 ◽  
Vol 110-116 ◽  
pp. 2963-2968 ◽  
Author(s):  
Masood Aghakhani ◽  
Ehsan Mehrdad ◽  
Ehsan Hayati ◽  
Maziar Mahdipour Jalilian ◽  
Arash Karbasian

Gas metal arc welding is a fusion welding process which has got wide applications in industry. In order to obtain a good quality weld, it is therefore, necessary to control the input welding parameters. In other words proper selection of input welding parameters in this process contribute to weld productivity. One of the important welding output parameters in this process is weld dilution affecting the quality and productivity of weldment. In this research paper using Taguchi method of design of experiments a mathematical model was developed using parameters such as, wire feed rate (W), welding voltage (V), nozzle-to-plate distance (N), welding speed (S) and gas flow rate (G) on weld dilution. After collecting data, signal-to-noise ratios (S/N) were calculated and used in order to obtain the optimum levels for every input parameter. Subsequently, using analysis of variance the significant coefficients for each input factor on the weld dilution were determined and validated. Finally a mathematical model based on regression analysis for predicting the weld dilution was obtained. Results show that wire feed rate (W),arc voltage (V) have increasing effect while Nozzle-to-plate distance (N) and welding speed (S) have decreasing effect on the dilution whereas gas Flow rate alone has almost no effect on dilution but its interaction with other parameters makes it quite significant in increasing the weld dilution


Author(s):  
Sandip Mondal ◽  
Goutam Nandi ◽  
Pradip Kumar Pal

Tungsten inert gas (TIG) welding on Duplex stainless steel (DSS) is more easy, comfortable and useful, if the process is precisely understood and controlled through development of the science & technology. TIG welding on DSS has been performed with the help of specific controlled welding process parameters. Welding quality has been strongly depended on these process parameters. In this study, some valuable welding parameters are chosen. These are welding current, shielding gas flow rate and speed of welding. These process parameters of TIG welding for ASTM/UNS 2205 DSS welds are optimized by using Principal Component Analysis (PCA) method and Grey based Taguchi’s L9 Orthogonal array (OA) experimental plan with the conception of signal to noise ratio (N/S). After that, compression results of above mentioned two analyses of TIG welding process parameters have been calculated. The quality of the TIG welding on DSS has been evaluated in term of ultimate tensile strength, yield strength and percentage of elongation. Compression results of both analyses indicate application feasibility for continuous improvement of welding quality on DSS in different components of chemical, oil and gas industries.


2015 ◽  
Vol 813-814 ◽  
pp. 456-461
Author(s):  
S. Saravanan ◽  
Pandian Pitchipoo

In this paper, multi objective optimization of Gas Metal Arc Welding GMAW) parameters are carried out to yield good mechanical strength in welded joints. Most of the failures are occurred on the welded elements due to the setting of improper welding parameters. The strength of welded joints in GMAW depends on several input process parameters such as welding current, welding voltage, gas flow rate, torch angle, welding speed, wire size and electrode feed rate. Wrong selection of these process parameters will lead to bad quality welds. So there is a need to control the process parameters to obtain good quality welded joints. For getting the better values of these parameters, it needs to conduct experiments by varying the input process parameters that are affecting the strength of the welded joints. In this work nine experimental runs based on an L9 orthogonal array of Taguchi method are performed to optimize the strength of the welded joint. To achieve this Grey Relational Analysis (GRA) is used. In this work Aluminum6063 material is used as base material.


Author(s):  
Zhehao Zhang ◽  
Yi Zhang ◽  
Feng Luo ◽  
Jie Li ◽  
Cheng Lu ◽  
...  

Abstract Convolutional neural network (CNN) is an efficient and robust method which can accurately detect the Tailor Rolled Blank laser welding pool penetration status. To select proper hyperparameters and optimization of CNN model are black box problem. In this paper, an innovative method based on CNN to identify the penetration status of the weld pool during laser welding was introduced. A coaxial monitoring platform is set up, as well as two-class, three-class and four-class datasets are created for training and validating the CNN. The Bayesian Optimization (BO) method is used to optimize hyper-parameters which are adopted for training CNN model, determine the best parameters of depth, initial learning rate, momentum and L2 regularization. The results show that using BO method leads to accuracy improvement compared with the CNN model trained from scratch with default hyper-parameters, hence it can effectively solve the problem that the hyper-parameters of CNN are difficult to adjust. Under various laser welding parameters, high-accuracy detection of penetration status can be acquired with the test accuracy of four-class reaching 95.2%, which slightly lower than the test accuracy of the three-class and two-class.


Sign in / Sign up

Export Citation Format

Share Document