Weld Geometry Monitoring for Metal Inert Gas Welding Process with Galvanized Steel Plates Using Bayesian Network

We present a novel method to monitor the weld geometry for metal inert gas(MIG)welding process with galvanized steel plates using Bayesian network(BN),and propose an effective method of extracting the weld reinforcement and width online.The laser vision sensor is mounted after the welding torch and used to profile the weld.With the extracted weld geometry and the adopted process parameters,a back propagation neural network(BPNN)is constructed offline and used to predict the weld reinforcement and width corresponding to the current parameter settings.A BN from welding experience and tests is presented to implement the decision making of welding current/voltage when the error between the predictive geometry and the actual one occurs.This study can deal with the negative welding tendency to adapt to welding randomness and indicates a valuable application prospect in the welding field.

Numerical analysis of dynamic variation of weld pool geometry in fully-penetrated TIG welding

A mathematical model is developed for numerical analysis of thermal process in TIG welding with a moving arc, which is considered the double-elliptic distribution for both arc heat flux and arc pressure. An adjusting factor is introduced into the expression of arc pressure. The domain within which the arc heat flux is distributed non-symmetrically due to arc moving is selected appropriately, and three conditions for the domain to meet are described. The latent heat is taken into consideration by liquid fraction method. The dynamic development of weld pool geometry during TIG welding is analyzed numerically, and the effect of arc moving on the weld pool geometry is discussed. The experimental results show that the numerical analysis accuracy is obviously improved through taking the above-mentioned measures.

Welding Polarity Effects on Weld Spatters and Bead Geometry of Hyperbaric Dry GMAW

Welding polarity has influence on welding stability to some extent, but the specific relationship between welding polarity and weld quality has not been found, especially under the hyperbaric environment. Based on a hyperbaric dry welding experiment system, gas metal arc welding（GMAW） experiments with direct current electrode positive（DCEP） and direct current electrode negative（DCEN） operations are carried out under the ambient pressures of 0.1 MPa, 0.4 MPa, 0.7 MPa and 1.0 MPa to find the influence rule of different welding polarities on welding spatters and weld bead geometry. The effects of welding polarities on the weld bead geometry such as the reinforcement, the weld width and the penetration are discussed. The experimental results show that the welding spatters gradually grow in quantity and size for GMAW with DCEP, while GMAW with DCEN can produce fewer spatters comparatively with the increase of the ambient pressure. Compared with DCEP, the welding current and arc voltage waveforms for DCEN is more stable and the distribution of welding current probability density for DCEN is more concentrated under the hyperbaric environment. When the ambient pressure is increased from 0.1 MPa to 1.0 MPa, the effects of welding polarities on the reinforcement, the weld width and the penetration are as follows： an increase of 0.8 mm for the weld reinforcement is produced by GMAW with DCEN and 1.3 mm by GMAW with DCEP, a decrease of 7.2 mm for the weld width is produced by DCEN and 6.1 mm by DCEP; and an increase of 3.9 mm for the penetration is produced by DCEN and 1.9 mm by DCEP. The proposed research indicates that the desirable stability in the welding procedure can be achieved by GMAW with DCEN operation under the hyperbaric environment.

Sensitivity analysis of rotating flux-cored arc welding process parameters

Empirical models were developed using curvilinear regression analysis to predict bead geometries of rotating fluxcored are welding （FCAW）. Parameters, such as rotational frequerwy, rotational radius, torch height and welding current, are used as design variables. The objective function is formed using bead width and penetration. Experiments of rotating FCAW were conducted based on orthogonal experimental design of four process parameters. A sensitivity analysis was also conducted and the effects of four process parameters on bead geometries were compared. The results show that the sensitivity of rotational radius on bead width is much higher than those of rotational frequency, torch height and welding current on bead width. Welding current is insensitive to bead width. The sensivity of rotational frequerwy on weld penetration is higher than those of other three parameters.

Effect of variable polarity frequency on 2A14-T6 aluminum alloy welds using HPVP-GTAW process

Hybrid ultrahigh frequency pulse variable polarity gas tungsten arc welding （HPVP-GTAW） for 2A14-T6 high strength aluminum alloy was carried out and the effects of variable polarity frequency with constant pulse current frequency 40 kHz on weld bead geometry, microstrueture and microhardness were analyzed. Experimental results indicate that, compared to that of the conventional VP-GTAW process, the weld depth and ratio of weld depth to width are improved significantly by the variable polarity frequency in the HPVP-GTAW process, which the ratio of weld depth to width is improved by 36% at equal variable polarity frequency of 100 Hz, and improved by 55% with that of 200 Hz. Weld microstructure and microhardness distribution are changed obviously with the increase of variable polarity frequency. In the conventional VP-GTA W process, the grains in weld central zone are coarser, and the microhardness in weld central zone and fusion zone is about 95 HV and the lowest 82 HV, respectively. The microhardness is enhanced to a certain extent both in the weld central zone and fusion zone with the variation of variable polarity frequency in the HPVP-GTAW process due to the refinement and uniformity of weld microstructure. With the variable polarity frequency of 600 Hz, the microhardness in weld central zone and fusion zone reaches nearly 110 HV and 97 HV, respectively.

Evaluation of Geometric Quality of Weld Beads in the Joining of Carbon Steel Pipelines with Single Pass

This work presents the uncertainty evaluation associated with the measurement of linear parameters that define the weld geometry, specifically the width, using a profile projector, in order to meet the current technical standards. The following steps were proposed and implemented: identification of linear parameters that define the weld geometry;identification and study of variables that affect the measurement of these parameters;the adoption of the mathematical model to estimate the uncertainty;planning and execution of experiments for data collection, calculation of uncertainty and, finally, analysis and discussion of the results. Through the results analysis it was concluded that the weld in overhead position produces the lowest front bead width values and the vertical weld produces the largest width values. The expanded uncertainty values were between 0.016 mm and 0.075 mm for all measurements, and the overhead position showed, on average, the highest values.

Multi-objective Optimization of Welding Parameters in Submerged Arc Welding of API X65 Steel Plates

Submerged arc welding（SAW）is one of the main welding processes with high deposition rate and high welding quality.This welding method is extensively used in welding large-diameter gas transmission pipelines and high-pressure vessels.In welding of such structures,the selection process parameters has great influence on the weld bead geometry and consequently affects the weld quality.Based on Fuzzy logic and NSGA-II（Non-dominated Sorting Genetic Algorithm-II）algorithm,a new approach was proposed for weld bead geometry prediction and for process parameters optimization.First,different welding parameters including welding voltage,current and speed were set to perform SAW under different conditions on API X65 steel plates.Next,the designed Fuzzy model was used for predicting the weld bead geometry and modeling of the process.The obtained mean percentage error of penetration depth,weld bead width and height from the proposed Fuzzy model was 6.06%,6.40% and 5.82%,respectively.The process parameters were then optimized to achieve the desired values of convexity and penetration indexes simultaneously using NSGA-II algorithm.As a result,a set of optimum vectors（each vector contains current,voltage and speed within their selected experimental domains）was presented for desirable values of convexity and penetration indexes in the ranges of（0.106,0.168）and（0.354,0.561）respectively,which was more applicable in real conditions.