Pulsed Metal Inert Gas Welding Research Articles

Prediction of the quality of pulsed metal inert gas welding using statistical parameters of arc signals in artificial neural network

One of the big challenges in welding is the prediction of weld-quality without destructive test. This work introduces an intelligent system for weld-quality prediction in a pulsed metal inert gas welding process based on the statistical parameters of the acquired current and voltage signals. Six process parameters and 10 statistical parameters of arc signals are used to describe various welding conditions. These process features obtained from a set of experiments are employed as input patterns to back propagation neural network and radial basis function network models to predict the corresponding weld qualities. The prediction errors show that the neural network model, which has been trained with the statistical parameters of arc signals along with the process parameters, gives superior prediction of weld quality as compared to that from a model developed with only the process parameters as its inputs.

Multisensor-based monitoring of weld deposition and plate distortion for various torch angles in pulsed MIG welding

Manufacturing companies often fail to maintain good weld quality due to poor arc stability and distortion after welding. Weld quality can be improved by reducing the transverse shrinkage and the angular distortion in butt welding. The welding deposition efficiency is also an important economic factor. In this work, various pulse voltage parameters have been varied along with welding torch angle in pulsed metal inert gas (P-MIG) welding. The experimental results revealed that the peak voltage is the dominant pulse voltage parameter. Various sensors were also used to monitor arc current, arc voltage, arc sound, and also weld temperature. A strong relationship between arc sound (as well as arc power) and transverse distortion (as well as metal deposition) was found to exist in P-MIG welding. The frequency domain features of welding arc sound were also extracted and correlated to the process characteristics.

Study of weld joint strength using sensor signals for various torch angles in pulsed MIG welding

The present work focuses on the influence of pulse parameters at various torch angles on the tensile properties of low carbon steel butt weld in pulsed metal inert gas welding. The interface of weld zone and heat affected zone was found to be the weakest area due to significant variation of weld microstructure. The weld bead characteristics strongly influenced the joint strength. An infrared pyrometer and sound sensor have also been used along with arc sensors to monitor the weld quality. The arc power and arc sound kurtosis were found to be strongly correlated with weld quality.

Prediction of metal deposition from arc sound and weld temperature signatures in pulsed MIG welding

The weld deposition efficiency is an important economic factor like productivity and weld quality in gas metal arc welding (GMAW). There is a strong relationship between arc sound signals and arc stability (or deposition efficiency) in GMAW. In this work, the variation of weld deposition efficiency with various pulse parameters in pulsed metal inert gas welding was investigated. The arc sound signal along with current and voltage signals were acquired and analyzed in time domain as well as in frequency domain. The sound signal kurtosis and arc power were found to be highly correlated with welding process stability. The weld deposition efficiency was also related to weld surface peak temperature. Finally, an attempt was made to correlate the sound time domain as well as frequency domain features of sound signal with the deposition efficiency. The variation of pulse shape with the duty factor also influenced the deposition efficiency as evidenced by in fast Fourier transform analysis.

Optimization of quality characteristics parameters in a pulsed metal inert gas welding process using grey-based Taguchi method

Optimization of a manufacturing process has to take into accounts all of the factors that influence the product quality and productivity. Optimization of welding process parameters is considerably complex because welding is a multi-variable process, which is influenced by a lot of process uncertainties. In this paper, a grey-based Taguchi method has been adopted to optimize the pulsed metal inert gas welding process parameters. Many quality characteristic parameters are combined into one integrated quality parameter by using grey relational grade or rank. The welding process parameters considered in this analysis are pulse voltage, background voltage, pulse frequency, pulse duty factor, wire feed rate, and table feed rate. The quality parameters considered are the tensile strength, bead geometry, transverse shrinkage, angular distortion, and deposition efficiency. Analysis of variance has been performed to find out the impact of individual process parameter on the quality parameters. If the tensile strength as the most important quality parameter is assigned a higher weight, then the pulse voltage was found to be the most influential process parameter. Experiments with the optimized parameter settings, which have been obtained from the analysis, are given to validate the results.

Neurowavelet packet analysis based on current signature for weld joint strength prediction in pulsed metal inert gas welding process

The monitoring of welding process is crucial for the development of a real time quality control system for the pulsed metal inert gas welding (PMIGW) process. This work introduces an intelligent system for weld joint strength prediction in a PMIGW process based on the analysis of acquired current signal by wavelet packet transform. A thirteen-dimensional array of process features, i.e. six process parameters and seven wavelet packet features, are used to describe various welding conditions. These process features obtained from a set of experiments are employed as input vectors of an artificial neural network model to predict the corresponding weld joint strengths. The results, i.e. the prediction errors, show that the use of wavelet packet features gives much accurate prediction as compared to the use of the purely time domain features.

Joint strength prediction in a pulsed MIG welding process using hybrid neuro ant colony-optimized model

In this work, a pulsed metal inert gas welding (PMIGW) process is modeled by using a hybrid soft computing technique. Ant colony optimization (ACO) and back-propagation neural network (BPNN) models are combined to predict the ultimate tensile strength of butt-welded joints. A large number of experiments have been conducted, and comparative study shows that the hybrid neuro ant colony-optimized model produces faster and also better weld-joint strength prediction than the conventional back propagation model.

Sensor based weld bead geometry prediction in pulsed metal inert gas welding process through artificial neural networks

Weld quality is primarily determined from the weld bead geometry. This work concerns the weld bead geometry prediction in pulsed metal inert gas welding (PMIGW) process. A back propagation neural network (BPNN) model, a radial basis function network (RBFN) model and regression model have been developed to predict the weld bead geometry of welded plates. Six process parameters, namely pulse voltage, back-ground voltage, pulse duty factor, pulse frequency, wire feed rate and the welding speed along with root mean square (RMS) values of two sensor signals, namely the welding current and the voltage signals, are used as input variables of the two models. The weld bead width, height and reinforcement of the welded plate are considered as the output variables. Having same process parameters does not always result in the same output quality. This is why, inclusion of sensor signals in the models, as developed in this work, results in better output prediction.

Radial basis function neural network model based prediction of weld plate distortion due to pulsed metal inert gas welding

Welding shrinkage and distortion affect the shape, dimensional accuracy and strength of the finished product. This work concerns the prediction of welding distortion in a pulsed metal inert gas welding (PMIGW) process. Six different types of radial basis function network (RBFN) models have been developed to predict the distortion of welded plates. Six process parameters, namely, pulse voltage, background voltage, pulse duty factor, pulse frequency, wire feed rate and the welding speed, along with the root mean square (RMS) values of two sensor signals, namely, the welding current and the voltage signals, are used as input variables of these models. The angular distortion and the transverse shrinkage of the welded plate are considered as the output variables. Inclusion of sensor signals in the models, as developed in this work, results in better output prediction.

Artificial neural network modeling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals

This paper addresses the weld joint strength monitoring in pulsed metal inert gas welding (PMIGW) process. Response surface methodology is applied to perform welding experiments. A multilayer neural network model has been developed to predict the ultimate tensile stress (UTS) of welded plates. Six process parameters, namely pulse voltage, back-ground voltage, pulse duration, pulse frequency, wire feed rate and the welding speed, and the two measurements, namely root mean square (RMS) values of welding current and voltage, are used as input variables of the model and the UTS of the welded plate is considered as the output variable. Furthermore, output obtained through multiple regression analysis is used to compare with the developed artificial neural network (ANN) model output. It was found that the welding strength predicted by the developed ANN model is better than that based on multiple regression analysis.

Evaluation of cold metal transfer (CMT) process for welding aluminium alloy

Cold metal transfer (CMT) is an automated welding process based on dip transfer welding, characterised by controlled material deposition during the short circuit of the wire electrode to the workpiece. Preliminary results are presented examining the suitability of this process for welding aluminium alloy. Trials show that in comparison with pulsed metal inert gas (MIG) welding, CMT exhibits a higher electrode melting coefficient. By adjusting the short circuit duration penetration can be controlled with only a small change in electrode deposition. Furthermore, by mixing pulsed MIG welding with CMT welding the working envelope of the process is greatly extended allowing thicker material sections to be welded with improved weld bead aesthetics.

Observations of the phenomenon of abnormal arc voltage occurring in pulsed metal inert gas welding of aluminium alloy

At the time of arc reignition after short circuiting during electrode positive polarity, cathode spots are newly formed in the centre of the weld pool surface, where oxides scarcely exist. The work function of the cathode surface increases and the cathode spots concentrate because of the lack of sufficient oxides, leading to an increase in the potential gradient across the cathode fall space and the adjoining contraction space. Consequently, the arc voltage becomes abnormally high in spite of the short arc length. Moreover, when electrode polarity is switched from positive to negative immediately after a droplet has detached from the wire tip, cathode spots are newly formed on the surface of the molten metal remaining at the wire tip, where little oxide exists, leading to an abnormal increase in arc voltage as well. Therefore, the change in arc voltage does not necessarily indicate a fluctuation in the arc length.

High speed welding of aluminium alloy sheets using laser assisted alternating current pulsed metal inert gas process

Abstract Alternating current pulsed metal inert gas welding is an appropriate process for joining aluminium alloy sheets because of its great gap tolerance and low heat input, which assists in avoiding burn through. However, when welding speed is higher than 2 m min-1 the low heat input is no longer an advantage since lack of penetration becomes a problem. Irradiation of the vicinity of the arc using a laser beam can solve this problem, and adjustment of the laser power can control the penetration. As a result, thin aluminium alloy sheets can be joined at a high speed of 4 m min-1 with sufficient gap tolerance. Moreover, investigation of the effect of laser beam diameter on the resulting weld for thin sheets indicates that a defocused laser beam having a diameter of several millimetres can further improve the ability to bridge joint gaps and tolerance of deviations in torch aim. Consequently, a high power diode laser having a relatively thick beam waist is suitable for this application.

Development of adaptive control system for alternating current pulsed metal inert gas welding parameters

A three-dimensional laser sensor is combined with an alternating current pulsed metal inert gas welding robot system to detect information about the variation of joint gap width and deviation of the joint position relative to the welding torch. Together with the joint tracking and torch direction adjustment, electrode negative polarity ratio and welding speed are also controlled adaptively according to the variation of joint gap width during welding. As a result, a high tolerance of joint gap variation is obtained and bead shape becomes more uniform and of reasonable quality in welding of aluminium alloy sheets.

Quality and productivity improvement in aluminium alloy thin sheet welding using alternating current pulsed metal inert gas welding system

An alternating current (ac) pulsed metal inert gas (MIG) welding power source has been developed for welding thin sheets of aluminium alloys and the process features are investigated. Advantages such as high wire melting coefficient, low heat input, shallow penetration, and increased reinforcement height are obtained at high values of electrode negative ratio (ratio of electrode negative current integration to electrode negative plus electrode positive current integration over one pulse cycle). These features successfully counteract the problem of burnthrough in welding of thin sheet joints and greatly improve the bridging ability for wide gap joints. Thin sheet joints can be welded at high speed and with low distortion. By integrating the present welding power source with a welding robot, welding process and current waveform parameters can be defined by key operations in the teach pendant. It is possible to switch between welding processes such as ac pulsed MIG, direct current (dc) pulsed MIG, low frequency modulated ac pulsed MIG, and low frequency modulated dc pulsed MIG during a continuous welding run, so that the optimum welding process can always be selected.

Influence of Pulsed Current Welding on the Microstructure and Porosity Content of Al-Zn-Mg Alloy Weldment / Einfluß des Schweißens mit pulsierender Stromstärke auf das Gefüge und die Porösität von Schweißungen an einer Al-Zn-Mg-Legierung

At different levels of mean current (150, 180 and 210A) the effect of pulse frequency, varied from 0 to 100 Hz, on the extent to recrystallization at heat affected zone (HAZ) and the microstructure and porosity content of weld deposit are investigated, during pulsed metal inert gas (MIG) welding of an Al-Zn-Mg alloy. The observations of pulsed current welding are compared with those found in conventional continuous current welding process