Prediction of weld quality in pulsed current GMAW process using artificial neural network

Abstract

Weld joint dimensions and weld metal mechanical properties are important quality characteristics of any welded joint. The success of building these characteristics in any welding situation depends on proper selection-cum-optimisation of welding process parameters. Such optimisation is critical in the pulsed current gas metal arc welding process (GMAW-P), as the heat input here is closely dictated by a host of additional pulse parameters in comparison to the conventional gas metal arc welding process. Neural network based models are excellent alternatives in such situations where a large number of input conditions govern certain outputs in a manner that is often difficult to adjudge a priori. Six individual prediction models developed using neural network methodology are presented here to estimate ultimate tensile strength, elongation, impact toughness, weld bead width, weld reinforcement height and penetration of the final weld joint as a function of four pulse parameters, e.g. peak current, base current, pulse on time and pulse frequency. The experimental data employed here are for GMAW-P welding of extruded sections of high strength Al–Zn–Mg alloy (7005). In each case, a committee of different possible network architectures is used, including the final optimum network, to assess the uncertainty in estimation. The neural network models developed here could estimate all the outputs except penetration fairly accurately.     

Weld pool shape prediction in plasma augmented laser welded steel

Abstract

A welding process that combined plasma arc welding with laser welding was used to make autogenous bead on plate welds on a sheet stock of a carbon steel. A wide range of welding parameters (arc current, laser power, weld speed) was employed. The experimental weld pool shapes were analysed and the data were used to train a neural network to predict weld pool shape as a function of process conditions. The predictions of the neural network model showed excellent agreement with the experimental results, indicating that a neural network model is a viable means for predicting weld pool shape. Using the model, a parametric study was carried out to examine the influence of process conditions on the final weld pool profile.     

Optimisation of hybrid tandem metal active gas welding using Gaussian process regression

In this paper, an additional filler wire with opposite polarity was inserted in tandem flux cored arc welding process to increase the welding speed and deposition rate. In this hybrid welding, the optimisation of welding parameters is required to improve the bead geometry which directly indicates the welding quality. However, the correlation between the parameters and the bead geometry is hard to identify, so the process parameters are usually selected intuitively by the experienced engineers. Therefore, welding process modelling is constructed with the Gaussian process regression model, and parameter optimisation is performed with sequential quadratic programming optimisation algorithm. The proposed modelling optimisation process is verified by performing the welding experiment using the parameters that are optimised by the proposed process.     

Thermal elastic‐plastic stress‐strain analysis considering temperature rise due to plastic deformation under dynamic loading in undermatched joints study of dynamic deformation and fracture properties of welded joints with strength heterogeneity (Report 1)

Summary

This paper describes an automatic welding system that can simultaneously control the bead height and back bead shape during one‐sided MAG welding with a backing plate. The system uses a high‐speed rotating arc welding process together with an arc sensing technique for seam tracking and torch height control.

The arc sensing technique is also used to detect variations in the groove shape. The detection mechanism is described in detail in this paper.

The system further uses a newly developed welding parameter control method in which only the wire feedrate and welding voltage are adaptively controlled, the other welding conditions being kept constant. This method is able to keep the bead height constant and retain the back bead shape even if the groove shape changes.

Initial welding experimental results have shown the system to be effective and satisfactory for controlling the weld bead shape in one‐sided GMAW (MIG/MAG) with a backing plate.     

Prediction of bead geometry in pulsed GMA welding using back propagation neural network

This paper presents the development of a back propagation neural network model for the prediction of weld bead geometry in pulsed gas metal arc welding process. The model is based on experimental data. The thickness of the plate, pulse frequency, wire feed rate, wire feed rate/travel speed ratio, and peak current have been considered as the input parameters and the bead penetration depth and the convexity index of the bead as output parameters to develop the model. The developed model is then compared with experimental results and it is found that the results obtained from neural network model are accurate in predicting the weld bead geometry.     

基于神经网络模型的P-GMAW焊缝成形过程仿真

脉冲熔化极气体保护焊(P-GMAW)是一种高效、适应性强的焊接方法之一,在工业生产中得到了广泛的应用.文中以低碳钢P-GMAW为对象,研究其焊缝成形过程的建模与仿真方法.文中首先利用BP神经网络,建立了该过程的动态模型,然后利用该模型的稳态与动态仿真揭示了P-GMAW过程的成形规律.同时,文中提出了一种利用神经网络模型...     

Artificial neural networks and acoustic emission applied to stability analysis in gas metal arc welding

Abstract

The present paper describes the application of neural networks to obtain a model for estimating the stability of gas metal arc welding (GMAW) process. A neural network has been developed to obtain and model the relationships between the acoustic emission (AE) signal parameters and the stability of GMAW process. Statistical and temporal parameters of AE signals have been used as input of the neural networks; a multilayer feedforward neural network has been used, trained with back propagation method, and using Levenberg Marquardt's algorithm for different network architectures. Different welding conditions have been studied to analyse the incidence of the parameters of the process in acoustic signals. The AE signals have been processed by using the wavelet transform, and have been characterised statistically. Experimental results are provided to illustrate the proposed approach. Finally a statistical analysis for the validation of the experimental results obtained is presented. As a main result of the study, the effectiveness of the application of the artificial neural networks for modelling stability analysis in welding processes has been demonstrated. The regression analysis demonstrates the validity of neural networks to predict the stability of welding process using the statistical characterisation of the signal parameters of AE that have been calculated.     

Sensitivity model for prediction of bead geometry in underwater wet flux cored arc welding

To investigate influence of welding parameters on weld bead geometry in underwater wet flux cored arc welding (FCAW), orthogonal experiments of underwater wet FCAW were conducted in the hyperbaric chamber at water depth from 0.2 m to 60 m and mathematical models were developed by multiple curvilinear regression method from the experimental data. Sensitivity analysis was then performed to predict the bead geometry and evaluate the influence of welding parameters. The results reveal that water depth has a greater influence on bead geometry than other welding parameters when welding at a water depth less than 10 m. At a water depth deeper than 10 m, a change in travel speed affects the bead geometry more strongly than other welding parameters.     

基于神经网络的药芯焊丝GMAW发尘率预测

焊接工艺对焊接发尘率有直接的影响,建立基于相关焊接工艺参数的焊接发尘率预测模型,预测特定焊接工艺的发尘率对控制和降低焊接烟尘的排放具有重要意义。鉴于焊接发尘率影响因素复杂,存在高度非线性特征,提出了基于神经网络的熔化极气体保护焊(GMAW)焊接发尘率的预测模型。通过药芯焊丝E501T-1发尘率实测数据,分别建立了BP和Elman神经网络模型,并采用遗传算法(GA)对2种神经网络进行了优化。基于15组实测数据的验证,结果表明,采用遗传算法优化后,BP和Elman神经网络模型的预测合格率分别提升了6.7%和13.4%,遗传算法优化的BP神经网络模型(GA-BP)的均方误差为586.21,平均绝对百分比误差为3.01%,均为4个模型中最小,其预测结果更为准确可靠。基于GA-BP模型所预测数据,对不同焊接电流和电弧电压的发尘率进行预测,在一定的焊接速度和保护气流量条件下,焊接电流约为170 A,电弧电压约为26 V时,焊接发尘率最小。 创新点： (1)将神经网络模型引入到焊接发尘率数值预测中,并通过遗传算法对神经网络的权值和阈值进行优化,提高了预测准确性和可靠性。 (2)根据优化后的模型的预测结果,分析了焊接电流和电弧电压对发尘率的影响规律,为进一步控制焊接发尘率提供了有益的指导。     

Occurrence of bay area in submerged arc welds

Abstract

An experimental study has been carried out to evaluate the effect of submerged arc welding parameters on the formation of a bay area in the heat affected zone of bead on plate welds in ASTM A36 steel. It was observed that the formation of weld beads having a bay area is influenced by the heat distribution from the arc, which in turn is determined by the welding conditions. The effect of the welding parameters on the weld bead formation is discussed in terms of the arc operation modes and the resulting heat distributions.     

APPLICATION OF ARTIFICIAL NEURAL NETWORK MODELING TO PLASMA ARC WELDING OF ALUMINUM ALLOYS

1.Weldingisacomplicatedprocesswhichisnoallnear,variable--coupledandrandom,soitissodifficulttofindaaccuratelawthatwehavetodependonscientificessaily.Ihrecentyears,autOInationOfarcweldingProcess,whichisbasedoninduStrialrobots,hasbeentakenPublicopinionseriously,andthebasisofconedofweldingPIDCessistoestablishinathernaticalmodelOfweldingprocessandweldingqUality'AtPreSent,weOftenuseformulaOfrecessionexperiencetosatisfytheneedOfweldingtechaology.aamrecessionmodelcanbeusedtOfindstatisticallawout…     

基于Elman网络算法的Inconel625合金堆焊稀释率的控制

文中建立了5-8-3结构的反馈Elman神经网络模型,以电弧长度、焊接电流、焊接速度、送丝速度和保护气流量为输入量,堆焊焊缝的熔宽、熔高和稀释率为输出量进行堆焊仿真计算分析.计算结果表明,Elman模型的预测结果比BP和GRNN神经网络更精确.建立了以电弧长度（X）、堆焊电流（Y）和送丝速度（Z）为空间坐标,堆焊稀释率δ等于f（X,Y,Z）为目标函数的四维图像来确定δ≤5%的堆焊工艺窗口.分别进行Elman模型仿真计算和堆焊工艺试验,得到的稀释率δ分别为2.55%和3.32%,仿真计算的稀释率的相对误差约0.8%,证实了Elman模型预测的Inconel625合金堆焊工艺窗口的可行性与可靠性.     

一种冷丝填充速度的GABP优化算法

冷丝填充埋弧焊过程中,冷丝填充量是决定焊缝组织和性能的主要参数.通过大量的工艺试验研究了冷丝填充量对微观组织和力学性能的影响,利用焊接电弧热平衡规律建立了冷丝填充过程热量动态分配平衡方程,推导出了计算冷丝填充速度的关系式.采用人工神经网络实现了焊接电流、电弧电压、焊接速度与冷丝填充速度的非线性映射关系.结果表明,基于遗传算法的BP神经网络(BP neural network based on genet-ic algorithm,GABP)优化算法实现了冷丝填充埋弧焊过程的自适应控制,实际焊接冷丝填充速度与期望值之间的线性相关度达到0.991 88,表明该算法可以满足冷丝填充埋弧焊工艺及性能要求.     

Neural network model of heat and fluid flow in gas metal arc fillet welding based on genetic algorithm and conjugate gradient optimisation

Abstract

Although numerical calculations of heat transfer and fluid flow can provide detailed insights into welding processes and welded materials, these calculations are complex and unsuitable in situations where rapid calculations are needed. A recourse is to train and validate a neural network, using results from a well tested heat and fluid flow model to significantly expedite calculations and ensure that the computed results conform to the basic laws of conservation of mass, momentum and energy. Seven feedforward neural networks were developed for gas metal arc (GMA) fillet welding, one each for predicting penetration, leg length, throat, weld pool length, cooling time between 800°C and 500°C, maximum velocity and peak temperature in the weld pool. Each model considered 22 inputs that included all the welding variables, such as current, voltage, welding speed, wire radius, wire feed rate, arc efficiency, arc radius, power distribution, and material properties such as thermal conductivity, specific heat and temperature coefficient of surface tension. The weights in the neural network models were calculated using the conjugate gradient (CG) method and by a hybrid optimisation scheme involving the CG method and a genetic algorithm (GA). The neural network produced by the hybrid optimisation model produced better results than the networks based on the CG method with various sets of randomised initial weights. The CG method alone was unable to find the best optimal weights for achieving low errors. The hybrid optimisation scheme helped in finding optimal weights through a global search, as evidenced by good agreement between all the outputs from the neural networks and the corresponding results from the heat and fluid flow model.     

Sensitivity analysis for process parameters in GMA welding processes using a factorial design method

Generally, the quality of a weld joint is strongly influenced by process parameters during the welding process. In order to achieve high quality welds, mathematical models that can predict the bead geometry and shape to accomplish the desired mechanical properties of the weldment should be developed. This paper focuses on the development of mathematical models for the selection of process parameters and the prediction of bead geometry (bead width, bead height and penetration) in robotic GMA (Gas Metal Arc) welding. Factorial design can be employed as a guide for optimization of process parameters. Three factors were incorporated into the factorial model: arc current, welding voltage and welding speed. A sensitivity analysis has been conducted and compared the relative impact of three process parameters on bead geometry in order to verify the measurement errors on the values of the uncertainty in estimated parameters. The results obtained show that developed mathematical models can be applied to estimate the effectiveness of process parameters for a given bead geometry, and a change of process parameters affects the bead width and bead height more strongly than penetration relatively.     

Sensitivity analysis of submerged arc welding process parameters

Selection of process parameters has great influence on the quality of a welded connection. Mathematical modelling can be utilized in the optimization and control procedure of parameters. Rather than the well-known effects of main process parameters, this study focuses on the sensitivity analysis of parameters and fine tuning requirements of the parameters for optimum weld bead geometry. Changeable process parameters such as welding current, welding voltage and welding speed are used as design variables. The objective function is formed using width, height and penetration of the weld bead. Experimental part of the study is based on three level factorial design of three process parameters. In order to investigate the effects of input (process) parameters on output parameters, which determine the weld bead geometry, a mathematical model is constructed by using multiple curvilinear regression analysis. After carrying out a sensitivity analysis using developed empirical equations, relative effects of input parameters on output parameters are obtained. Effects of all three design parameters on the bead width and bead height show that even small changes in these parameters play an important role in the quality of welding operation. The results also reveal that the penetration is almost non-sensitive to the variations in voltage and speed.     

Research on laser-arc hybrid welding of lap fillet joints of thin sheet

ABSTRACT

Laser welding is capable of welding at high speeds by high-density energy, while arc welding is an effective construction method from the viewpoint of tolerance of the gap and welding position. Laser-arc hybrid welding has both these features. The authors have researched suitable welding parameters and consumables for this hybrid welding process that couples laser beam with MAG arc for lap fillet weld joining of thin steel sheets. As a result, the following welding parameters have been proven to be the most appropriate for better bead shapes and root-gap tolerance, i.e. laser leading (kept at a right angle) and MAG trailing (kept at a push angle); the laser-arc distance was 3 mm and the laser beam focus size was 2 mm. In addition, it was proven that HT490-class welding wire of Si-Mn-Ti type (JIS YGW11) was the most appropriate for better bead shapes and root-gap tolerance. The bead shape was apt to be better in cases of higher surface tension of welding wire. The result of the tensile shear test of the joint by welding with HT490-class welding wire of Si-Mn-Ti type (JIS YGW11) under selected welding condition demonstrated that the value of the tensile strength of parent material was equal to that of lab fillet joints.     

电弧焊熔透ICA-BP神经网络识别模型

以氩弧焊熔透状态识别为研究对象,研究一种基于ICA (Imperialist Competitive Algorithm) 的BP(Back Propagation)神经网络识别模型方法. 首先利用ICA全局搜索不易陷入局部极值及搜索速度快的特点对神经网络权值和阈值初始化,再用BP算法对神经网络进行训练. 通过摄取焊接过程中的熔池图像,提取熔池面积、熔宽以及熔池质心位置作为神经网络预测模型的输入量,分析熔池图像三个特征与焊缝熔透状态的映射关系,最终建立熔透状态预测模型. 结果表明,采用ICA-BP神经网络能够有效地预测焊缝的熔透状态.     

Application of neural network to arc sensor

Abstract

Full penetration control of the weld pool in the first layer of a single side multilayer weldment is important to obtain a good quality weld. For this purpose, a new method, the switchback welding method, is proposed to achieve a stable back bead. A welding torch not only weaves along the groove, but also moves back and forth. Also, a neural network (NN) arc sensor is proposed that estimates the wire extension and the arc length by using measurements of both voltage and current. Moreover, from the output of the NN, the gap and the error (deviation) of the oscillation centre of the torch from the groove centre are estimated. Training data are constructed from experimental results, and performance of the NN arc sensor is examined using test data. Seam tracking is carried out via the output of the NN arc sensors: a good tracking result is obtained.     

大功率盘形激光焊接过程等离子体图像特征分析

研究一种基于等离子体图像特征的大功率盘形激光深熔焊质量分析及检测的新方法．以大功率盘形激光焊接Type 304不锈钢板为试验对象,应用高速摄像机摄取焊接过程中的等离子体图像,通过图像处理技术提取等离子体的面积和高度特征．以熔宽作为衡量焊接过程稳定性的因素,对比焊接过程中等离子体图像和焊接试件的熔宽变化,研究相邻等离子体...