Multisensor information fusion of pulsed GTAW based on improved D-S evidence theory

The D-S evidence theory is a method widely used in information fusion technology, but it cannot solve the conflict evidence problem. This paper proposed a new method to dispose the conflict evidence problem in D-S evidence theory. The method first used evidence distance to obtain the weights of different evidences, then fuzzy inference theory was used to adjust the basic probability assignments (BPA) of every evidence according to the obtained weights, and the adjusted BPAs were fused by the D-S combine rules to obtain the fusion results in the end. The method was used in pulsed gas tungsten arc welding (GTAW) and fused the information obtained by arc, sound, and visual sensors in pulsed GTAW process. Experiment results showed that the method could effectively solve the conflict evidence problem, sufficiently fuse different sensors' information, and obtain more precise results than using a single sensor alone.     

A study of multisensor information fusion in welding process by using fuzzy integral method

Multisensor information fusion technology in welding process was studied, and Choquet fuzzy integral method was used in this paper to fuse the information obtained by arc, sound, and visual sensors in pulsed gas tungsten arc welding (GTAW) process. A novel method to obtain the fuzzy set function values in fuzzy integral was proposed to obtain the prediction results of single sensor, and a method by using supporting degrees of different sensors was proposed to obtain the fuzzy measure function values in fuzzy integral. Choquet fuzzy integral was used to fuse the information after the fuzzy set function and fuzzy measure values were obtained, and the multisensor information fusion model based on the method was proposed. Experiment was done to test the effectiveness of the method in the end.     

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.     

Optimizing pulsed current parameters to minimize corrosion rate in gas tungsten arc welded titanium alloy

The preferred process for welding titanium alloy is frequently gas tungsten arc (GTA) welding due to its comparatively easier applicability and better economy. Weld fusion zones of this alloy typically exhibit coarse columnar grains and lead to inferior mechanical and metallurgical properties. In the case of single pass GTA welding of a thinner section of this alloy, the pulsed current has been found to be beneficial primarily due to grain refinement of the weld fusion zone over the conventional continuous current process. Fusion zone grain refinement is controlled by pulsed current parameters such as peak current, back ground current, pulse frequency and pulse-on-time. In this investigation, a mathematical model has been developed to predict corrosion rate of gas tungsten arc welded titanium alloy by incorporating pulsed current parameters. Four factors, five level, central composite, rotatable design matrix has been used to minimize the experimental conditions. A mathematical model has been developed by response surface method (RSM). The developed model has been optimized using genetic algorithm (GA) and contour plots to attain minimum corrosion rate in the weld fusion zone.     

基于D-S理论和BP网络的驾驶行为识别技术研究

提出了BP神经网络与D-S证据理论相结合的驾驶行为识别、预测方法;将汽车行驶过程中人-车-路的信息作为BP神经网络的输入,利用BP神经网络对驾驶行为进行初步识别,并将BP神经网络输出的结果归一化处理后作为D-S证据理论的基本概率分布;利用证据距离理论对证据进行证据冲突处理,通过D-S证据组合理论对输入信息进行综合分析处理,决策识别出当前的驾驶行为;利用MATLAB语言编写了仿真测试程序,仿真结果表明该方法能够准确的识别出当前的驾驶行为。     

Three-dimensional vision-based sensing of GTAW: a review

Automated and robotic welding is now widely used in manufacturing industry. The control of the welding process plays a crucial role in producing quality welds in automated and robotic welding where the assistance from skilled welders is no longer available. In gas tungsten arc welding (GTAW) which is the primary arc welding process for precision joining of metals, the weld pool is the major source of information that can be used to assure the production of desired weld penetration which is the most critical factor determining the weld integrity. To meet this challenge, various sensing technologies have been proposed/studied to sense and obtain the feedback for the weld pool state. This paper summarizes the researches on weld pool state sensing: conventional sensing technologies, vision sensing technology, and multi-sensor information fusion technology, with emphasis on the analysis of three-dimensional vision sensing methods. And three-dimensional vision sensing, multi-sensor technology, intelligent modeling, and effective commercial product development show the future trends of GTAW penetration sensing.     

Optimization of pulsed GTA welding process parameters for the welding of AISI 304L stainless steel sheets

Optimization of pulsed gas tungsten arc welding (pulsed GTAW) process parameters was carried out to obtain optimum weld bead geometry with full penetration in welding of stainless steel (304L) sheets of 3 mm thickness. Autogenuous welding with square butt joint was employed. Design of experiments based on central composite rotatable design was employed for the development of a mathematical model correlating the important controllable pulsed GTAW process parameters like pulse current (I _p), pulse current duration (T _p), and welding speed (S) with weld bead parameters such as penetration, bead width (W), aspect ratio (AR), and weld bead area of the weld. The developed models were checked for adequacy based on ANOVA analysis and accuracy of prediction by conducting a confirmation test. Weld bead parameters predicted by the models were found to confirm observed values with high accuracy. Using these models, the main and interaction effects of pulsed GTAW process parameters on weld bead parameters were studied and discussed. Optimization of pulsed GTAW process parameters was carried out to obtain optimum bead geometry using the developed models. A quasi-Newton numerical optimization technique was used to solve the optimization problem and the results of the optimization are presented.     

Optimization of Inconel 718 alloy welds in an activated GTA welding via Taguchi method, gray relational analysis, and a neural network

The purpose of this work is to optimize the weld bead geometry of Inconel 718 alloy gas tungsten arc (GTA) welds that are coated with activating flux before welding. In order to obtain the optimal welding parameters with multiple quality characteristics (QCs) such as penetration and depth-to-width ratio (DWR) of weld bead, the Taguchi method (TM), gray relational analysis (GRA), and a neural network (NN) are employed in this work. The TM is first used to construct a database for the NN. The GRA is adopted to solve the problem of multiple QCs. The gray relational grade (GRG) obtained from the GRA is used as the output of the backpropagation (BP) NN. Then, a NN with the Levenberg–Marquardt BP (LMBP) algorithm is used to provide the nonlinear relationship between welding parameters and GRG of each specimen. The optimal parameters of the activated GTA welding process are determined by simulating parameters using a well-trained BPNN model. The experimental procedure of the proposed approach not only improves the DWR of weld bead but also increases the penetration of Inconel 718 alloy welds.     

Obtaining weld pool vision information during aluminium alloy TIG welding

An image sensing system for the TIG (tungsten inert-gas arc) welding process of aluminium alloy was established. The relationships between the image sensing system and the characteristic of welding current were discussed in detail. Front and back images of the weld pool were obtained with different welding parameters. In order to process the image, the characteristics of an aluminium alloy were analysed. Image processing and pattern recognition were first used to obtain information from the TIG welding process for aluminium alloy. The image of the weld pool was pre-processed using a series of methods: a weighted median filter, a statistical threshold by expectation and the projection method. A neural network method was used to extract the edge of the images of the weld pool. The result of detecting the edge with a BP neural network were excellent. The symmetry of the weld pool for aluminium alloy was studied when the welding current is large. The edge of the image of the whole weld pool is obtained in a single side image and an accurate method for measuring the weld pool geometry parameter is provided. Experiments show that using the image sensing to control the TIG weld width for aluminium alloy is an effective method.     

激光焊匙孔特征的近红外与X射线传感分析

由于多传感匙孔特征参数可以有效地反映大功率激光焊接质量状态,本文研究了匙孔特征信息的提取方法并建立了焊缝成形预测模型。以大功率盘形激光焊接304不锈钢为试验对象,应用近红外高速摄像机和X射线视觉成像系统同时提取了焊接过程中的熔池动态图像,并分割出匙孔区域。针对近红外图像,应用矩方法导出匙孔的不变矩特征,同时定义并提取匙孔面积和最前端点纵坐标两个特征;针对X射线图像则提取匙孔深度和熵两个特征。在不同激光功率条件下得到匙孔特征并进行特征融合分析,然后建立了3个BP神经网络焊缝成形预测模型。探索了匙孔形态、焊接条件和焊接状态三者之间的联系,实现了对焊接过程的在线监测。试验结果表明,将两个传感器获取的匙孔特征信息融合并进行主成分分析变换后,熔宽和熔深的预测绝对误差平均值分别为0.18mm和0.57mm,比基于单个传感器获取匙孔特征建立的BP神经网络分别减小了0.03mm和0.31mm,显示提出的方法能够有效在线监测大功率盘形激光焊接状态。     

低功率激光诱导电弧复合焊接钛合金薄板工艺研究

采用低功率脉冲YAG激光诱导非熔化极惰性气体保护(Tungsten inert gas,TIG)焊电弧复合热源实现了1 mm厚TC4钛合金薄板的优质焊接,研究激光诱导电弧复合焊接过程中热源能量匹配、热源间角度、对接间隙对焊缝成形的影响规律。结果表明,钛合金薄板低功率脉冲YAG激光诱导TIG电弧复合热源焊接过程中,激光能量与电弧能量之间的相互匹配将显著影响焊缝的表面成形。相对于电弧功率的变化,焊缝成形对激光功率变化的敏感度更高。随着热源间角度减小,激光诱导电弧复合热源传热能力增强;由于复合焊接速度快、热输入小、焊接试板横向变形小,当对接间隙为0~0.5 mm范围内时均能获得良好的焊缝成形。为了使焊缝成形均匀连续,焊接过程中需要对焊缝背面采用氩气进行保护,当保护气体流量为5~8L/min时获得最佳焊接接头。     

ARTIFICIAL NEURAL NETWORK AND FUZZY LOGIC CONTROLLER FOR GTAW MODELING AND CONTROL

0 INTRODUCTION(The satisfied control of the overall weld process is not easily accomplished, largely due to the inadequacies of the available process models. Without exceptions, most welding control methods are based upon the analytical welding models. Although these models are derived directly from the physical laws that govern the main features of the weld pool, a number of assumptions are made to obtain the mathematical solutions and some variables are ignored due to the complexity of t…     

Real-time control of welding penetration during robotic GTAW dynamical process by audio sensing of arc length

This paper presents a new technology of real-time arc length monitoring and sag-depression prediction through arc sound signal, which is essential to realize the welding penetration control during gas tungsten arc welding of arc length. A set of automatic measurement and control system have been proposed to achieve real-time arc length control via audio sensing system. After preprocessing of arc sound signal, the piecewise linear models of arc sound signal were established under two different arc length variation 3–4 and 4–5–6 mm, analyzing the prediction errors of linear model, which were proved to be good enough for online monitoring of arc length in pulse GTAW. Based on the linear relationship between arc sound and arc length, the linear fitting model was implemented on predicting the surface height of weld pool. A segmented self-adaptive PID controller was proposed to achieve the monitoring and controlling of arc length;, the confirmatory experiments have been designed to test the control effect of arc-length monitoring based on arc sound signal.     

不锈钢AA-TIG焊接法

针对不锈钢,提出一种新型活性TIG焊方法——电弧辅助活性TIG焊,即AA-TIG焊。采用CO2+Ar作为小电流钨极电弧的保护气体进行单弧AA-TIG焊,分别研究小电流钨极电弧和正常TIG焊工艺参数对焊缝熔深的影响,并针对试验范围内的最佳焊接规范研究不锈钢AA-TIG焊的焊缝成形、焊缝显微组织、化学成分和焊缝性能。采用AA-TIG焊可以单道焊透10mm厚的不锈钢板材,单面焊双面成形。与传统TIG焊相比,焊缝组织和化学成分几乎没有变化,焊缝的耐Cu/CuSO4腐蚀性能和低温冲击韧度都满足相关标准要求。     

基于信息融合的滚动轴承故障诊断

滚动轴承故障诊断中同一征兆域很难区分多种故障，单一传感器对故障分类识别有不确定性。提出了利用加速度传感器和声音传感器，基于BP神经网络及D-S证据理论，对所采集的振动信号和声音信号的多种特征信号进行信息融合，实现故障诊断。并对该方法进行仿真试验验证。     

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.     

Robot welding seam tracking method based on passive vision for thin plate closed-gap butt welding

A passive vision sensor is added to a teaching and playback welding robot for pulsed gas tungsten arc welding, which is normally used in the welding of thin plate closed-gap butts. This paper presents a seam tracking method based on this sensor through period visual measurement of the offset between the torch and the seam center. A robust image processing algorithm is developed to extract the seam center. A kind of ARX(auto-regressive with exogenous input) model is studied to describe the relationship between the rectifying voltage and the offset. The fuzzy PID(proportional-integral-derivative) seam tracking controller is analyzed and designed in consideration of various offsets based on the ARX model. The experimental results on straight line weld display a good seam tracking capability of the proposed method.     

Effect of pulsed current welding on mechanical properties of high strength aluminum alloy

High strength aluminum alloys (Al-Zn-Mg-Cu alloys) have gathered wide acceptance in the fabrication of lightweight structures requiring high strength-to-weight ratio, such as transportable bridge girders, military vehicles, road tankers and railway transport systems. The preferred welding processes of high strength aluminum alloy are frequently the gas tungsten arc welding (GTAW) process and the gas metal arc welding (GMAW) process due to their comparatively easy applicability and better economy. Weld fusion zones typically exhibit coarse columnar grains because of the prevailing thermal conditions during weld metal solidification. This often results in inferior weld mechanical properties and poor resistance to hot cracking. In this investigation, an attempt has been made to refine the fusion zone grains by applying a pulsed current welding technique. Rolled plates of 6 mm thickness were used as the base material for preparing single pass welded joints. A single ‘V’ butt joint configuration was prepared for joining the plates. The filler metal used for joining the plates was AA 5356 (Al-5Mg (wt%)) grade aluminum alloy. Four different welding techniques were used to fabricate the joints: (1) continuous current GTAW (CCGTAW), (2) pulsed current GTAW (PCGTAW), (3) continuous current GMAW (CCGMAW) and (4) pulsed current GMAW (PCGMAW). Argon (99.99% pure) was used as the shielding gas. Tensile properties of the welded joints were evaluated by conducting tensile tests using a 100 kN electro-mechanical controlled universal testing machine. Current pulsing leads to relatively finer and more equi-axed grain structure in GTA and GMA welds. In contrast, conventional continuous current welding resulted in predominantly columnar grain structures. Grain refinement is accompanied by an increase in tensile strength and tensile ductility.     

A variable precision rough set based modeling method for pulsed GTAW

Modeling is an important step both for quality and shaping control of the arc welding process. Current modeling methods have made great advances in the field of arc welding, however they all posses certain limitations. It is due to these limitations that we created the variable precision rough set (VPRS) based modeling method. The VPRS modeling has been shown to be both a more efficient and reliable modeling method for the arc welding process due to its ability to account for the character of the welding media. The method was used to produce a dynamic predictive model for pulsed gas tungsten arc welding (GTAW). Results showed that the VPRS modeling method was able to sufficiently acquire knowledge during welding practices. In addition, comparison of VPRS model with classic rough set model and BP neural network model showed that VPRS model was more stable and could predict the unseen data better than classic RS model. Moreover, the VPRS model owns similar precision with neural network model, but has better understandability.     

Effects of Active Gases on Droplet Transfer and Weld Morphology in Pulsed-Current NG-GMAW of Mild Steel

The current research of narrow-gap gas metal arc welding (NG-GMAW) primarily focuses on improving the sidewall fusion and avoiding the lack-of-fusion defect.However,the high cost and operation difficulty of the methods limit the industrial application.in this study,small amount of active gases CO2 and O2 were added into pure argon inert shield-ing gas to improve the weld formation of pulsed-current narrow-gap gas metal arc welding (NG-GMAW) of mild steel.Their effects on droplet transfer and arc behavior were investigated.A high-speed visual sensing system was utilized to observe the metal transfer process and arc morphology.When the proportion Of CO2,being added into the pure argon shielding gas,changes from 5％ to 25％,the metal transfer mode changes from pulsed spray streaming transfer to pulsed projected spray transfer,while it remains the pulsed spray streaming transfer when 2％ to 10％ O2 is added.Both CO2 and O2 are favorable to stabilizing arc and welding process.O2 is even more effective than CO2.However,O2 is more likely to cause slags on the weld surface,while CO2 can improve the weld appearance in some sense.The weld surface concavity in NG-GMAW is greatly influenced by the addition of active gas,but the weld width and weld penetration almost keep constant.This study proposes a new method which is beneficial to improving the weld bead formation and welding process stability.