Pose Planning for the End-effector of Robot in the Welding of Intersecting Pipes

All-position robots are widely applied in the welding of complicated parts.Welding of intersecting pipes is one of the most typical tasks.The welding seam is a complicated saddle-like space curve,which puts a great challenge to the pose planning of end-effector.The special robots designed specifically for this kind of tasks are rare in China and lack sufficient theoretical research.In this paper,a systematic research on the pose planning for the end-effectors of robot in the welding of intersecting pipes is conducted. First,the intersecting curve of pipes is mathematically analyzed.The mathematical model of the most general intersecting curve of pipes is derived,and several special forms of this model in degraded situations are also discussed.A new pose planning approach of bisecting angle in main normal plane（BAMNP） for the welding-gun is proposed by using differential geometry and the comparison with the traditional bisecting angle in axial rotation plane（BAARP） method is also analytically conducted.The optimal pose of the welding-gun is to make the orientation posed at the center of the small space formed by the two cylinders and the intersecting curve to help the welding-pool run smoothly.The BAMNP method can make sure the pose vertical to the curve and center between the two cylinders at the same time,therefore its performance in welding-technique is superior to the BAARP method.By using the traditional BAARP method,the robot structure can become simpler and easier to be controlled,because one degree of freedom（DOF） of the robot can be reduced.For the special case of perpendicular intersecting,an index is constructed to evaluate the quality of welding technique in the process of welding.The effect of different combination of pipe size on this index is also discussed.On the basis of practical consideration,selection principle for BAARP and BAMNP is described.The simulations of those two methods for a serial joint-type robot are made in MATLAB,and the simulation results are consistent to the analysis.The mathematical model and the proposed new pose-planning method will lay a solid foundation for future researches on the control and design of all-position welding robots.

Friction stir welding of AZ31 magnesium alloys processed by equal channel angular pressing

Equal channel angular pressing （ECAP） is an effective thermo-mechanical process to make ultrafine grains. An investigation was carried out on the friction stir welding （FSW） of ECAPed AZ31 magnesium alloys with a thickness of 15 mm. For different process parameters, the optimum FSW conditions of ECAPed AZ31 magnesium alloys were examined. The basic characterization of weld formation and the mechanical properties of the joints were discussed. The results show that the effect of welding parameters on welding quality was evident and welding quality was sensitive to welding speed. Sound joints could be obtained when the welding speed was 37.5 mm/min and the rotation speed of the stir tool was 750 r/min. The maximum tensile strength （270 MPa） of FSW was 91% that of the base materials. The value of microhardness varied between advancing side and retreating side because of the speed field near the pin of the stir tool, which weakened the deformed stress field. The value of microhardness of the welding zone was lower than that of the base materials. The maximum value was located near the heat-affected zone （HAZ）. Remarkable ductile character was observed from the fracture morphologies of welded joints.

Study on path planning and compensation of off-line programming for thick walled curve welding

Thick walled curve welding are usually joined by multi-layer and multi-pass welding, which quality and efficiency could be improved by off-line programming of robot welding. However, the precision of off-line programming welding path was decreased due to the deviation between the off-line planned welding path and the actual welding path. A path planning algorithm and a path compensation algorithm of multi-layer and multi-pass curve welding seam for off-line programming of robot welding are developed in this paper. Experimental results show that the robot off-line programming improves the welding efftcieney and precision for thick walled curve welding seam.

Path Planning of Planar Kinked Line Seam by Visual Servoing for Robotic Welding

Welding path planning can substitute for the manual teaching process of the robot and can promote the autonomous level of the robotic welding. A path planning method by visual servoing was presented, in which the optimal angle of charge-coupled device (CCD) camera was also planned. Aiming at planning two forms of kinked line seams, obtuse angle seam and right angle seam, a practicable solution was put forward. In this solution, the intersection of two adjacent straight segments is detected in each local seam image, and if intersection is found, the seam errors are calculated using the next straight segment. The experimental results show that kinked line seam can be well planned using this solution.

THE 47TH ANNUAL ASSEMBLY THE INTERNATIONAL INSTITUTE OF WELDING

ＴＨＥ４７ＴＨＡＮＮＵＡＬＡＳＳＥＭＢＬＹＴＨＥＩＮＴＥＲＮＡＴＩＯＮＡＬＩＮＳＴＩＴＵＴＥＯＦＷＥＬＤＩＮＧＬｉｎＳｈａｎｇｙａｎｇ，Ｃｈａｉｒｍａｎ（ＴｈｅＣｈｉｎｅｓｅＯｒｇａｎｉｚｉｎｇＣｏｍｍｉｔｔｅｅ）ＧｕａｎＱｉａｏ，Ｐｒｅｓｉｄｅｎｔ...

Equalization of Ti 6Al 4V alloy welded joint by scanning electron beam welding

The equalization of Ti 6Al 4V alloy welded joint with base metal on corrosion resistance, strength and ductility was studied. The solidification microstructure is transformed from 650 μm columnar grains to 100 μm equiaxed grains by scanning electron beam welding. The anodic polarization curve of 150 μm equiaxed grains coincides with that of base metal. Equal corrosion resistance between weld metal and base metal was obtained. Uniform microstructure and solute distribution are the basis of equalization. Corrosion rate of weld with 150 μm equiaxed grains is the lowest, 2.45 times lower than that of 650 μm columnar grains. Weld strength is 98% as much as that of base metal, yield strength ratio is 99.5%, which is 3.6% higher than that of base metal.

Weldability evaluation and tensile strength estimation model for aluminum alloy lap joint welding using hybrid system with laser and scanner head

Aluminum welding using a hybrid system with a laser and scanner welding head was performed under various welding conditions to verify the feasibility of applying an aluminum alloy to a car body.The experimental material was 5J32 aluminum alloy,and the laser power,welding speed,and laser incidence angle were used as the control variables.The weld bead shape and the tensile shear strength were evaluated in order to understand the aluminum lap joint weld characteristics.Analysis of variance (ANOVA) was conducted to identify the effect of the process variables on the tensile shear strength.Tensile strength estimation models using three different regression models were also suggested.The input variables were the laser power,welding speed,and laser incidence angle,and the output was the tensile shear strength.Among the models,the second-order polynomial estimation model had the best estimation performance,and the average error rate of this model was 0.058.

Interfacial Characterization and Mechanical Property of Ti/Cu Clad Sheet Produced by Explosive Welding and Annealing

It was aim to investigate the interfacial microstructure and shear performance of Ti/Cu clad sheet produced by explosive welding and annealing. The experimental results demonstrate that the alternate distribution of interfacial collision and vortex of flyer layer forms in the interface a few of solidification structure. TEM confirms that the interfacial interlayer contains obvious lattice distortion structure and intermetallic compounds. It interprets the explosive welding as the interfacial deformation and thermal diffusion process between dissimilar metals. The interfacial shear strength is very close to the Cu matrix strength, which is determined by the mixture of the mechanical bonding and metallurgical bonding. Several cracks exist on the shear fracture owing to the intermetallic compound in the interfacial solidifi cation structure and also the probable welding inclusion.

Seam-tracking based on dynamic trajectory planning for a mobile welding robot

A new seam-tracking method based on dynamic trajectory planning for a mobile welding robot is proposed in order to improve the response lag of the mobile robot and the high frequency oscillation in seam-tracking.By using a front-placed laser-based vision sensor to dynamically extract the location of the weld seam in front of torch,the trend and direction of the weld line is roughly obtained.The robot system autonomously and dynamically performs trajectory planning based on the isometric approximation model.Arc sensor technology is applied to detect the offset during welding process in real time.The dynamic compensation of the weld path is done in combination with the control of the mobile robot and the executive body installed on it.Simulated and experimental results demonstrate that the method effectively increases the stability of welding speed and smoothness of the weld track,and hence the weld formation in curves and corners is improved.

Planning of circlelocus for multi-path/multi-layer welding robot with automatical error-correction

In this paper, a planning algorithm for multi path/multi layer circular locus is poposed. The algorithm is applied to weld the nipples on the header of boiler. Multi path/multi layer circular locus is planned according to three teaching points, which is lapped head on end to satisfy the requirement of technology. For the nipples wherever they are arranged radially or axially, even if there are errors caused by positioning and thermal deformations, providing that nipple's position and orientation relative to the teaching one can be measured, the multi path/multi layer circular locus can be planned without teaching any more. The algorithm has been applied in welding robot for manufacturing power station' boiler.

Estimation of the Temperature in the Weld Penetration Channel in Electron Beam Welding

In this paper, the method of experimental estimation of the temperature in a penetration channel in electron beam welding is described on the basis of chemical elements concentration in the vapors above welding zone. The temperature of a vapor-gas phase in the penetration channel is determined when equating calculated and experimental concentrations of the elements.

基于BP-ANN与RBF-ANN的钢筋与混凝土黏结强度预测模型研究

为研究神经网络对钢筋与混凝土黏结强度的预测能力以及神经网络的输出性能,基于大量的试验数据,提出一种基于改进神经网络的变形钢筋与混凝土黏结强度预测模型,对混凝土结构的研究与实际工程应用均有着重要的意义。收集290组黏结锚固试验数据,引入基于反向传播人工神经网络(BP-ANN)与径向基函数神经网络(RBF-ANN)算法,揭示混凝土强度、保护层厚度、钢筋直径、锚固长度及配箍率对变形钢筋与混凝土黏结性能的影响规律,建立基于改进神经网络算法的钢筋与混凝土黏结强度预测模型。对比分析不同数据预处理方法和训练神经元个数对建议模型预测结果的影响,评估各经典模型与建议模型的预测精度和离散性,提出临界锚固长度计算公式。结果表明:BP-ANN预测值与试验值比值的均值、标准差及变异系数分别为1.009、0.188、0.86,其预测精度略高于RBF-ANN;建议模型能够更准确、更稳定地预测钢筋与混凝土的黏结强度,该方法为解决钢筋与混凝土黏结问题提供了新思路。

基于ANN和XGB算法的锈蚀钢筋混凝土高温粘结强度预测方法

为准确评估锈蚀钢筋混凝土(CRC)结构在突发火灾下的结构承载力,锈蚀钢筋混凝土高温粘结强度的统一预测方法研究亟待开展。然而,粘结退化机理复杂,粘结因素众多,实验方法不能考虑所有粘结因素的相关复杂关系的影响。在现有大量试验数据的基础上,采用机器学习方法可以有效地通过数据建立输入和输出特征之间的回归关系。该文利用ANN和XGB两种机器学习算法建立了一个统一的锈蚀钢筋混凝土高温粘结强度预测模型。基于612组高温锈蚀钢筋混凝土的试验研究数据,进行模型训练和测试。结果表明:ML模型的预测结果与实验结果十分吻合。此外,针对机器学习算法本身存在的黑盒子问题,使用SHAP方法来解决锈蚀钢筋混凝土高温粘结强度预测过程中的模型可解释性问题。同时,还将ML模型的计算结果与三种理论计算公式的结果进行了比较,结果表明:ML模型具有明显的优势。新构建的混合机器学习模型很有可能成为准确评估CRC结构经受高温后的损伤程度问题的新选择。

ANN Based Predictive Modelling of Weld Shape and Dimensions in Laser Welding of Galvanized Steel in Butt Joint Configurations

The quality assessment and prediction becomes one of the most critical requirements for improving reliability, efficiency and safety of laser welding. Accurate and efficient model to perform non-destructive quality estimation is an essential part of this assessment. This paper presents a structured and comprehensive approach developed to design an effective artificial neural network based model for weld bead geometry prediction and control in laser welding of galvanized steel in butt joint configurations. The proposed approach examines laser welding parameters and conditions known to have an influence on geometric characteristics of the welds and builds a weld quality prediction model step by step. The modelling procedure begins by examining, through structured experimental investigations and exhaustive 3D modelling and simulation efforts, the direct and the interaction effects of laser welding parameters such as laser power, welding speed, fibre diameter and gap, on the weld bead geometry (i.e. depth of penetration and bead width). Using these results and various statistical tools, various neural network based prediction models are developed and evaluated. The results demonstrate that the proposed approach can effectively lead to a consistent model able to accurately and reliably provide an appropriate prediction of weld bead geometry under variable welding conditions.

基于ANN的RECFST短柱轴压承载力预测

目的针对相关设计规范和文献在计算圆端形截面钢管混凝土短柱轴压承载力上的局限性,开发高精高效的轴压承载力预测模型。方法首先,基于国内外已有的RECFST短柱轴压试验研究结果建立有限元模型,并通过验证;其次,基于Python脚本批量生成有限元模型,建立涵盖广泛输入参数的数据集;然后,利用数据集开发高精度的ANN模型并与相关规范和文献结果进行比较;最后,基于ANN模型开发GUI图形用户界面工具。结果ANN模型预测值与试验结果之比的平均值N ANN/N u=0.98,模型预测误差远低于相关规范和文献公式预测误差;ANN模型的均方误差K MSE=7.3734×10-7,总数据样本回归值R=0.99963,表明了ANN模型的有效性以及预测结果的精确性。结论ANN模型可以准确预测RECFST短柱的轴压承载力,基于模型开发的GUI工具简便实用。

基于SEM与ANN混合方法的社交问答平台用户转移行为

社交问答平台得到了用户的广泛使用,但由于各平台的功能类似,用户转移起来较为容易,这将导致用户流失。基于PPM模型,研究社交问答平台用户转移行为。采集447份有效数据,采用SEM(结构方程模型)与ANN(人工神经网络)混合方法进行分析。结果发现:推力因素(不满意度、厌倦性)和拉力因素(内容质量、用户体验)正向影响用户的转移意向,锚定因素(转移成本)负向影响转移意向,且负向调节推力因素和拉力因素的作用。ANN结果显示:不满意度是影响转移意向的最重要因素。因此,社交问答平台需要提高内容质量,改善用户体验,降低用户的不满意度和厌倦性,从而防止用户的转移行为,实现用户保持。

基于GA改进ANN算法的车载网控系统故障诊断

车载网控系统是保证运行安全的一类重要控制设备,也是确保系统稳定运行的核心部件。为了提高车载网控系统故障诊断效率,通过遗传算法(GA)具有的全局寻优功能来实现对神经网络初始阈值与权值的优化,把寻优结果代到神经网络内完成训练过程;使ANN泛化方法具有的映射性能获得充分利用可以防止产生局部极小值情况,获得更高的分类精度;利用实例分析方式测试车载故障诊断过程的有效性。研究结果表明:采用GA改进ANN算法可以有效优化平均误差及数据正确率,有效降低迭代次数,表明可以通过GA改进ANN方法来提升神经网络运算性能。经过遗传算法优化处理的ANN在训练过程中可以获得比初始ANN更快时收敛速率。

A Study on Prediction of Weld Geometry in Laser Overlap Welding of Low Carbon Galvanized Steel Using ANN-Based Models

Predictive modelling for quality analysis becomes one of the most critical requirements for a continuous improvement of reliability, efficiency and safety of laser welding process. Accurate and effective model to perform non-destructive quality estimation is an essential part of this assessment. This paper presents a structured approach developed to design an effective artificial neural network based model for predicting the weld bead dimensional characteristic in laser overlap welding of low carbon galvanized steel. The modelling approach is based on the analysis of direct and interaction effects of laser welding parameters such as laser power, welding speed, laser beam diameter and gap on weld bead dimensional characteristics such as depth of penetration, width at top surface and width at interface. The data used in this analysis was derived from structured experimental investigations according to Taguchi method and exhaustive FEM based 3D modelling and simulation efforts. Using a factorial design, different neural network based prediction models were developed, implemented and evaluated. The models were trained and tested using experimental data, supported with the data generated by the 3D simulation. Hold-out test and k-fold cross validation combined to various statistical tools were used to evaluate the influence of the laser welding parameters on the performances of the models. The results demonstrated that the proposed approach resulted successfully in a consistent model providing accurate and reliable predictions of weld bead dimensional characteristics under variable welding conditions. The best model presents prediction errors lower than 7% for the three weld quality characteristics.

ANN模型与分段线性插值及回归模型的比较及应用

对ANN模型、分段线性插值模型和非线性回归模型从原理上进行了比较,ANN模型易于构建各影响因素与因变量间复杂关系,非线性回归模型和分段线性插值模型可以将自变量与因变量间的关系通过表达式直观表达。以荆江三口分流量与枝城流量的关系为应用算例,采用相关系数、纳什效率系数、均方根误差和平均绝对误差等4个评价指标对3个模型的拟合精度和误差大小进行了比较。结果表明:3个模型均可应用于模拟枝城流量与荆江三口分流量的关系,但3个模型的计算值与实际值间的误差大小存在差异,从4个评价指标综合来看,ANN模型计算值与实测值的误差最小,分段线性插值模型次之,回归模型计算精度相对较低。

Development of Full Automatic External Welding Machine for Annular Welds of Pipeline

To meet the demands of rapid development of pipeline constructions in China, a complete set of full automatic external welding machine for annular welds of pipeline and welding procedure have been developed thereof. The system has been applied in the “West East Pipeline Project” and its performance is proven. With this welding machine the welding parameters can be either preset before or adjusted in real time during the welding process, which avoids the blemishes of same type domestic and international products. Thus it is best propitious to in situ construction conditions and workers’ technical level in China. In this article the development of mechanical and control systems of this product is introduced and typical welding procedure parameters are provided.