基于BAS算法优化的电弧增材制造焊道尺寸预测

目的 为提高实际应用中电弧增材制造对工艺参数的选取效率及成形形貌的控制效果,建立高效且精准的成形尺寸预测模型,实现对焊道尺寸的合理预测。方法 在单层单道CMT电弧增材制造实验的基础上,建立基于天牛须搜索算法(Beetle Antennae Search,BAS)优化BP神经网络的焊道尺寸预测模型,利用BAS算法实现对BP神经网络初始权值和阈值的优化,可以实现预测不同工艺参数(焊接速度、送丝速度、干伸长)下焊道的成形尺寸(熔宽、余高)。利用试验验证BAS-BP预测模型的性能,与现有模型进行对比,结果 结果表明该模型具有较高精度的预测效果,能够有效映射工艺参数与焊道尺寸之间的非线性关系,印证了该模型具有良好的拟合和泛化能力,同时其对焊道熔宽和余高的预测误差分别不超过0.2、0.12 mm,预测平均误差率均不超过6%,相对于其他预测模型表现出较好的准确性和稳定性。结论 BAS-BP神经网络预测模型的输出误差较小,网络训练收敛速度加快,避免了过拟合及欠拟合的风险,有效提高了预测模型的泛化能力和预测精度,可以实现一定工艺参数范围内的焊道尺寸预测,为后续电弧增材的实时预测及控制参数应用提供了技术支持。     

基于CMT技术的铝合金电弧增材制造研究现状

由于铝合金的应用领域较为广泛,使其增材制造技术成为了研究热点。CMT技术作为一种新型焊接工艺,焊接过程中弧长控制较为精确,其热输入量小、飞溅少等工艺特点非常适合铝合金等低熔点金属的增材制造,因此,铝合金CMT增材制造技术成为了近年来国内外各研究机构的研究热点。从控形控性的角度分析了国内外相关研究机构的研究方向,重点综述了焊接速度、送丝速度、CMT工艺等工艺参数和热处理对成形件形貌及性能的影响,同时概述了铝合金CMT电弧增材制造中尺寸控制、组织性能、气孔缺陷等方向的研究工作。借此指出,基于CMT技术的铝合金电弧增材制造技术的相关研究工作仍主要聚焦于试验研究阶段,并未深入到成形机理的探究。该领域的研究工作应更深入、系统地从成形尺寸精度控制、控制气孔缺陷、组织演变规律及性能优化等角度展开,力求加速推进该技术在现代制造业的应用。     

410马氏体不锈钢块体材料的冷金属过渡焊电弧增材制造与性能表征

电弧增材制造具有效率高、成本低和不受成形尺寸限制等独特优势,在新型制造、修复领域拥有良好的应用前景.获得力学性能良好、显微组织均匀的电弧增材制造件是目前急需解决的问题.通过冷金属过渡焊(CMT)丝材电弧增材制造系统,制备了两种410马氏体不锈钢块体材料.光学显微镜(OM)、扫描电镜(SEM)和力学性能测试结果表明,现有工艺可制备显微组织均匀、硬度平均值为530HV、抗拉强度平均值为1 196 MPa且延伸率均匀的沉积件.本工作还探讨分析了电弧增材制造件的力学性能特点及成因,并与锻造、激光增材制造等方法制得的H13热作模具钢的力学性能进行比较,分析了电弧增材制造件的性能与其他方法制备的工件性能存在差异的原因,考察了冷金属过渡电弧增材制造410不锈钢在修复件中使用的可行性,阐述了提升电弧增材制造件力学性能的方向.     

工艺参数对机器人电弧增材制造成形的影响研究

目的 提高电弧增材制造质量,获得更好的参数匹配。方法 研究机器人焊接速度和层间冷却时间变化对增材件形貌、熔宽、余高的影响规律。选取焊接速度为30 cm/min和40 cm/min,层间冷却时间为30 s和40 s,进行两变量两个水平的全面实验。利用机器人电弧增材制造技术在5 mm厚的316L不锈钢板上进行20层的堆积;在焊道上均匀选取6个点,测得总高、熔宽和余高数据。在此基础上,分析增材件总体形貌及熔宽、余高的变化规律。结果 发现当层间冷却时间达到一定值后,熔池已凝固且温度较低,熔宽、余高变化不大。随着焊接速度提升,熔池单位时间内熔化的金属量锐减,引起增材件熔宽、余高缩小。结论 改变焊接速度对增材件形貌的影响更为明显,层间冷却时间达到一定值后,层间温度不再发生变化,形貌变化不大。     

5556铝合金CMT增材单道成形质量及尺寸预测模型研究

目的 研究不同参数下5556铝合金CMT增材单道成形质量及尺寸预测模型。方法 利用游标卡尺和钢直尺,对增材试样截面的余高、熔宽、成形高度及成形宽度进行测量,并且使用SPSS、Excel及Origin等软件进行尺寸预测模型的建立及验证。结果 对于单层单道增材试样,随着焊接电流从60 A增至140 A,其余高、熔宽均整体呈上升趋势,并且余高的增长速度远小于熔宽的增长速度;随着焊接速度从300 mm/min增至1 100 mm/min,其熔宽、余高均呈下降趋势,但当焊接速度超过700 mm/min时,熔宽的变化较小;随着气体流量从10L/min增至25L/min,余高的变化幅度较小,但熔宽的变化幅度较大。对于多层单道增材试样,随着焊接速度从400 mm/min变为800 mm/min,其成形高度和宽度均变小;随着焊接电流从90 A变为130 A以及层间停留时间从1 min变为5 min,其成形高度和宽度均变大。通过多层单道增材实验和尺寸预测模型可知,焊接电流与增材试样的宽度呈正相关,焊接速度与增材试样的高度和宽度皆呈负相关。结论 单层单道增材试样的熔宽主要受焊接电流的影响,而余高主要受焊接速...     

基于回归方法和神经网络的电弧增材制造单道成形形貌预测

目的 针对电弧增材制造技术实际应用中工艺参数选取困难和成形结果难预测的问题,确定高效、准确的电弧增材制造单道成形形貌预测的数学方法,以快速、方便地选取丝材电弧增材制造工艺参数并指导成形质量控制。方法 在单道单层丝材电弧增材制造实验的基础上,采用多种回归方法和神经网络方法分别建立焊接电流、电压和焊枪移动速度等多个工艺参数与增材层宽度、增材层高度及熔池深度等成形形貌参数之间的数学关系模型。结果 电弧增材制造单道成形形貌与焊接电流、电压和焊枪移动速度显著相关,且各参数间存在非线性交互作用;采用多元线性回归法可较准确地预测单道增材层宽度,但对于增材层高度和熔深的预测效果较差;神经网络可良好地处理各工艺参数间复杂的非线性关系,其对增材层宽度、增材层高度和熔深的预测平均误差率分别为4.17%、6.60%和7.01%,显著优于多元线性回归法。结论 采用神经网络法可以准确预测电弧增材制造单道成形的形貌参数,进而指导增材制造工艺参数的选取和成形质量的控制。     

CMT电弧增材制造Cu-Ni-Al-Mn-Fe铝青铜合金微观组织性能研究

目的研究冷金属过渡技术(Cold metal transfer,简称CMT)增材制造Cu-Ni-Al-Mn-Fe铝青铜合金的微观组织成形规律。方法采用CMT电弧增材的方式制备了Cu-Ni-Al-Mn-Fe铝青铜合金的薄壁试样件,研究了试样件在不同位置、不同方向的微观组织。结果 CMT电弧增材制造Cu-Ni-Al-Mn-Fe铝青铜合金的微观组织分为3个区域,前3层的不稳定区域主要是由基材树枝晶到柱状晶的转变区域;第3层到最后一层的稳定区域主要是外延生长的柱状晶区;在最后一层靠近空气侧约360μm厚度范围内,出现转向枝晶。交替往复电弧增材的Cu-Ni-Al-Mn-Fe铝青铜合金,在每层顶部均会形成转向枝晶,但随后新一层电弧增材的熔池会熔化顶部形成的转向枝晶,最终在微观组织形貌上表现出柱状晶外延生长的形式。结论通过控制合适工艺参数,可以获得致密无缺陷的CMT电弧增材制造Cu-Ni-Al-Mn-Fe铝青铜合金薄壁试样,在试样的稳定区域,微观组织是外延生长的柱状晶,柱状晶的晶界上Al,Ni,Mn元素产生富集现象,质量分数高于平均值。在柱状晶的晶内,Cu元素高于均值,而Al,Ni,Mn元素质量分数均低于均值,这与柱状晶的形核顺序有关。     

冷金属过渡电弧增材制造强制限位冷却工艺研究

目的 针对冷金属过渡(CMT)电弧增材制造过程中不稳定气流环境造成的熔池流动不均、墙体成形异常以及墙体内部气孔过多和晶粒粗大的问题,研究增强沉积墙体组织性能的工艺。方法 开发了CMT电弧增材制造强制限位冷却工艺,通过控制电弧增材制造的沉积区间和凝固过程,来改善沉积墙体的结构性能。结果 沉积墙体平均沉积速度由0.120 mm/s升到0.149 mm/s,材料利用程度由78.2%升到83.2%,孔隙率由2.15%降到1.06%,平均晶粒度由15.7 μm降到13.3 μm。同时提高了沉积墙体的韧性,沉积墙体横向平均极限拉伸强度由157 MPa升到179 MPa。结论 CMT电弧增材制造强制限位冷却工艺制造的沉积墙体在沉积速度和材料利用程度方面有了相应提高,同时强制限位冷却工艺改善了沉积墙体的结构性能,这对增材制造具有一定的指导意义。     

CMT电弧增材制造GH4169合金的组织和拉伸性能

目的研究冷金属过渡CMT电弧增材制造GH4169合金单道多层薄壁试样的组织和拉伸性能。方法利用CMT增材制造成形系统进行GH4169合金的单壁墙增材制造试验,分析了成形薄壁试样的组织演化和力学性能,讨论了柱状晶组织的各向异性以及均匀化处理对合金力学性能的影响。结果成形试样的显微组织主要为γ相和共晶(γ+Laves)相,试样沿沉积方向具有[100]择优取向。枝晶组织随着沉积层数的增加变得粗大,枝晶间距变大且二次枝晶臂变小,Laves相的取向特征越明显。从底部区域到顶部区域,试样枝晶臂间距λ_1从13.76μm增大到23.27μm。沿柱状晶生长方向的抗拉强度最大,约为774 MPa;而沿电弧行走方向的抗拉强度随沉积层数的增加逐渐减小,断后伸长率逐渐增大,最大抗拉强度约为763MPa。1170℃固溶+时效处理后,原粗大柱状晶形成较小的多边形晶粒,成形试样组织的均匀性提高,沉积方向最大抗拉强度为1222 MPa,沿电弧行走方向最大抗拉强度为1085 MPa。结论 CMT增材制造GH4169合金组织特征与激光增材制造的试样基本一致,热处理前后CMT成形GH4169合金试样抗拉强度均小于激光立体成形,但伸长率更大。     

CMT电弧增材制造铝青铜的微观组织及耐腐蚀性能研究

目的研究冷金属过渡技术(Cold metal transfer,CMT)增材制造Cu-Ni-Al-Mn-Fe铝青铜合金的微观组织演变规律以及在不同温度下的耐腐蚀性能。方法采用CMT电弧增材的方式制备了铝青铜合金的薄壁试样件,通过光学显微镜研究了试样件在不同位置的微观组织演变规律,并通过电化学工作站测试试样在质量分数为3.5%的NaCl溶液中的电位极化曲线,进而分析其耐腐蚀性能。结果 CMT电弧增材制造铝青铜合金的微观组织主要表现为3个区域。前3层微观组织由基材树枝晶转变为柱状晶的区域;中间稳定区域主要是垂直于基板方向生长的均匀柱状晶微观组织;以及在最后一层出现柱状晶转向树枝晶的区域。当温度由20℃上升到60℃时,该材料的稳定电位ER由-0.2540 V下降到-0.2745 V。自腐蚀电流密度由2.84×10-6 A/cm~2增加到了5.149×10-6A/cm~2。结论采用合适工艺参数,可以获得致密无缺陷的CMT电弧增材制造铝青铜合金薄壁试样,在试样的稳定区域,微观组织是外延生长的柱状晶。同时试样在质量分数为3.5%的NaCl浓度溶液中有着良好的耐腐蚀性能,并且由于腐蚀过程介质温度的升高,电极反应速度加快、溶液的对流和扩散加强,从而加快了阳极过程和阴极过程,加速了金属的腐蚀。由此可见,介质温度对腐蚀速率的影响是非常重要的。     

基于 CMT 电弧增材的焊缝成形尺寸规律研究

目的研究焊接参数对焊缝成形尺寸的影响规律。方法基于冷金属过渡技术,采用正交试验方法得到在不同参数组合下焊缝熔宽、余高和第2层增高,通过多元线性回归拟合,建立了焊缝熔宽、余高和第2层增高与焊接参数之间的回归模型。结果影响焊缝熔宽和余高的主要焊接参数是焊接速度,影响焊缝第2层增高的主要焊接参数是送丝速度,而层间温度的变化对熔宽会有显著影响,但是对余高和第2层增高的影响不大,而且焊缝第2层的增高与余高在数值上存在较大的差异,对比预测值和试验值验证了回归模型的准确性。结论通过改变焊接速度可以引起熔宽和余高的显著变化,层间温度对余高和第2层增高不会造成很大影响。     

A comparative study of multiple regression analysis and back propagation neural network approaches on plain carbon steel in submerged-arc welding

Weld bead plays an important role in determining the quality of welding particularly in high heat input processes. This research paper presents the development of multiple regression analysis (MRA) and artificial neural network (ANN) models to predict weld bead geometry and HAZ width in submerged arc welding process. Design of experiments is based on Taguchi’s L16 orthogonal array by varying wire feed rate, transverse speed and stick out to develop a multiple regression model, which has been checked for adequacy and significance. Also, ANN model was accomplished with the back propagation approach in MATLAB program to predict bead geometry and HAZ width. Finally, the results of two prediction models were compared and analyzed. It is found that the error related to the prediction of bead geometry and HAZ width is smaller in ANN than MRA.     

Effect of Welding Parameters on Dilution and Weld Bead Geometry in Cladding

The effect of pulsed gas metal arc welding （GMAW） variables on the dilution and weld bead geometry in cladding X65 pipeline steel with 316L stainless steel was studied. Using a full factorial method, a series of experiments were carried out to know the effect of wire feed rate, welding speed, distance between gas nozzle and plate, and the vertical angle of welding on dilution and weld bead geometry. The findings indicate that the dilution of weld metal and its dimension i.e. width, height and depth increase with the feed rate, but the contact angle of the bead decreases first and then increases. Meantime, welding speed has an opposite effect except for dilution. There is an interaction effect between welding parameters at the contact angle. The results also show forehand welding or decreasing electrode extension decrease the angle of contact. Finally, a mathematical model is contrived to highlight the relationship between welding variables with dilution and weld bead geometry.     

Experimental investigation on the effects of process parameters of GMAW and transient thermal analysis of AISI321 steel

Gas metal arc welding (GMAW) develops an arc by controlling the metal from the wire rod and the input process parameters. The deposited metal forms a weld bead and themechanical properties depend upon the quality of the weld bead. Proper control of the process parameters which affect the bead geometry, the microstructures of the weldments and the mechanical properties like hardness, is necessary. This experimental study aims at developing mathematical models for bead height (HB), bead width (WB) and bead penetration (PB) and investigating the effects of four process parameters
viz: welding voltage, welding speed, wire feed rate and gas flow rate on bead geometry, hardness and microstructure of AISI321 steel with 10 mm thickness. The transient thermal analysis shows temperature and residual stress distributions at different conduction and convection conditions.     

Fatigue properties of arc-welded lap joints with weld start and end points

Fatigue properties of arc‐welded lap joints with weld start and end points were investigated through experiments with 2.3‐mm and 3.2‐mm thick 440 MPa‐class steel sheets. Macroscopic fatigue crack‐initiation sites depended on the length of the weld bead to the specimen width. In joints with shorter weld beads, cracks mainly initiated at the toe of the weld start points, while joints with longer beads had initial cracks at the toe of the bead centre. Crack‐propagation analyses, taking stress distribution around the weld toe and residual stress into account, suggested that residual stress distribution could move crack‐initiation sites from the weld start point to the bead centre, although the applied stress at the toe of the weld start point remains the highest.     

Optimization of A-TIG process parameters using response surface methodology

In the present work, the influence of process parameters such as welding current (I), welding speed (S), and flux coating density (F) on different aspects of weld bead geometry for example depth of penetration (DOP), bead width (BW), depth to width ratio (D/W), and weld fusion zone area (WA) were investigated by using the central composite design (CCD). 9–12% Cr ferritic stainless steel (FSS) plates were welded using A-TIG welding. It was observed that all input variables have a direct influence on the DOP, BW, and D/W. However, flux coating density has no significant effect on WA. Mathematical models were generated from the obtained responses to predict the weld bead geometry. An optimized DOP, BW, D/W, and WA of 6.95?mm, 8.76?mm, 0.80, and 41.99?mm², respectively, were predicted at the welding current of 213.78 A, the welding speed of 96.22?mm/min, and the flux coating density of 1.99?mg/cm². Conformity test was done to check the practicability of the developed models. The conformity test results were in good agreement with the predicted values. Arc constriction and reversal in Marangoni convection were considered as major mechanisms for the deep and narrow weld bead during A-TIG welding.     

Predicting of bead undercut defects in high-speed gas metal arc welding (GMAW)

In the gas metal arc welding (GMAW) process, when the welding speed reaches a certain threshold, there will be an onset of weld bead undercut defects which limit the further increase of the welding speed. Establishing a mathematical model for high-speed GMAW to predict the tendency of bead undercuts is of great significance to prevent such defects. Under the action of various forces, the transferred metal from filler wire to the weld pool, and the geometry and dimension of the pool itself decide if the bead undercut occurs or not. The previous model simplified the pool shape too much. In this paper, based on the actual weld pool geometry and dimension calculated from a numerical model, a hydrostatic model for liquid metal surface is used to study the onset of bead undercut defects in the high-speed welding process and the effects of different welding parameters on the bead undercut tendency.     

Predicting of bead undercut defects in high-speed gas metal arc welding (GMAW)

In the gas metal arc welding (GMAW) process, when the welding speed reaches a certain threshold, there will be an onset of weld bead undercut defects which limit the further increase of the welding speed. Establishing a mathematical model for high-speedGMAWto predict the tendency of bead undercuts is of great significance to prevent such defects. Under the action of various forces, the transferred metal from filler wire to the weld pool, and the geometry and dimension of the pool itself decide if the bead undercut occurs or not. The previous model simplified the pool shape too much. In this paper, based on the actual weld pool geometry and dimension calculated from a numerical model, a hydrostatic model for liquid metal surface is used to study the onset of bead undercut defects in the high-speed welding process and the effects of different welding parameters on the bead undercut tendency.