Quality estimation of resistance spot welding of stainless steel based on BP neural network

The end value of the dynamic resistance curve of stainless steel was proved to have strong correlation with nugget size by experiments, so it was an important factor for estimation of weld quality. BP neural network was employed to estimate the weld quality. The end value of the dynamic resistance curve, welding current and welding time were selected as the input variables while the nugget diameter, which is closely related to weld quality, was selected as the output variable. Testing results shows that such network has fine fault tolerance and real-time quality estimation is possible.     

基于BP神经网络的DP600点焊熔核参数建模

以焊接电压、焊接电流构造输入向量,熔核直径、热影响区外径和焊接区焊后厚度为输出量,建立DP600高强钢电阻点焊的熔核参数模型。推导了梯度下降法、动量梯度法和共轭梯度法三种权值算法,并用实际试验数据对模型进行训练和预测。结果表明,共轭梯度法训练后的预测结果误差率最低,所有参数的误差在8%内,平均误差在4%内,可用于在线检测来提高产品质量。     

基于模糊神经网络的电阻焊机恒电流控制研究

由于建立实际电阻点焊过程精确的数学模型比较困难,使得常规的人工调节PID控制器参数较难实现良好的匹配,从而难以获得满意的控制效果。针对该问题,将智能调节与PID控制方法相结合,利用模糊神经网络设计了参数kp、ki、kd自适应调整的PID控制器,构建了逆变电阻点焊电源的系统模型,通过对系统运行状态的在线学习智能化地修正PID的三个参数。PID控制输出量通过PWM发生器产生四路独立的、占空比实时变化的PWM波形,进而控制逆变器的功率开关器件导通时间,最终实现对系统恒电流的输出控制。仿真结果表明,该方法能根据系统的运行状态自行匹配对应最优控制规律下的PID三个参数,能有效地控制焊接电流的恒定,达到满意的效果。     

基于焊点表面图像处理的点焊质量监测

以采集的电阻点焊接头表面的数字图像作为信息源,探索了一种新的点焊质量无损监测方法.首先,通过图像特征分析,焊点表面图像被划分为4个环形特征区域,提取环形特征区域面积作为表征焊点质量的特征参数.其次,根据特征区域面积与焊点抗剪强度的相关性分析结果,选择了相关性显著的3个特征参数作为输入向量,焊点抗剪强度作为输出向量,建立了点焊质量的RBF神经网络监测模型.仿真分析和验证结果表明,基于焊点表面图像特征信息处理监测点焊质量的方法是可行的.     

基于BP神经网络遗传算法的薄板CMT点焊变形

焊接是汽车车身制造的一个关键环节,焊接质量的好坏严重影响汽车车身质量,所以焊接参数的选择至关重要. 针对薄板焊接质量控制问题,论文利用BP神经网络解决非线性问题的优势,建立焊接变形量与工艺参数之间映射关系模型;结合遗传算法构建基于遗传神经网络焊接的工艺参数优化系统;同时设计正交试验,将该方法与正交试验法相对比. 结果表明,该方法可以有效地实现CMT(cold metal transfer)点焊焊接变形预测与工艺参数优化. 通过预测模型给出合理参数,指导钢薄板和铝合金薄板的CMT点焊变形试验,提高焊接的效率.     

Neural network prediction of the shunt current in resistance spot welding

An error back propagation （BP） neural network prediction model was established for the shunt current compensation in series resistance spot welding. The input variables for the neural network consist of the resistivity of the material, the thickness of workpiece and the spot spacing, and the shunt rate is outputted. A simplified calculation for the shunt rate was presented based on the feature of the constant-current resistance spot welding and the variation of the resistance in resistance spot welding process, and then the data generated by simplified calculation were used to train and adjust the neural network model. The neural network model proposed was used to predict the shunt rate in the spot welding of 20# mlid steel （in Chinese classification） （in 2. 0 mm thickness） and 10# mild steel （in 1.5 mm and 1.0 mm thickness）. The maximum relative prediction errors are, respectively, 2. 83%, 1.77% and 3.67%. Shunt current compensation experiments were peoCormed based on the neural network prediction model proposed to check the diameter difference of nuggets. Experimental results show that maximum nugget diameter deviation is less than 4% for both 10# and 20# mlid steels with spot spacing of 30 mm and 50 mm.     

Quality assessment for resistance spot welding based on binary image of electrode displacement signal and probabilistic neural network

To improve the efficiency of acquiring monitored features and present a reliable quality assessment method for resistance spot welding, a novel method for converting the electrode displacement signal into binary image is proposed. The probabilistic neural network is adopted to provide a probabilistic viewpoint and a deterministic classification result of weld quality when the image characteristic of displacement signal is selected as monitored features. Test results of the classifier demonstrate that it is feasible and reliable to utilise binary image of the displacement signal to evaluate weld quality. The method reserves weld quality information as much as possible and it avoids complex algorithm for extracting and selecting monitored features. At the same time, when there are small samples, the classifier can identify good or bad weld rapidly and accurately even though the weld is from abnormal welding process, such as expulsion, current shunting and small edge distance condition.     

多参数点焊质量的偏最小二乘综合评价方法

将一种新型的统计回归方法--偏最小二乘(PLS,partial least square)方法用于点焊质量的多参数监测与分析中.借助于提取主元的思想,利用PLS方法对于点焊参数和焊接质量之间的相关信息进行筛选和综合,讨论和分析了点焊参数的各种数据信息.在此基础上,建立了点焊质量多参数综合评价模型.结果表明,该方法可以有效解决点焊质量综合评价模型中点焊参数存在的高维及多重相关性问题,建立的综合评价模型具有良好的评估能力.     

基于电极位移信号的电阻点焊质量预测模型

设计了电阻点焊过程动态参数监测系统，采集焊接电压、电流以及电极位移信号，建立以交流电阻点焊过程中的周波参数为输入空间，以试样的抗拉剪切强度为输出空间的点焊质量预测神经网络模型．为实现电阻点焊质量在线监控奠定了理论基础。试验结果证明了RBF神经网络用于这类应用场合的可行性和有效性。     

Filling technique for keyhole of friction stir spot welding based on the principles of resistance spot welding

Keyhole at the end of a weld prepared by friction stir welding(FSW) is one of the major issues that impede the application of FSW. To address this issue, a keyhole filling technique was proposed in this paper, which is based on the principles of resistance spot welding(RSW). A three-phase secondary rectifier resistance spot welder was applied as the experimental instrument for filling the keyhole in the center of friction stir spot weld(FSSW). The test sheet is a 2024-T4 aluminium alloy with a thickness of 6.0 mm. The experiments results show that the filled joint strength is improved by 26.12% since the area is increased for the plug in the keyhole. And there are two kinds of dimples in the tensile fracture—equiaxial dimples and long dimples. The filled joint involves the fusion welding zone(FWZ), pressure welding zone(PWZ), melted plug zone(MPZ), and plastic deformation zone(PDZ). The FWZ and the PWZ is the melting bond and diffusion bond between the plug and keyhole, respectively. The MPZ is the center part and the PDZ is upper or lower part of the plug.     

电阻点焊质量在线无损估测

采用动态电阻法建立了低碳钢电阻点焊熔核直径的人工神经网络模型,该模型为3层BP向前网络结构,通过大量正交试验训练获得其模型数据。将模型数据移植到C语言中,建立了熔核直径在线估测系统。该系统有望应用于实际生产的质量监控。     

基于频谱分布分析及神经网络的点焊超声检测

分析了检测信号的频谱分布,采用小波分析的方法提取了能够描述点焊超声波频谱分布特征及功率特征的超声检测特征值.由这些检测特征值构成超声特征矢量,结合BP神经网络的模式识别功能对点焊直径进行精确分类与识别.与传统时域分析方法相比较,其备更高识别能力、更高的识别效率、更少的识别特征以及更小的外部干扰因素.     

基于信号特征提取的电阻点焊质量在线评判

以焊点接头强度作为焊点质量评判的指标,通过对点焊过程焊接电流、动态电阻、电极位移信号的同步采集和特征分析,提取若干特征参量监测点焊过程,依据特征参量与焊点接头抗剪强度间的相关分析结果,选取来自不同监测信号的7个特征参量建立了表征点焊过程的特征模式,并将此转化为计算机可以识别的模式矩阵,同时以焊接电流参数为模式分类的依据,建立不同模式矩阵类别和焊点接头抗剪强度之间的映射,将模式矩阵作为Hopfield神经网络的记忆样本存储于网络,利用网络联想记忆的功能实现对未知样本点焊过程的模式识别,进而实现点焊质量的评判。网络测试结果表明,利用Hopfield网络进行焊点质量在线评判可以得到满意的效果。     

精密逆变电阻点焊的应用

首先介绍了精密逆变电阻点焊机系统，包括系统的组成，特点，然后介绍几种典型工件的焊接工艺，结果表明，这种焊机在精密零件 的电阻点焊中有其独持的工艺优势，有很好的推广应用价值。     

Parameter selecting and quality predicting of spot welding based on artificial neural networks

This paper proposes a procedure for using artificial neural networks (ANN) in spot welding, and estabishesspot wilding parameter selecting ANN systems and sopt welding joint quality predicting ANN systems.It has been provedthat the ANN systems have high prediction precision ,providing a new way of parameter selecting and quality predicting in spot welding.     

Artificial neural networks applied to spot welding process modeling

Artificial neural networks have been studied for applicability for modeling of spot welding process. Some basic concepts relating to neural networks are explained as well as how they can be used to model welding quality parameters in terms of the welding process parameter. The performance of the neural networks for modeling is presented and evaluated using actual welding data. It is concluded that neural network modeling is a good means of estimating spot welding quality on-line.     

数学化电阻点焊控制器

根据电阻点焊的控制要求,设计了基于微处理器技术的数字化点焊控制器。控制器基于PHILIPS的80C552单片机设计,具有焊接程序控制、焊接电流波形调制、故障诊断等功能;控制器提供了基于LCD显示与键盘输入的数字化参数设置界面对控制器的可靠性设计进行了分析,采取了硬件和软件的抗干扰措施。试验证明设计的点焊数字控制器具有良好的动态特性。     

基于并口的点焊工艺参数测试及缺陷信息分析

利用单片机和计算机构建了基于并口通讯的铝合金冲击波点焊工艺参数测试系统,利用LabVIEW开发了界面友好的测试系统软件.所建立的测试系统具有抗干扰强、可靠性高、采集速度和传输速度快、可扩充能力强等优点,测试系统软件不仅具有通讯、数据操作等功能,还具有数据库和数据分析功能.对所采集的点焊工艺参数曲线分析研究表明,电极电压曲线上的"塌陷"状突变信号和电极压力曲线上的高频躁动突变信号可用来识别前期喷溅,对于后期喷溅,只能利用电极压力曲线上的高频躁动突变信号来进行识别.电极压力曲线上的热膨胀上升量和锻压力下降量可用来识别未熔合及未完全熔合缺陷.     

基于人工神经网络的点焊熔核直径预测

从电极位移曲线上提取出的两个特征值及焊接能量值作为输入值,熔核直径为输出值,建立了基于BP算法的铝合金直流点焊熔核直径预测模型.该模型为隐层结点数为5的三层结构,隐层转移函数为Sigmoid函数,输出层的转移函数为线性函数.对实测结果与仿真结果进行了对比分析,结果表明,45.2%的预测值与实测值相差不超过0.5 mm,77.4%的预测误差不超过1 mm,94.3%的预测误差没有超过2 mm.回归分析结果为A=0.878T 0.982.     

基于核Fisher判别分析的点焊质量评估

通过对点焊过程电极位移信号的实时采集和特征分析,利用模糊化方法将电极位移信号映射为15×25模式矩阵.依据不同焊接电流参数下位移信号的模式特征将位移信号的模式分为5类,分别对应不同的焊点质量.以不同类别焊点的模式矩阵构建输人数据空间,利用核Fisher判别技术将低维数据空间的非线性分类问题转化为高维特征空间的线性分类问...