汽车格栅制品的常见缺陷及解决办法

对汽车通风格栅这种塑料制品在成型的过程中容易产生的填充不足、熔接线/熔接痕、气穴、翘曲、溢料飞边等五种最为常见的缺陷进行了分析,阐述了影响格栅制品成型质量的主要因素,最后提出了防止质量缺陷的产生,获得高质量的格栅制品的措施。     

基于Moldflow的薄板注塑件填充过程研究

本文对薄板注塑件的充填过程进行了充分的研究,对熔体前锋的充填模式、熔接线和气穴位置进行了的快速预测,并与实验结果进行了比较,理论计算模拟的结果与实验结果基本一致.     

基于RBF神经网络水泥强度预测模型的研究

介绍了RBF神经网络的结构、网络的学习算法,针对目前水泥28天强度值预测需时长、精度低的现状,建立了水泥强度RBF网络预测模型并进行了MATLAB仿真试验,表明RBF算法水泥强度的预测模型能很好地跟踪其实测值,且模型训练的速度快。该模型为水泥强度的快速预测提供了一种新方法。     

基于卷积神经网络的GTAW熔透预测

焊接熔池信息能反映熔透状态,但建立熔池与熔透状态的关系十分困难。针对该问题,提出一种基于卷积神经网络(Convolution neural networks,CNN)的GTAW背面熔透预测模型。通过基于被动视觉的熔池二维图像采集,建立了用于CNN网络训练和测试的训练集和测试集。其次建立了CNN背面熔透预测模型,优化了学习率、batch-size、迭代次数等网络参数。研究发现:第一层卷积核尺寸为9×9,最后一层含有64个卷积核使模型在预测准确率和训练时间上综合表现达到最佳。使用训练集数据训练模型,将训练完成的模型在测试集上对背面熔透进行预测,取得了高于96%的预测准确率。通过对预测模型的特征映射进行可视化分析,模型是通过熔池边缘,反光点位置和熔池尾部等特征来预测背面熔透情况。     

结晶性塑料制品注塑成形质量在线监测方法研究

结晶性材料的结晶度与塑料制品质量有紧密联系。利用电容传感器的物理特性,通过测量注塑成形过程中的结晶度来实现制品质量的在线监测,重点研究了熔体温度、注塑压力、注塑时间及保压压力对结晶度的影响机制,同时分析了工艺参数-结晶度-力学性能的关系,设计并制造出了一套注塑模具进行试验验证。试验结果表明,随着结晶度的增大,注塑件的拉伸强度和弯曲强度随之增大,通过调控工艺参数,能有效控制制品的结晶度,进而得到优良力学性能的注塑制品。     

基于神经网络的激光熔覆高度预测

激光成形过程中,对熔覆高度进行实时检测,从而实现熔覆高度闭环控制是成形高质量零件的保证.激光成形过程是一个多参数耦合的非线性过程,大量激光参数对成形熔覆表面质量具有重要影响.在分析激光参数对熔覆高度影响的基础上,建立利用激光工艺参数预测熔覆高度的误差反向传播(Back propagation,BP)神经网络模型,完成了网络算法设计.通过激光成形试验采集样本,利用训练样本对所建立的网络进行训练,完成网络输入输出高度映射关系,并利用测试样本对所训练的网络进行检验.仿真试验表明,神经网络熔覆高度预测模型具有很高的精度,验证了该预测模型在理论和实践上的可行性与有效性.神经网络熔覆高度预测模型为实现激光加工过程熔覆高度实时预测与闭环控制打下基础,对提高成形产品质量具有重要意义.     

薄壁件残余应力变形仿真预测与切削参数优化

针对薄壁件铣削残余应力变形难以准确预测的问题,提出了一种仿真预测方法,并在此基础上研究了薄壁件铣削切削参数优化方法。首先,提出了基于工况映射与薄壳应力贴合的残余应力变形仿真预测方法,实验结果表明该方法能够有效预测薄壁件的加工残余应力变形。在此基础上,利用支持向量回归机建立了基于切削参数的残余应力变形响应预测模型;然后,根据所建立的预测模型,采用遗传算法,以残余应力变形为约束、最大加工效率为目标对工艺参数进行优化。结果分析表明,该优化方法获得了最优的加工参数。     

切削数据预测分析方法研究

数据预测分析是切削数据库的重要功能之一,文中采用回归分析预测法、有限元分析方法与神经网络预测方法建立了切削力预测模型。通过切削实验验证了模型的准确性,并对不同模型的数据来源特点与预测精度进行了分析研究。获得的结果可以为预测模型的建立与预测方法的选择提供理论支撑。     

轮盘低周疲劳寿命预测的一种新方法

低循环疲劳失效是轮盘失效的主要形式。为了找到更加精确可靠地预测轮盘低周疲劳寿命的方法,基于三参数幂函数公式,提出了描述Walker等效应变参量与疲劳寿命关系的修正寿命预测模型。应用修正寿命预测模型对1Cr11Ni2W2Mo V、GH4133、TC4及TC11合金材料不同条件下的低周疲劳试验数据进行模拟,发现拟合曲线能够很好地描述Walker等效应变与寿命之间的关系,寿命预测点全部位于2倍分散带内。采用不同方法对高压压气机I级盘60℃下的寿命进行预测,并将预测结果与轮盘试验值进行比较。结果表明:修正模型的预测寿命值为1 048,与试验值1 340相近,相对误差仅为-21.8%,预测精度明显高于另外三种模型,并且修正模型能够考虑平均应力的变化对疲劳寿命所产生的影响,可为发动机轮盘的低周疲劳寿命预测提供参考方法。     

基于人工神经网络的激光点焊焊点形态预测

建立适用于激光点焊焊点形态预测的人工神经网络模型,以点焊过程中的三个主要工艺参数(激光功率、点焊时间和离焦量)作为模型输入,输出为焊点表面、熔合面、背面直径以及熔深和横截面面积五个焊点形态参数。在此基础上,建立焊点形态模型,模型输入为神经网络的预测结果,输出为焊点形态。所建立的神经网络预测模型和焊点形态模型结合之后,可以实现激光点焊焊点的形态预测。网络测试结果显示实际值与网络预测值之间的RMS误差为0.1左右,模型输出的预测焊点形态与实际焊点形态之间较为吻合。根据模型的仿真结果,进一步研究点焊参数对焊点尺寸和形态的影响规律。结果表明未熔透焊点形态为Y形,而熔透焊点则存在多种形态,形态之间的转变主要受激光功率的影响。     

Reducing the effects of weldlines on appearance of plastic products by Taguchi experimental method

Weldlines influence not only strength of injection products but also the appearance of the products. This paper studies the effects of processing parameters on the appearance of weldlines by Taguchi experimental design method. Weldlines are obtained by the right door of copy machine which is modeled with three gates. The pictures of molding products are taken by digital camera. The samples of products and weldlines are extracted by software photoshop. The hue values of the samples of products and weldlines are calculated by software matlab. The visibility of weldlines is defined with the difference of the hue values of products and weldlines. By analysis, it turns out melt temperature, injection velocity, and injection pressure are the main factors which influence the appearance of weldlines.     

液压调速阀流场分析

建立液压调速阀动力学模型和内部流道三维模型,利用计算流体动力学(CFD)分析调速阀流场,取得了液压调速阀稳态时内部压力场、速度场的分布规律以及阀体壁面粗糙度对其的影响规律。分析结果表明:出口可变节流孔处压力损失较大,且油液以喷射流形式流出,阀口需采用抗冲刷及高强度材料;阀体壁面粗糙度对压力损失有影响。计算结果与实验结果一致。     

Frequency-dependent damping model for the hydroacoustic finite element analysis of fluid-filled pipes with diameter changes

The integration of a model for longitudinal hydroacoustic fluid damping in thin hydraulic pipes in 3D finite element models is presented in this paper. In order to perform quantitative prediction of the vibroacoustic behavior and resulting noise levels of such fluid-structure coupled system due to hydraulic excitation, an accurate frequency-dependent fluid damping model including friction effects near the pipe wall is required. This step is achieved by matching complex wave numbers from analytical derivation into a parameterized damped wave equation and consecutive translation into finite element modeling.Since the friction effect close to the pipe wall changes locally with the inner pipe radius, the fluid damping model is applied segment-wise in order to model the influence of cross-sectional discontinuity, such as orifices, on the oscillating pressure pulsations. A component synthesis approach, which uses pipe segments as substructures, allows a simple model generation and fast computation times.The numerical harmonic results are compared to experimental frequency response functions, which are performed on a hydraulic test bench driven by a dynamic pressure source in the kHz-range.     

钢制薄壁内压短圆筒静强度的试验研究

分析认为钢制薄壁内压圆筒存在类似于钢制薄壁外压圆筒的长、短之分。基于试验研究,推导得到了确定钢制薄壁内压短圆筒静强度的经验公式,以及区分内压长、短圆筒的临界长度计算公式;27组试验数据证明了经验公式的有效性。     

内压及壁厚对充气支撑结构模态影响的仿真分析

为研究内压及壁厚对充气支撑结构固有频率和振型的影响,对不同壁厚的充气支撑结构施加适量的内压,应用薄壳的无矩理论求解出充气支撑结构的应力,并以此应力作为结构的预应力求解多自由度系统的动力学基本方程进行模态计算,采用兰索斯法提取了结构的固有频率和振型的分析结果.结果表明:在0～5000 Pa的压力范围内,低阶频率几乎不受内压的影响,而高阶振动频率随着内压的增大而增大,内压对结构高阶频率的影响是不可忽视的;内压在影响结构固有频率的同时也改变了结构的振型;低阶频率几乎不受壁厚变化的影响;内压的存在降低了壁厚对结构高阶振动频率的影响.     

一种高强度、高稳定性铸铁的研究及应用

试验采用高Si/C比、Mo与Cu低合金化、强化孕育等工艺方法,生产低应力高强度铸铁,并用静态弯曲和开口环测应力法,对普通铸铁和高强度铸铁的弹性模量、应力松弛性能进行了对比试验。结果表明,高Si/C比、低合金化的高强度铸铁,能够满足大型精密仪器薄壁基础铸件的高刚度、高稳定性要求。     

薄壁身管强度分析

某型号步兵战车配有100mm低膛压火炮,该炮身管距炮口945mm的范围内为薄壁圆筒.文章以该段薄壁身管为研究对象,将其简化为内压薄壁圆筒,在只考虑切向应力的情况下,通过静力学理论分析和有限元分析(软件ANSYS)对其强度进行了求解和对比,结果证实两种方法虽均切实可行,但相比之下理论公式更为精确.     

Application of a neural network to predict thickness strains and finite element simulation of hydro-mechanical deep drawing

In this paper an artificial neural network (ANN) is used to predict the thickness along a cup wall in hydro-mechanical deep drawing. This model uses a feed-forward back-prorogation neural network. After using the experimental results to train and test the network, the model was applied to new data for the prediction of thickness strains in hydro-mechanical deep drawing. The results are promising. In the present work, we also attempt to perform a finite element simulation of the process for the two dimensional axi-symmetric case using explicit finite element code LS-DYNA 2D. Counter pressure on the blank is applied by specifying the pressure boundary conditions. A comparison was made between simulated, experimental and ANN results of hydro-mechanical deep drawing using low carbon extra deep drawing grade steel sheets of 0.96 mm thickness. It was also found that by hydro-mechanical deep drawing, a higher drawability and a more uniform thickness distribution were obtained when compared to conventional deep drawing.     

Prediction of the sound pressure level of blanking noise during sheet-metal blanking using servo press with counterforce

In this research, a prediction model of the sound pressure level during blanking using servo press with counterforce was established based on the acoustic theory as well as the vibration equation of punch in the course of breakthrough process. The theoretical values of the sound pressure level of blanking noise were calculated based on the developed prediction model. The variation of the sound pressure level of blanking noise with different parameters was also investigated and compared with the experimental results. It reveals that the blanking noise increases with the shear strength and the thickness of sheet metal, and further the blanking speed. The relative error between the experimental results and the theoretical ones determined based on the prediction model is less than 1.7%, and the application example of the prediction model in batch production is given. The prediction model is thus proved to be promising and efficient for noise prediction during blanking using servo press with counterforce.     

薄壁箱形梁的焊接变形预测

通过试验和理论的结合,对薄壁箱形梁的焊接变形进行了预测。主要采用热弹塑性有限元法分析焊接时梁的变形情况,结果与实际吻合得非常好,为后面预测大型薄壁结构的焊接变形奠定了基础。