动力子结构法中Ritz基的一种选择

基于弹性动力学变分原理,本文导出了混合型动力子结构方法的一种Ritz基矢量,即采用正交化的块Lanczos基代替主模态,结出了相应的子结构模态变换的格式和综合后的系统方程式.文未给出了算例.     

不等厚度表板夹层板的问题

给出不等厚表板Пpycakob－杜庆华型夹层板正则形式全场方程及广义变分原理。     

A low-cost digitized microscope stage for linear measurements

A low-cost device for making fine, but repetitive linear measurements under the binocular microscope is described. Linear displacement is coupled on to digital callipers which read the measurements in numerical values. The accuracy of the measurements was such that their 95% confidence interval was within 0·01 mm when read through the apparatus. The data were assimilated on a computer and then transmitted into a PC for analysis.     

弱导非线性自聚焦光纤无量纲模式参量的变分公式

用变分法导出了弱导近似下非线性自聚焦光纤线偏振模的无量纲在量和传播常数的解析式，结果由归一化频率，光功率和临界自降焦功率给出。     

Variational principles for non‐conforming finite element methods

Variational principles with relaxed inter‐element continuity requirement for non‐conforming element methods in linear and non‐linear analyses are developed. Based on the principles, any non‐conforming element displacement can be used directly to derive the explicit expressions of non‐conforming displacement function, which can ensure the passage of the patch test C for the requirement of convergence Copyright © 2001 John Wiley & Sons, Ltd.     

A uniform deformation gradient hexahedron element with artificial hourglass control

An 8-noded linear hexahedron element for large strain hyperelastic analysis is presented in this paper. The element is based on a constant deformation gradient interpolation and is formulated using a mixed variational principle of the Hu–Washizu type. Volumetric and isochoric components of the deformation are treated independently to ensure the correct evaluation of the element volume. A simple procedure to control the propagation of spurious hourglass deformation modes is also discussed. This is based on the addition of artificial hourglass forces which vanish under constant deformation gradient conditions, thereby ensuring that the element passes a non-linear version of the patch test. Applications in the field of neo-Hookean materials and superplastic forming processes are also considered.     

矿用永磁直驱电机异响声信号降噪方法研究

针对矿用永磁直驱电机异响声信号噪声干扰大,有用信号被噪声淹没难以提取的问题,提出一种融合改进VMD与小波软阈值的降噪方法。首先,利用粒子群算法优化变分模态分解算法得到分解层数k和惩罚因子α的最优参数组合,基于最优参数组合分解获得矿用永磁直驱电机异响声信号k个本征模态分量(IMF)。其次,利用加权裕度指标筛选出有效信号分量和需进一步分解的含噪分量,基于小波软阈值对含噪分量进一步降噪。最后,将有效信号分量与小波软阈值降噪后的分量重构得到最终降噪信号。应用此方法分别对仿真信号和矿用永磁直驱电机异响声信号降噪,并与其他方法对比。试验结果表明,该方法能将仿真信号信噪比提升至27.524 7 dB,均方根误差降低至0.085 5,实测信号信噪比提升至34.715 3 dB,均方根误差降低至0.006 7,降噪效果较好,为后续的故障特征提取与故障诊断工作提供数据基础。     

Network traffic prediction model based on improved VMD and PSO-ELM

The rapid update of computing power leads to exponential data traffic growth, and the incidence of network attacks is also increasing. It is significantly important to analyze and predict network traffic accurately in the early stage and take corresponding preventive measures. The existing network flow integrated forecasting models still have some bottlenecks that are difficult to solve, for example, the slow optimization speed of modal decomposition parameters, easy falling into local optimal solutions, the slow convergence speed of the training process, and poor generalization capability. In this paper, particle swarm optimization (PSO) is utilized to improve the parameters selection process of the variational mode decomposition (VMD) algorithm and the extreme learning machine (ELM) algorithm. First, the PSO-VMD combined with multi-scale permutation entropy (MPE) is utilized to decompose the original network flow, and multiple eigenmode components are obtained. Second, the PSO-ELM is utilized to train the network traffic prediction model, and the PSO parameters in PSO-ELM are updated through adaptive weight adjustment and synchronous learning factors to increase the training and prediction speed, and the component prediction results are reconstructed to get a high-precision network flow forecasting result. Finally, through the prediction and verification of the public network flow data of the WIDE backbone, the result of this experiment indicates that the VMD-PSO-ELM can break through the bottlenecks of slow optimization speed of VMD decomposition parameters, reduce the computational complexity of ELM, accelerate the convergence speed, and increase the forecasting accuracy.     

VMD和混合深度学习框架融合的短期风速预测

风速预测是影响风电场效率和稳定性的重要因素.文中基于风速的时空特征,融合变分模态分解(VMD)和混合深度学习框架进行短期风速预测,即VHSTN (VMD-based hybrid spatio-temporal network).其中,混合深度学习框架由卷积神经网络(CNN)、长短时记忆网络(LSTM)以及自注意力机制(SAM)组成.该算法对原始数据清洗后,采用VMD将多站点风速的时空数据分解为固有模态函数(intrinsic mode functions, IMF)分量,去除风速数据的不稳定性;然后针对各IMF分量,应用底部的CNN抽取空域特征;再用顶层LSTM提取时域特征,之后用SAM通过自适应加权加强对隐藏特征的提取并得到各分量的预测结果;最后合并获得最终预测风速.在数据集WIND上进行实验,并和相关典型算法对比,实验结果表明了该算法的有效性和优越性.     

结合知识图谱的变分自编码器零样本图像识别

近年来,结合生成模型的零样本算法得到了广泛的研究,但此类方法通常仅使用属性注释,缺少类别语义,而单一信息对类别表征能力不够强,容易产生域偏移,影响知识迁移的效果,进而降低分类结果的准确率。为了解决此问题,提出一种结合知识图谱变分自编码器零样本识别算法（KG-VAE）,通过构建联合类别分级结构,类别文本描述和词向量的层次结构化知识图谱作为语义信息库,将知识图谱中丰富的语义知识结合到以变分自编码器为基础的生成模型中,使生成的潜在特征更好保留有效的判定性信息,减小域偏移,促进知识迁移。在四个公开的零样本数据集上进行了实验,对比基准方法 CADA-VAE,分类平均准确率有一定的提高;同时利用消融实验证明了知识图谱作为语义辅助信息的有效性。