基于SMOTE-IKPCA-SeNet深度迁移学习的小批量生产质量预测研究

随着智能制造技术的发展和客户个性化需求的增加,多品种小批量生产方式逐渐成为制造业的主流。面向大批量生产、以统计过程控制为核心的质量管理方式并不适用于小批量生产。针对复杂生产过程存在参数多、非线性和交互作用的问题,提出利用深度迁移学习的方式将历史生产数据作为源域迁移至小样本目标产品数据进行质量预测。首先,通过合成少数类过采样技术(synthetic minority over-sampling technique,SMOTE)和改进的核主成分分析(improved kernel principal component analysis,IKPCA)算法筛选源域和目标域的可迁移特征,这不仅兼顾了特征重要性和可迁移性,还减少了“负迁移”,提高了模型泛化能力;然后,采用结合通道注意力机制的卷积神经网络SeNet构建基于深度迁移学习的质量预测模型。仿真结果表明,随着目标域样本的增加,所提方法的预测准确性明显优于广泛采用的支持向量机建模方法。同时,所提可迁移特征筛选方法显著提高了深度迁移学习的质量预测效果,为复杂的小批量生产过程质量保证提供了新方法。

基于KPCA-LSSVM的回采工作面瓦斯涌出量的预测

为了提高瓦斯涌出量预测精度,针对瓦斯涌出量影响因素具有线性重叠、高维非线性等问题,提出使用核主成分分析法(KPCA)对影响因素进行非线性降维。选取沈阳某矿30组样本数据,以前24组数据作为训练集,后6组数据作为测试集,将确定后的核主成分作为最小二乘支持向量机(LSSVM)的输入变量,建立KPCA-LSSVM预测模型,将预测结果与PCA-LSSVM、LSSVM、多元非线性回归、KPCA-BP神经网络、PCA-BP神经网络以及BP神经网络预测结果进行对比。以最大相对误差绝对值作为模型预测精度的评价指标。研究结果表明:当选取前4个核主成分时,即达到模型训练要求。KPCA-LSSVM模型的预测最大相对误差绝对值为5.89%,预测精度均优于其他6种对比模型。研究结果可为实现瓦斯涌出量高精度预测提供参考。

基于KPCA-FCM工况精简的机组燃烧优化

针对深度调峰下运行工况频繁变动使锅炉燃烧优化参数调整难度增大的问题,提出了一种基于KPCA-FCM工况精简的燃烧优化方法。首先对锅炉实际历史运行数据提取稳态工况后,通过核主成分分析法(KPCA)进行降维,选取贡献率较大的运行参数利用模糊聚类算法(FCM)进行分析完成工况划分,实现对工况的精简。然后对不同的燃烧工况匹配对应的工况簇,调整燃烧参数到该类的最佳运行参数。为了验证该方法的合理性,采用最小二乘支持向量机辨识锅炉燃烧热效率模型。以高低两个工况区间为例进行仿真验证,结果表明提取到的最优运行参数目标值可以使锅炉热效率最高提升0.2%。因此,提出的工况精简方法可有效选取最优运行目标值,为现场运行人员调整运行参数提高锅炉效率提供了合理的数据参考。

基于肌音信号的KPCAGASVM步态模式识别

外骨骼机器人发展迅速,基于生理信号的运动意图识别在人机协同控制研究中得以重视。针对肌电信号易受肌肉疲劳影响和采集要求高的缺点,提出一种基于肌音信号的核主成分分析和改进支持向量机(KPCAGASVM)的模式识别方案,对平地行走、上楼下楼和上坡下坡5种步态进行模式识别研究。基于遗传算法进行参数调优,其识别方案KPCAGASVM的识别准确率为97.33%,优于PCAGASVM和其他分类器。实验验证,基于肌音信号的KPCAGASVM为一种高效的步态运动识别方案。

Lagrangian coherent structure analysis on transport of Acetes chinensis along coast of Lianyungang,China

Spatial heterogeneity or“patchiness”of plankton distributions in the ocean has always been an attractive and challenging scientific issue to oceanographers.We focused on the accumulation and dynamic mechanism of the Acetes chinensis in the Lianyungang nearshore licensed fishing area.The Lagrangian frame approaches including the Lagrangian coherent structures theory,Lagrangian residual current,and Lagrangian particle-tracking model were applied to find the transport pathways and aggregation characteristics of Acetes chinensis.There exist some material transport pathways for Acetes chinensis passing through the licensed fishing area,and Acetes chinensis is easy to accumulate in the licensed fishing area.The main mechanism forming this distribution pattern is the local circulation induced by the nonlinear interaction of topography and tidal flow.Both the Lagrangian coherent structure analysis and the particle trajectory tracking indicate that Acetes chinensis in the licensed fishing area come from the nearshore estuary.This work contributed to the adjustment of licensed fishing area and the efficient utilization of fishery resources.

基于KPCA和数据处理组合方法神经网络的半球谐振陀螺温度建模补偿方法

针对半球谐振陀螺(HRG)的温度建模与补偿问题,提出基于核主成分分析(KPCA)和数据处理组合方法(GMDH)神经网络的建模补偿方法.通过分析HRG的温度特性和大数据特征,初步确定网络模型的特征向量.为了去除HRG输出数据的相关性和冗余性,引入KPCA并降低特征向量维度.将特征向量代入GMDH神经网络训练,区分训练集和验证集以确定网络权值和网络结构,实现HRG温度漂移的建模与补偿.实验结果表明,单一样本预测时,所提方法预测效果明显好于传统多项式模型;多样本预测时,在4种不同训练样本下,所提方法相比传统多项式模型精度分别提升了48.5%、54.0%、56.3%、68.4%,相比GMDH模型分别提升了3.6%、5.1%、3.8%、8.8%.所提方法能够有效提高HRG在变温工况下的测量精度.

基于KPCA-BiLSTM-iForest的瓦斯体积分数异常智能识别方法

为了实现瓦斯体积分数异常在线精准超前识别,提出1种基于多元异构数据融合的瓦斯体积分数异常识别方法(KPCA-BiLSTM-iForest),该方法采用核主成分分析(KPCA)对非线性数据进行降维和特征提取,提取主要信息并减少计算量,并采用双向长短期记忆神经网络(BiLSTM)对降维后的数据进行瓦斯体积分数预测,利用隔离森林(iForest)根据预测结果及实际值相关数据进行异常检测。研究结果表明:该方法能够提前20 min检测到瓦斯体积分数异常,且异常识别准确率较KPCA-LSTM-iForest方法,KPCA-iForest方法和KPCA-BiLSTM-LOF方法可以提升3个百分点以上。研究结果可为识别瓦斯体积分数异常并提出预警提供依据。

Model reduction of fractional impedance spectra for time–frequency analysis of batteries, fuel cells, and supercapacitors

Joint time–frequency analysis is an emerging method for interpreting the underlying physics in fuel cells,batteries,and supercapacitors.To increase the reliability of time–frequency analysis,a theoretical correlation between frequency-domain stationary analysis and time-domain transient analysis is urgently required.The present work formularizes a thorough model reduction of fractional impedance spectra for electrochemical energy devices involving not only the model reduction from fractional-order models to integer-order models and from high-to low-order RC circuits but also insight into the evolution of the characteristic time constants during the whole reduction process.The following work has been carried out:(i)the model-reduction theory is addressed for typical Warburg elements and RC circuits based on the continued fraction expansion theory and the response error minimization technique,respectively;(ii)the order effect on the model reduction of typical Warburg elements is quantitatively evaluated by time–frequency analysis;(iii)the results of time–frequency analysis are confirmed to be useful to determine the reduction order in terms of the kinetic information needed to be captured;and(iv)the results of time–frequency analysis are validated for the model reduction of fractional impedance spectra for lithium-ion batteries,supercapacitors,and solid oxide fuel cells.In turn,the numerical validation has demonstrated the powerful function of the joint time–frequency analysis.The thorough model reduction of fractional impedance spectra addressed in the present work not only clarifies the relationship between time-domain transient analysis and frequency-domain stationary analysis but also enhances the reliability of the joint time–frequency analysis for electrochemical energy devices.

基于KPCA-GA-BP模型的页岩气集输管道的内腐蚀速率预测

针对页岩气集输管道的内腐蚀,提出了一种基于KPCA-GA-BP组合模型的腐蚀速率预测算法。以某条页岩气集输管道的检测结果作为训练数据,运用反向传播(BP)神经网络建立预测模型,运用遗传算法(GA)优化了神经网络权值和阈值的初始值,运用核主成分分析法(KPCA)对数据进行了降维,在模型建立的过程中不断优化提升模型的预测精度,采用所建模型对另一条相邻管道进行预测并开挖验证。结果表明:选择TRAINGDM作为训练函数,隐含层节点为(8,1),遗传算法进化数为50,种群规模为100,交叉概率为0.3,变异概率为0.2,运用KPCA将数据从7维降为4维后,此模型的均方误差最低为0.12,当该模型用于相邻管道的预测时,均方误差为0.14。运用KPCAGA-BP模型,对页岩气集输管道内腐蚀速率进行预测具有一定的准确性,此模型可用于辅助指导现场内腐蚀直接评价等相关工作。

Application of Isogeometric Analysis Method in Three-Dimensional Gear Contact Analysis

Gears are pivotal in mechanical drives,and gear contact analysis is a typically difficult problem to solve.Emerging isogeometric analysis(IGA)methods have developed new ideas to solve this problem.In this paper,a threedimensional body parametric gear model of IGA is established,and a theoretical formula is derived to realize single-tooth contact analysis.Results were benchmarked against those obtained from commercial software utilizing the finite element analysis(FEA)method to validate the accuracy of our approach.Our findings indicate that the IGA-based contact algorithmsuccessfullymet theHertz contact test.When juxtaposed with the FEA approach,the IGAmethod demonstrated fewer node degrees of freedomand reduced computational units,all whilemaintaining comparable accuracy.Notably,the IGA method appeared to exhibit consistency in analysis accuracy irrespective of computational unit density,and also significantlymitigated non-physical oscillations in contact stress across the tooth width.This underscores the prowess of IGA in contact analysis.In conclusion,IGA emerges as a potent tool for addressing contact analysis challenges and holds significant promise for 3D gear modeling,simulation,and optimization of various mechanical components.

基于KPCA-PSO-LSSVM的轴承寿命预测研究

为了预测不同工况下对于滚动轴承的最大剩余使用寿命(RUL),提出了一种基于核主成分分析(KPCA)结合粒子群优化最小二乘支持向量机(PSO-LSSVM)的滚动轴承RUL预测框架。该方法首先从时域、频域以及小波包域进行轴承故障特征提取,得到一系列退化特征;其次,在尽可能多保留退化特征的前提下,运用KPCA方法进行特征约简;最后采用PSO-LSSVM构建结合的模型来预测滚动轴承的RUL。通过美国智能维护中心(IMS)提供的多组轴承衰退振动信号对模型进行验证,实验结果表明,相比较于PSO-LSSVM和KPCA-LSSVM模型,论文提出的KPCA-PSO-LSSVM的轴承剩余寿命预测方法具有更低的预测误差,可以比较准确出拟合滚动轴承的退化情况。

Preliminary electromagnetic analysis of the COOL blanket for CFETR

The supercritical CO_(2)cOoled Lithium-Lead(COOL)blanket has been designed as one advanced blanket candidate for the Chinese Fusion Engineering Test Reactor(CFETR).This work focuses on the electromagnetic(EM)loads(Maxwell force and Lorentz force)acting on the COOL blanket,which are important mechanical loads in further structural analysis of the COOL blanket.A 3D electromagnetic analysis is performed using the ANSYS finite element method to obtain EM loads on the COOL blanket in this study.At first,the magnetic scalar potential(MSP)method is used to obtain the magnetic field and the Maxwell force on the COOL blanket.Then,the magnetic vector potential(MVP)method is performed during a plasma disruption event to get the eddy current distribution.At last,a multi-step method is adopted for the calculation of the Lorentz force and the torque.The maximum Lorentz forces of inboard and outboard blanket structural components are 5624 kN and 2360 kN respectively.

SFGA-CPA: A Novel Screening Correlation Power Analysis Framework Based on Genetic Algorithm

Correlation power analysis(CPA)combined with genetic algorithms(GA)now achieves greater attack efficiency and can recover all subkeys simultaneously.However,two issues in GA-based CPA still need to be addressed:key degeneration and slow evolution within populations.These challenges significantly hinder key recovery efforts.This paper proposes a screening correlation power analysis framework combined with a genetic algorithm,named SFGA-CPA,to address these issues.SFGA-CPA introduces three operations designed to exploit CPA characteris-tics:propagative operation,constrained crossover,and constrained mutation.Firstly,the propagative operation accelerates population evolution by maximizing the number of correct bytes in each individual.Secondly,the constrained crossover and mutation operations effectively address key degeneration by preventing the compromise of correct bytes.Finally,an intelligent search method is proposed to identify optimal parameters,further improving attack efficiency.Experiments were conducted on both simulated environments and real power traces collected from the SAKURA-G platform.In the case of simulation,SFGA-CPA reduces the number of traces by 27.3%and 60%compared to CPA based on multiple screening methods(MS-CPA)and CPA based on simple GA method(SGA-CPA)when the success rate reaches 90%.Moreover,real experimental results on the SAKURA-G platform demonstrate that our approach outperforms other methods.

Geometric prior guided hybrid deep neural network for facial beauty analysis

Facial beauty analysis is an important topic in human society.It may be used as a guidance for face beautification applications such as cosmetic surgery.Deep neural networks(DNNs)have recently been adopted for facial beauty analysis and have achieved remarkable performance.However,most existing DNN-based models regard facial beauty analysis as a normal classification task.They ignore important prior knowledge in traditional machine learning models which illustrate the significant contribution of the geometric features in facial beauty analysis.To be specific,landmarks of the whole face and facial organs are introduced to extract geometric features to make the decision.Inspired by this,we introduce a novel dual-branch network for facial beauty analysis:one branch takes the Swin Transformer as the backbone to model the full face and global patterns,and another branch focuses on the masked facial organs with the residual network to model the local patterns of certain facial parts.Additionally,the designed multi-scale feature fusion module can further facilitate our network to learn complementary semantic information between the two branches.In model optimisation,we propose a hybrid loss function,where especially geometric regulation is introduced by regressing the facial landmarks and it can force the extracted features to convey facial geometric features.Experiments performed on the SCUT-FBP5500 dataset and the SCUT-FBP dataset demonstrate that our model outperforms the state-of-the-art convolutional neural networks models,which proves the effectiveness of the proposed geometric regularisation and dual-branch structure with the hybrid network.To the best of our knowledge,this is the first study to introduce a Vision Transformer into the facial beauty analysis task.

Evaluation of the seismic behavior of reinforced concrete structures with flat slab-column gravity frame and shear walls through nonlinear analysis methods

This paper presents an investigation of the seismic behavior of reinforced concrete(RC)structures in which shear walls are the main lateral load-resisting elements and the participation of flat slab floor systems is not considered in the seismic design procedure.In this regard,the behavior of six prototype structures(with different heights and plan layouts)is investigated through nonlinear static and time history analyses,implemented in the OpenSees platform.The results of the analyses are presented in terms of the behavior of the slab-column connections and their mode of failure at different loading stages.Moreover,the global response of the buildings is discussed in terms of some parameters,such as lateral overstrength due to the gravity flat slab-column frames.According to the nonlinear static analyses,in structures in which the slab-column connections were designed only for gravity loads,the slab-column connections exhibited a punching mode of failure even in the early stages of loading.However,the punching failure was eliminated in structures in which a minimum transverse reinforcement recommended in ACI 318(2019)was provided in the slabs at joint regions.Furthermore,despite neglecting the contribution of gravity flat slab-column frames in the lateral load resistance of the structures,a relatively significant overstrength was imposed on the structures by the gravity frames.

Erratum to:Vibration analysis of a gear-rotor-bearing system with outer-ring spalling and misalignment

Because of an unfortunate mistake during the production of this article,Figure 13 was wrongly inserted.The corrected Figure 13 is shown as follows.

Advances in microfluidic-based DNA methylation analysis

DNA methylation has been extensively investigated in recent years,not least because of its known relationship with various diseases.Progress in analytical methods can greatly increase the relevance of DNA methylation studies to both clinical medicine and scientific research.Microflu-idic chips are excellent carriers for molecular analysis,and their use can provide improvements from multiple aspects.On-chip molecular analysis has received extensive attention owing to its advantages of portability,high throughput,low cost,and high efficiency.In recent years,the use of novel microfluidic chips for DNA methylation analysis has been widely reported and has shown obvious superiority to conventional methods.In this review,wefirst focus on DNA methylation and its applications.Then,we discuss advanced microfluidic-based methods for DNA methylation analysis and describe the great progress that has been made in recent years.Finally,we summarize the advantages that microfluidic technology brings to DNA methylation analysis and describe several challenges and perspectives for on-chip DNA methylation analysis.This review should help researchers improve their understanding and make progress in developing microfluidic-based methods for DNA methylation analysis.

Stability Analysis of Inverse Lax-Wendroff Procedure for a High order Compact Finite Difference Schemes

This paper considers the finite difference(FD)approximations of diffusion operators and the boundary treatments for different boundary conditions.The proposed schemes have the compact form and could achieve arbitrary even order of accuracy.The main idea is to make use of the lower order compact schemes recursively,so as to obtain the high order compact schemes formally.Moreover,the schemes can be implemented efficiently by solving a series of tridiagonal systems recursively or the fast Fourier transform(FFT).With mathematical induction,the eigenvalues of the proposed differencing operators are shown to be bounded away from zero,which indicates the positive definiteness of the operators.To obtain numerical boundary conditions for the high order schemes,the simplified inverse Lax-Wendroff(SILW)procedure is adopted and the stability analysis is performed by the Godunov-Ryabenkii method and the eigenvalue spectrum visualization method.Various numerical experiments are provided to demonstrate the effectiveness and robustness of our algorithms.

Privacy Protection in COVID Data Tracking: Textual Analysis of the Literature

The literary review presented in the following paper aims to analyze the tracking tools used in different countries during the period of the COVID-19 pandemic. Tracking apps that have been adopted in many countries to collect data in a homogeneous and immediate way have made up for the difficulty of collecting data and standardizing evaluation criteria. However, the regulation on the protection of personal data in the health sector and the adoption of the new General Data Protection Regulation in European countries has placed a strong limitation on their use. This has not been the case in non-European countries, where monitoring methodologies have become widespread. The textual analysis presented is based on co-occurrence and multiple correspondence analysis to show the contact tracing methods adopted in different countries in the pandemic period by relating them to the issue of privacy. It also analyzed the possibility of applying Blockchain technology in applications for tracking contagions from COVID-19 and managing health data to provide a high level of security and transparency, including through anonymization, thus increasing user trust in using the apps.

Molecular cloning,characterization and promoter analysis of LbgCWIN1 and its expression profiles in response to exogenous sucrose during in vitro bulblet initiation in lily

Lily(Lilium spp.) is an important ornamental flower, which is mainly propagated by bulbs. Cell wall invertases(CWINs), which catalyze the irreversibly conversion of sucrose into glucose and fructose in the extracellular space, are key enzymes participating in sucrose allocation in higher plants. Previous studies have shown that CWINs play an essential role in bulblet initiation process in bulbous crops, but the underlying molecular mechanism remains unclear. Here, a CWIN gene of Lilium brownii var. giganteum(Lbg) was identified and amplified from genomic DNA. Quantitative RT-PCR assays revealed that the expression level of LbgCWIN1 was highly upregulated exactly when the endogenous starch degraded in non-sucrose medium during in vitro bulblet initiation in Lbg. Phylogenetic relationship, motif, and domain analysis of LbgCWIN1 protein and CWINs in other plant species showed that all sequences of these CWIN proteins were highly conserved. The promoter sequence of LbgCWIN1 possessed a number of alpha-amylase-, phytohormone-, light-and stress-responsive cis-elements. Meanwhile, β-glucuronidase(GUS) assay showed that the 459 bp upstream fragment from the translational start site displayed maximal promoter activity. These results revealed that LbgCWIN1 might function in the process of in vitro bulblet initiation and be in the response to degradation of endogenous starch.