Research on aiming methods for small sample size shooting tests of two-dimensional trajectory correction fuse

The longitudinal dispersion of the projectile in shooting tests of two-dimensional trajectory corrections fused with fixed canards is extremely large that it sometimes exceeds the correction ability of the correction fuse actuator.The impact point easily deviates from the target,and thus the correction result cannot be readily evaluated.However,the cost of shooting tests is considerably high to conduct many tests for data collection.To address this issue,this study proposes an aiming method for shooting tests based on small sample size.The proposed method uses the Bootstrap method to expand the test data;repeatedly iterates and corrects the position of the simulated theoretical impact points through an improved compatibility test method;and dynamically adjusts the weight of the prior distribution of simulation results based on Kullback-Leibler divergence,which to some extent avoids the real data being"submerged"by the simulation data and achieves the fusion Bayesian estimation of the dispersion center.The experimental results show that when the simulation accuracy is sufficiently high,the proposed method yields a smaller mean-square deviation in estimating the dispersion center and higher shooting accuracy than those of the three comparison methods,which is more conducive to reflecting the effect of the control algorithm and facilitating test personnel to iterate their proposed structures and algorithms.;in addition,this study provides a knowledge base for further comprehensive studies in the future.

Reliability Assessment for the Solenoid Valve of a High-Speed Train Braking System under Small Sample Size

Reliability assessment of the braking system in a high?speed train under small sample size and zero?failure data is veryimportant for safe operation. Traditional reliability assessment methods are only performed well under conditions of large sample size and complete failure data,which lead to large deviation under conditions of small sample size and zero?failure data. To improve this problem,a new Bayesian method is proposed. Based on the characteristics of the solenoid valve in the braking system of a high?speed train,the modified Weibull distribution is selected to describe the failure rate over the entire lifetime. Based on the assumption of a binomial distribution for the failure probability at censored time,a concave method is employed to obtain the relationships between accumulation failure prob?abilities. A numerical simulation is performed to compare the results of the proposed method with those obtained from maximum likelihood estimation,and to illustrate that the proposed Bayesian model exhibits a better accuracy for the expectation value when the sample size is less than 12. Finally,the robustness of the model is demonstrated by obtaining the reliability indicators for a numerical case involving the solenoid valve of the braking system,which shows that the change in the reliability and failure rate among the di erent hyperparameters is small. The method is provided to avoid misleading of subjective information and improve accuracy of reliability assessment under condi?tions of small sample size and zero?failure data.

An Improved Algorithm for Imbalanced Data and Small Sample Size Classification

Traditional classification algorithms perform not very well on imbalanced data sets and small sample size. To deal with the problem, a novel method is proposed to change the class distribution through adding virtual samples, which are generated by the windowed regression over-sampling (WRO) method. The proposed method WRO not only reflects the additive effects but also reflects the multiplicative effect between samples. A comparative study between the proposed method and other over-sampling methods such as synthetic minority over-sampling technique (SMOTE) and borderline over-sampling (BOS) on UCI datasets and Fourier transform infrared spectroscopy (FTIR) data set is provided. Experimental results show that the WRO method can achieve better performance than other methods.

Wasserstein GAN-Based Small-Sample Augmentation for New-Generation Artificial Intelligence: A Case Study of Cancer-Staging Data in Biology

It is essential to utilize deep-learning algorithms based on big data for the implementation of the new generation of artificial intelligence. Effective utilization of deep learning relies considerably on the number of labeled samples, which restricts the application of deep learning in an environment with a small sample size. In this paper, we propose an approach based on a generative adversarial network (GAN) combined with a deep neural network (DNN). First, the original samples were divided into a training set and a test set. The GAN was trained with the training set to generate synthetic sample data, which enlarged the training set. Next, the DNN classifier was trained with the synthetic samples. Finally, the classifier was tested with the test set, and the effectiveness of the approach for multi-classification with a small sample size was validated by the indicators. As an empirical case, the approach was then applied to identify the stages of cancers with a small labeled sample size. The experimental results verified that the proposed approach achieved a greater accuracy than traditional methods. This research was an attempt to transform the classical statistical machine-learning classification method based on original samples into a deep-learning classification method based on data augmentation. The use of this approach will contribute to an expansion of application scenarios for the new generation of artificial intelligence based on deep learning, and to an increase in application effectiveness. This research is also expected to contribute to the comprehensive promotion of new-generation artificial intelligence.

Metal Corrosion Rate Prediction of Small Samples Using an Ensemble Technique

Accurate prediction of the internal corrosion rates of oil and gas pipelines could be an effective way to prevent pipeline leaks.In this study,a proposed framework for predicting corrosion rates under a small sample of metal corrosion data in the laboratory was developed to provide a new perspective on how to solve the problem of pipeline corrosion under the condition of insufficient real samples.This approach employed the bagging algorithm to construct a strong learner by integrating several KNN learners.A total of 99 data were collected and split into training and test set with a 9:1 ratio.The training set was used to obtain the best hyperparameters by 10-fold cross-validation and grid search,and the test set was used to determine the performance of the model.The results showed that theMean Absolute Error(MAE)of this framework is 28.06%of the traditional model and outperforms other ensemblemethods.Therefore,the proposed framework is suitable formetal corrosion prediction under small sample conditions.

尺寸效应对岩石单轴压缩试验影响研究

为探究尺寸效应对小尺寸岩样单轴压缩试验的影响规律,通过在室内伺服试验机上对直径25 mm,不同长度的花岗岩岩样进行单轴压缩试验,研究尺寸效应对小尺寸花岗岩岩石力学参数以及破坏形式的影响规律。试验结果表明,随着长径比增加,岩样表现出抗压强度和泊松比逐渐减小,弹性模量增加的趋势。其中,多项式模型较为适合小尺寸岩样尺寸效应强度模型;不同长径比岩样的单轴压缩试验应力应变曲线加载趋势不同,其峰值应变随着长径比的增加而减小;随着长径比的增加,岩石破坏形式从脆性剪切破坏转变为剪切破坏,最后逐步变为脆性破坏,岩样破坏面数量与角度出现规律性变化。当长径比在1.1~2.2时,岩样破坏形式遵循相同的破坏准则,通过拟合公式推导不同长径比岩样的力学参数存在可行性;岩石单轴试验破坏过程中的能量与长径比呈负相关,且当长径比在1.9~2.2时,各能量变化幅度趋于平缓,岩样破坏形式较为统一,其强度在数值上表现的差异性较小,可作为小尺寸岩样单轴试验的最佳长径比。

最大熵试验法对切割器功能可靠性的评估

针对切割器设计裕度大且刺激能量服从正态分布的特点,提出采用最大熵试验法对切割器的功能可靠性进行评估。以某型切割器为实例,通过临界药量摸底试验、升降法试验及成败型试验对其功能可靠性进行了评估。结果表明:运用最大熵试验法,采用46个试验样本即可完成切割器在置信度γ=0.95下,可靠性指标不小于0.999 995的可靠性评估试验,为航天火工装置(尤其是切割器)的小样本量高可靠性评估提供了技术途径。

基于改进3E-LDA的织物图像分类算法

针对训练样本数太少(训练样本数量小于数据维数)导致的模型分辨能力下降问题,提出了一种基于正则化改进3E-LDA的织物图像分类算法(I3E-LDA算法)。首先利用类加权中值代替样本均值计算类内散点矩阵,削弱离群值和噪声的影响,以此作为非参数加权特征提取法对类内散点矩阵进行正则化。然后利用目标组合的方法,通过引入平衡参数对目标函数进行正则化,来保留更具判别性的特征数据。通过不同织物图像间更具判别性的特征数据可以更好地对其区分。结合改进的零空间法解决类内散点矩阵奇异性和小样本问题,从而提高分类准确率。在阿里天池织物数据集和花色织物图像上进行训练和测试,将图像按照正常图像和非正常图形(瑕疵图像)进行区分。实验结果表明,I3E-LDA算法有效实现了织物图像分类,且对于较少的训练样本(20%~40%的样本用于训练)提升了分类精度。

适用小样本的并网光伏阵列故障诊断方法

该文提出一种适用小样本的并网光伏阵列故障诊断方法。首先,使用光伏阵列的稳态输出电信号时间序列构建特征向量,论证该特征向量可以表征正常、开路故障、短路故障、阴影等不同状态。其次,针对光伏阵列运行环境多变的情况,提出一种将实际气象条件下光伏阵列输出值转换到统一工况下的数据处理方法。然后,为适用小样本情况,将线性判别分析方法与有偏差的协方差估计、公共奇异值分解相结合,解决样本高维低量导致的样本协方差矩阵估计奇异和判别函数求解困难的问题。最后,在上海市某高校楼顶搭建实验平台,采集光伏阵列不同状态下的实验数据,验证了所提数据处理方法对使用稳态电信号的必要性,及该故障分类算法在小样本场景中的有效性。

基于多任务学习的间质性肺病分割算法

间质性肺病(ILD)的分割标签标注成本极高,且现有数据集通常存在样本量较少的问题,导致训练的模型效果较差。针对该问题,提出一种基于多任务学习的ILD分割算法。首先,基于U-Net构建多任务分割模型;其次,使用生成的肺部分割标签作为辅助任务标签进行多任务学习;最后,使用一种自适应调整多任务损失函数权重的方法,平衡主任务和辅助任务的损失。在自构建的ILD数据集上的实验结果表明,多任务分割模型的Dice相似系数(DSC)达到了82.61%,与U-Net相比提升了2.26个百分点。验证了所提算法可以提升ILD的分割性能,协助临床医生进行ILD诊断。

15-15Ti奥氏体不锈钢热老化小尺寸试样单轴拉伸行为的GTN微观损伤模型研究

通过加速热老化试验模拟了15-15Ti奥氏体不锈钢的辐照效应,构建了Ramberg-Osgood力学本构模型和GTN(Gurson-Tvergaard-Needleman)微观损伤模型。结合有限元方法,探讨了热老化不同时间的15-15Ti奥氏体不锈钢小尺寸试样在不同温度拉伸试验过程中的应力-应变响应行为和损伤断裂过程。结果表明:热老化小尺寸试样中有少量碳化物析出和大量σ相形成,导致其抗拉强度和屈服强度显著下降;未热老化试样的拉伸断口中有大量韧窝,为韧性断裂,而热老化试样的拉伸断口中韧窝数量明显减少,析出相周围有撕裂棱,为脆性断裂;热老化试样标距段的应力集中和颈缩均延迟发生;热老化试样的断裂应变明显小于未热老化试样;热老化能促使小尺寸试样中孔洞的聚集和增多,从而加速失效。

高置信水平结构逆可靠度分析与优化方法研究进展

不确定性客观存在于工程结构生产制造以及服役等各环节之中并对结构的承载性能影响显著.特别是对于服役条件苛刻的航空航天承载装备,在设计阶段考虑多源不确定性的影响对于结构安全至关重要.在众多不确定性分析方法中,逆可靠度分析方法在效率和稳健性方面具有一定优势.为此,国内外学者在高置信水平结构逆可靠度分析与优化方法方面开展了大量研究并取得了长足进步,包括自适应迭代控制算法、先进可靠度优化策略与非充分样本下的高置信水平设计方法等.本文首先对国内外逆可靠度分析与优化方法取得的进展进行了系统梳理与总结,特别是逆可靠度分析方法的发展历程以及面临的挑战问题,主要包括强非线性功能函数、多设计点以及低失效概率问题.进一步,针对长期困扰可靠度方法实际应用的小样本问题,重点从结构高置信水平可靠度分析与优化理论角度开展系统介绍,详细论述了小样本诱发的认知不确定性到可靠度置信水平的传播链条.最后,基于现有成果和国家重大前沿需求,重点围绕航天装备可重复使用需求对结构可靠度未来研究方向进行了思考与展望,期望相关研究成果能够进一步助力我国航空航天结构实现高可靠性与极致轻量化设计.

基于最大均值差异的卷积神经网络故障诊断模型

针对工程场景中轴承故障数据采集困难,小样本下轴承故障诊断准确率较低且稳定性不高的问题,提出了一种小样本下滚动轴承故障的诊断方法,即基于最大均值差异(MMD)的卷积神经网络(CNN)诊断模型(方法)。首先,根据轴承故障机理,获取了滚动轴承故障的仿真信号,基于生成式对抗网络构建了仿真信号与少量真实样本间的对抗训练模型,得到了伪域样本,并将其扩充为训练数据集;其次,以交叉熵损失和最大均值差异(MMD)为卷积神经网络(CNN)的优化准则,引入了缩放因子,对网络进行了动态优化,根据测试结果选取缩放因子为0.05作为最优网络结构参数,构建了故障诊断的训练模型;最后,将结构均为1024个数据点的伪域样本和真实样本共同构成模型的训练集,对其进行了归一化处理,然后将其输入到构建的网络模型中,并以MMD作为约束,进行了卷积、池化操作,以实现特征提取的目的,经反向传播对模型进行了优化,实现了诊断模型参数的迭代更新目标。研究结果表明:基于MMD的CNN诊断模型(方法)对小样本下轴承的故障诊断识别精度有明显的改善,当样本数仅为16时,识别率可达95%以上,证明该方法在小样本下的轴承故障诊断中依然能获得较高的故障识别率。

基于少量标注样本的茶芽目标检测YSVD-Tea算法

构建大规模茶芽目标检测数据集是一项耗时且繁琐的任务,为了降低数据集构建成本,探索少量标注样本的算法尤为必要。本文提出了YSVD-Tea(YOLO singular value decomposition for tea bud detection)算法,通过将预训练模型中的基础卷积替换为3个连续的矩阵结构,实现了对YOLOX算法结构的重构。通过维度变化和奇异值分解操作,将预训练权重转换为与重构算法结构相对应的权重,从而将需要进行迁移学习的权重和需要保留的权重分离开,实现保留预训练模型先验信息的目的。在3种不同数量的数据集上分别进行了训练和验证。在最小数量的1/3数据集上,YSVD-Tea算法相较于改进前的YOLOX算法,mAP提高20.3个百分点。对比测试集与训练集的性能指标,YSVD-Tea算法在测试集与训练集的mAP差距仅为21.9%,明显小于YOLOX的40.6%和Faster R-CNN的55.4%。在数量最大的数据集上,YOLOX算法精确率、召回率、F1值、mAP分别为86.4%、87.0%、86.7%和88.3%,相较于对比算法均最高。YSVD-Tea在保证良好性能的同时,能够更好地适应少量标注样本的茶芽目标检测任务。

小样本下竞争风险限制平均损失时间的转换法研究

目的当竞争风险存在时,基于限制平均损失时间(restricted mean time lost,RMTL)的方法具有较少的模型假设条件和更直观的解释性。组间效应量为RMTL差值(RMTL difference,RMTLd),对应假设检验基于大样本下构建,而在小样本假设下的表现效果未知。方法本文探讨RMTLd在小样本下的表现,并发展了几种RMTL的变量转换法以提高此时的统计性能,且通过Monte Carlo模拟评价它们在不同情形下的Ⅰ类错误和检验效能。结果在小样本下,RMTLd检验原方法存在Ⅰ类错误膨胀的现象,而四种转换法之一的逻辑转换法能够保持较好的统计性能。结论在分析小样本竞争风险数据时,推荐使用RMTL的逻辑转换进行统计分析。

互耦条件下基于稀疏重构的MIMO雷达角度估计

为了降低阵列互耦对多输入多输出(MIMO)雷达波达角度(DOA)估计性能的影响,实现少量快拍条件下的目标角度估计,该文提出了基于迭代最小化稀疏学习(SLIM)算法的互耦校正和目标角度估计算法。所提算法利用目标回波信号的空域稀疏性,通过迭代优化算法估计了MIMO雷达发射和接收阵列的阵元互耦系数,以及目标稀疏空间谱。该算法无需设置超参数,且具有良好的收敛特性。仿真结果表明,当MIMO雷达发射和接收阵列存在互耦时,如果目标角度间隔较小,所提算法能够在较高信噪比条件下基于少量快拍高精度地估计目标角度;如果目标角度间隔较大,则在较低信噪比和少量快拍条件下仍有较高的角度估计精度。

基于S-LSSF的小样本滚动轴承故障诊断研究

文中针对滚动轴承故障诊断中滚动轴承故障样本不足的问题,提出基于S-LSSF的滚动轴承故障诊断模型,将Sty-leGan2-ada运用在轴承故障诊断领域。首先利用连续小波变换将时域振动信号转化为时频图像输入StyleGan2-ada生成对应的样本,然后将原始样本和生成样本合并输入改进的ShuffleNetV2模型。在反向传播过程中引入LabelSoomthloss损失函数,降低错误标签对模型诊断性能的影响,进一步抑制过拟合在下采样单元引入LeakyReLU函数解决梯度消失的问题。实验结果表明:S-LSSF模型与原模型相比诊断准确率提高了1.9%,并且平均用时缩短了5 s。与原始样本相比,使用生成样本训练模型后其准确率、精确率、召回率和F1分数分别提高了3.58%、5.71%、6.15%和6.06%,验证了S-LSSF模型在小样本条件下轴承故障诊断的可行性和泛化性。

贝叶斯网在小样本认知诊断中的应用

认知诊断的一个理想应用场景是在小样本情境的课堂测试中提供学生的诊断信息,进而促进补救教学;当前多数的认知诊断模型需较大的样本量进行参数估计,并且有些参数估计方法存在计算效率问题不能提供及时的诊断反馈。基于贝叶斯网的认知诊断方法可以实现小样本情况下诊断分类,并且能够提供及时的诊断反馈,这对于推进认知诊断在实践中的应用提供了可能。研究尝试使用贝叶斯网络方法进行小样本认知诊断分类,模拟研究表明:贝叶斯网络方法的诊断分类性能优于同样适用于小样本的海明距离法。

试样支座垫片对小尺寸试样冲击试验结果的影响

在室温下对Q235B钢板进行了3种不同厚度试样的冲击试验,研究了增加垫片对小尺寸试样冲击试验结果的影响。结果表明:对于冲击吸收能量大于60 J,且厚度为7.5,5.0 mm的小尺寸试样,是否增加垫片对试样的冲击试验结果影响不大;对于厚度为2.5 mm的小尺寸试样,增加垫片可以使试样位于摆锤中心位置,以避免额外的能量吸收;是否增加垫片对不同厚度小尺寸试样的侧膨胀值、断口显微组织以及宏观形貌影响不大。

采用虚拟训练样本优化正则化判别分析

在模式特征子空间中选取一组标准正交向量,使用这组向量可以生成大量的虚拟训练样本,从而实现对协方差矩阵的优化.在ORL人脸库上的实验表明,优化后协方差矩阵的特征值均显著变大,使该矩阵的逆阵稳定性得到了提高.利用优化的协方差矩阵对正则化判别分析方法进行优化,其模式分类正确率有显著提高.