共查询到16条相似文献,搜索用时 62 毫秒
1.
2.
由于存在干扰,飞参系统记录的发动机参数中,经常会有不少间断点和奇异值.为了利用数据对发动机性能趋势进行预测,必须对数据进行预处理.发动机作为一个系统,其各主要输入和输出参数之间必然存在着一定的函数关系.本文研究了利用RBF神经网络和参数之间的关系对数据进行预处理,得到了较为正常的数据,结果表明该方法是有效的. 相似文献
3.
4.
5.
6.
针对飞参记录仪工作中存在数据缺损的现象,提出一种基于复合神经网络(CNN)对缺失数据估计的方法。仿真结果表明,运用该方法进行数据处理,可以有效地解决飞参缺损数据的问题,并且能够提高飞参数据的准确性和可信度。 相似文献
7.
8.
9.
袁群义 《中国新技术新产品》2022,(19):52-54
为提升电力通信网络异常数据检测结果准确率,该文引入了物联网技术,进行了对基于物联网技术的电力通信网络异常数据检测方法的设计研究。在电力通信网络跨区域环境中,建立电力通信网络信道模型;通过小波包分解的方式提取电力通信网络数据特征集;引入物联网技术,实现对异常数据的识别以及对离群异常数据的检测。对比试验证明,新的检测方法可有效提高检测结果的精度,检测结果能更准确地描述电力通信网络中数据运行的实际情况。 相似文献
10.
郑仁丹 《中国新技术新产品》2019,(12)
随着人民群众和环保部门对环境质量的要求和管理力度不断加强,安装污染源自动监控设备的企业也不断增多,数据量也逐渐增加,成效也越来越明显。然而在传输和分析过程中,因受到传输环境及仪器设备运行状态等因素影响,监控数据可能出现偏差。该文针对出现异常数据的情况,结合其检测和判别方法进行深入分析,并在此基础上给出提升准确性的建议和按照相关文件要求对异常数据的处置。 相似文献
11.
12.
With the development of science and technology, the status of the water
environment has received more and more attention. In this paper, we propose a deep
learning model, named a Joint Auto-Encoder network, to solve the problem of outlier
detection in water supply data. The Joint Auto-Encoder network first expands the size of
training data and extracts the useful features from the input data, and then reconstructs
the input data effectively into an output. The outliers are detected based on the network’s
reconstruction errors, with a larger reconstruction error indicating a higher rate to be an
outlier. For water supply data, there are mainly two types of outliers: outliers with large
values and those with values closed to zero. We set two separate thresholds, τ1 and τ2,
for the reconstruction errors to detect the two types of outliers respectively. The data
samples with reconstruction errors exceeding the thresholds are voted to be outliers. The
two thresholds can be calculated by the classification confusion matrix and the receiver
operating characteristic (ROC) curve. We have also performed comparisons between the
Joint Auto-Encoder and the vanilla Auto-Encoder in this paper on both the synthesis data
set and the MNIST data set. As a result, our model has proved to outperform the vanilla
Auto-Encoder and some other outlier detection approaches with the recall rate of 98.94
percent in water supply data. 相似文献
13.
High-dimensional data monitoring and diagnosis has recently attracted increasing attention among researchers as well as practitioners. However, existing process monitoring methods fail to fully use the information of high-dimensional data streams due to their complex characteristics including the large dimensionality, spatio-temporal correlation structure, and nonstationarity. In this article, we propose a novel process monitoring methodology for high-dimensional data streams including profiles and images that can effectively address foregoing challenges. We introduce spatio-temporal smooth sparse decomposition (ST-SSD), which serves as a dimension reduction and denoising technique by decomposing the original tensor into the functional mean, sparse anomalies, and random noises. ST-SSD is followed by a sequential likelihood ratio test on extracted anomalies for process monitoring. To enable real-time implementation of the proposed methodology, recursive estimation procedures for ST-SSD are developed. ST-SSD also provides useful diagnostics information about the location of change in the functional mean. The proposed methodology is validated through various simulations and real case studies. Supplementary materials for this article are available online. 相似文献
14.
基于稀疏表示的人脸识别算法(SRC)识别率相当高,但是当使用l1范数求最优的稀疏表示时,大大增加了算法的计算复杂度,矩阵随着维度的增加,计算时间呈几何级别上升,该文提出利用拉格朗日算法求解矩阵的逆的推导思路,用一种简化的伪逆求解方法来代替l1范数的计算,可将运算量较高的矩阵求逆运算转变为轻量级向量矩阵运算,基于AR人脸库的实验证明,维度高的时候识别率高达97%,同时,计算复杂度和开销比SRC算法大幅度降低95%。 相似文献
15.
光滑逼近超完备稀疏表示的图像超分辨率重构 总被引:1,自引:0,他引:1
为改善单帧降质图像的分辨率水平,提出了一种新的基于稀疏表示的学习法超分辨率图像重构方法。针对信号在既定的欠定超完备字典下的非稀疏性问题,采用光滑的递减函数逼近L0范数以避免对稀疏度先验的依赖,从而实现待重构图像块的有效稀疏表示,同时通过梯度下降的迭代优化获得稳定的收敛解。与双立方插值相比,图像的三倍超分辨实验显示,图像峰值信噪比(PSNR)提高2dB,框架相似性(SSIM)改善0.04,重构图像剔除了更多的模糊退化及边缘伪迹。该方法适于单帧降质图像的超分辨率增强。 相似文献
16.
目的 提升自动化产线上工件表面微小缺陷的检测精度和检测速度。方法 首先,在预处理阶段提出采用CutMix的数据增强方法,增加训练样本的多样性,提高模型的鲁棒性和泛化能力,避免训练模型产生过拟合;使用K–means++聚类算法生成边界候选框,以适应不同尺寸的缺陷,并较早地筛选出更精细的特征。其次,借助CSP Darknet53网络及SPP模块提取输入原始图像的特征,通过训练获得针对工件表面质量的在线检测模型,提升YOLOV4缺陷位置检测及识别的精度。结果 实验结果表明,文中所提出的基于YOLOV4的工件表面质量在线监测方法的预测精度达到97.5%,检测速度达到32.8帧/s,均优于同类的深度学习算法。以贵州某航空工业产品的自动化产线作为实验平台验证了所提方法的可行性和有效性。结论 该方法具备结构简单清晰、自适应性强等优点,检测精度和速度均满足工业场景需求,可以将其用于产品表面质量的在线检测。 相似文献