Results 31 to 40 of about 2,185 (152)

Named entity recognition based on equipment and fault field of CNC machine tools [PDF]

open access: yes, 2020
With the advent of intelligent manufacturing and big data, the Made in China 2025 Initiative and Industry 4.0 have been paying increasing attention to automation and intelligent industrial equipment. In the background of the present times, the complexity
Huan WANG   +4 more
core   +1 more source

Application of three-order diagonal cumulants in fault diagnosis [PDF]

open access: yes, 2012
三阶累量能有效去除高斯噪声,而且其对角累量能有效保持信号特征,由其产生的1(1/2)维谱可以显示信号的二次相位耦合信息。实验中通过计算故障信号和正常信号的三阶对角累量信息,然后利用这些信息进行具体的故障判别。实验结果取得了令人满意的效果。Three-order cumulant can eliminate the Gaussian background noise and keep signals features effectively.The 1(1/2) dimensional spectrum ...
吴文兵, 黄宜坚
core  

Renewable Energy Distribution Network Overcurrent Protection Based on Positive-Sequence Sudden-Change Component Locus Identification [PDF]

open access: yes
ObjectivesWith the widespread integration of renewable energy, the uncertainty of power flow in distribution networks with neutral points grounded through small resistors has made the setting of traditional three-stage current protection increasingly ...
LI Shuyi   +6 more
core   +1 more source

基于核Fisher判别分析技术的电力变压器DGA故障诊断模型研究

open access: yesGaoya dianqi, 2007
鉴于核Fisher判别分析技术(KFDA)在模式识别问题中表现出的良好性能,提出了基于KFDA的变压器故障诊断模型,该模型首先提出了区分放电及过热两大类故障的特征量,并用KFDA分类器来识别类内故障的具体类别。采用基于网格搜索的交叉验证法来选择模型参数,避免了参数选择的盲目性和随意性。实例分析表明,该模型具有训练时间短、不存在局部极小等优点,与IEC三比值及改良电协研法相比,具有更好的故障识别效果。
吴晓辉   +4 more
doaj  

基于多尺度广义S变换和深度残差网络的雷击跳闸故障类型识别方法

open access: yesDianci bileiqi, 2021
为提高雷击跳闸类型判断的效率和智能化水平,提出一种基于多尺度广义S变换和深度残差网络的雷击跳闸故障识别方法。首先采用广义S变换对雷击跳闸暂态信号进行时频变换,通过改变广义S变换中的调节因子λ获得多尺度时频分布图像,然后将变换得到的多尺度时频分布特征图作为特征图像输入到深度残差网络中,进行特征提取和识别模型建立,最终识别出雷击跳闸故障类型。以124个输电线路实测雷击跳闸暂态电压信号样本作为训练集和测试集输入到识别模型中,并与其他方法进行对比,验证提出方法的有效性。结果表明 ...
刘宇舜   +6 more
doaj  

Application of Complex Three-Order Cumulants to Fault Diagnosis of Hydraulic Valve [PDF]

open access: yes, 2013
为了提高故障诊断正确率,提出了一种基于复数三阶累积量的机械故障诊断方法.三阶累积量的不同定义的复数形式包含了信号间不同的耦合信息,利用这些信息进行了故障诊断.在溢流阀故障诊断实验中,利用这些不同的耦合信息,通过二维小波在不同的方向上对故障信号和正常信号进行特征提取,然后将这些特征值输入支持向量机进行故障判别.实验结果表明,上述方法可以提高故障诊断正确率.同时还对实数三阶累积量也进行了相同的实验,这些实验所取得的诊断效果证明了采用本文方法的有效性.In order to improve the ...
吴文兵, 周桃庚, 杨淑群
core  

Fault diagnosis of ship diesel power distribution system based on WOA-RF algorithm [PDF]

open access: yes
ObjectiveThe marine diesel generator (DG) power distribution system is crucial for ship navigation. However, due to the harsh marine environment, frequent failures occur. Therefore, a fault diagnosis method based on whale optimization algorithm-optimized
Daojie RUAN   +5 more
core   +1 more source

Fault detection and diagnosis method for heterogeneous wireless network based on GAN [PDF]

open access: yes, 2020
Aiming at the problem that in the process of network fault detection and diagnosis,how to train the precise fault diagnosis and detection model based on small data volume,a fault diagnosis and detection algorithm based on generative adversarial networks (
Peipei ZHANG, Xiaorong ZHU
core   +1 more source

Application of complex cumulants slices in mechanical fault diagnosis [PDF]

open access: yes, 2013
复数三阶累量具有不同的定义形式,定义形式不同,其耦合性质也不相同,则由其产生的复数累量切片也包含了信号间不同的耦合信息,实验中利用这些不同的定义方式,对特定的故障信号和正常信号同时采用相同的耦合方式进行故障判别。同时定义了复数三阶累量切片谱,通过切片谱对正常信号和故障信号的耦合特征进行了分析。实验结果表明,随着耦合方式的不同,同一故障的诊断正确率也不相同,从而为特定的故障判别提供了一种可供选择的方法。Complex third-order cumulant has different ...
吴文兵, 黄宜坚
core  

基于MWPE和DBO‑SVM的齿轮故障诊断

open access: yesZhendong Ceshi yu Zhenduan
针对齿轮故障领域识别率低和识别时间长的问题,基于多尺度加权排列熵(multiscale weighted permutation entropy,简称MWPE)、蜣螂算法(dung beetle optimizer,简称DBO)与支持向量机(support vector machine,简称SVM)的原理,提出基于MWPE和DBO结合SVM的故障识别方法。首先,由于MWPE的嵌入维数难以确定且对结果影响较大,通过MWPE熵值分析引入变异系数(coefficient of variation,简称CV ...
doaj   +1 more source

Home - About - Disclaimer - Privacy