搜索资源列表
PCA-KPCA
- 主成分分析(Principle Component Analysis, PCA)是最为常用的特征提取方法，被广泛应用到各领域，如图像处理、综合评价、语音识别、故障诊断等。-Principal component analysis (Principle Component Analysis, PCA) is the most commonly used feature extraction methods are widely applied to various fields, such as
tiqutezheng
- 从已经出现故障的信号中，提取能够反映该信号故障特征的值，以后就能根据数值直接判断别的信号有没有出现该故障，更加直观-Signals the fault has appeared in the fault feature extraction and can reflect the value of signal, after can according to numerical directly to judge the other signals have appeared the faul
matalab-多重分形谱算法+盒子维数的计算
- 基于matalab软件，对多重分形谱算法和盒子维数的计算算法进行编写和改进，可以用于机械设备的故障诊断和特征提取，对利用分型学的基本理论进行故障诊断具有极高的参考价值。
Desktop
- 在齿轮箱故障诊断中，需要对故障信号进行特征提取，本程序是齿轮箱特征提取源代码。-Gearbox fault diagnosis, the need for fault signal feature extraction, the procedure is to extract the source code gearbox features.
Hilbert-Huang-Transform
- 希尔伯特黄变换，主要用于测量汽车发动机故障，提取故障特征。-Hilbert Huang Transform, mainly used to measure automobile engine fault, fault feature extraction.
tezhengtiqu
- 用matlab程序对正常和故障的风电机组振动信号进行特征提取，提取时域的16个特征值-Using matlab program for normal and faulty wind turbine vibration signal feature extraction, extraction time domain 16 eigenvalues
emd
- 可以有效方便地对原始数据进行自适应分解，广泛用于故障诊断和模式识别等方面的特征提取。-Can be effectively and easily decompose the raw data adaptively, widely used in troubleshooting and other aspects of the pattern recognition feature extraction.
lmd_outer
- 轴承外圈12K实际信号LMD分解程序，信号包络频谱，能明显提取故障特征-LMD bearing outer ring 12K actual signal decomposition process, the signal envelope spectrum, can significantly fault features
time-frequency-feature
- 此代码用于故障诊断特征提取，所提取特征包括传统时、频域特征和时频特征三部分，数据为轴承数据-This code is used when troubleshooting feature extraction, the extracted features, including traditional, frequency domain and time-frequency characteristics of three parts, the data is bearing data
zhouchen
- 小波阈值自动选取方案去噪，并用HHT对去噪后的轴承信号进行处理，提取故障特征。-Wavelet threshold de-noising program automatically chooses, for bearing with HHT denoised signal processing, fault features.
BPQPSOBP
- 主要针对级联式变频器故障特征比较难提取，运用小波分析提取故障特征，然后用粒子群优化神经网络进行故障诊断-Mainly for the cascading inverter and difficult to extract the fault features, using wavelet analysis to extract the fault feature, and then use particle swarm optimization neural network for fault
shiyuzhibiao14
- 故障诊断14个时域特征提取代码，包括均值，均方根值，10个有量纲量，4个无量纲量-matlab codes of feature extract
HHT
- 把HHT和神经网络结合起来，识别出是否故障。对于HHT变换，这里用到的是它的IMF分解，然后用能量理论来判别哪些模组是虚假分量，哪些是是真实分量。对于EMD分解后的谱进行特征提取 ，利用的理论基础就是模糊熵。计算出真实 分量的模糊熵，作为输入层；输出层为两个神经元，为0（故障 ）1（正常 （正常 ）判别该信号是否出现故障。-The combination of HHT and neural network to identify whether the fault. For the HHT tr
waveletpacketdecomp
- 一维信号特征提取参考程序，正常信号和故障信号特征的提取，开发环境为MATLAB。是使用小波分解处理信号的参考，使用了小波包三层分解。-One dimensional signal feature extraction reference program, normal signals and fault feature extraction, the development environment of MATLAB.Is the use of wavelet decomposition pro
cluster_VMDaFCM_casedat
- 为了精准、稳定地提取滚动轴承故障特征，提出了基于变分模态分解和奇异值分解的特征提取方法，采用标准模糊C均值聚类(fuzzy C means clustering, FCM)进行故障识 别。对同一负荷下的已知故障信号进行变分模态分解，利用 奇异值分解技术进一步提取各模态特征，通过FCM形成标准聚类中心，采用海明贴近度对测试样本进行分类，并通过计算分类系数和“卜均模糊嫡对分类性能进行评价，将该方法 应用于滚动轴承变负荷故障诊断。通过与基于经验模态分解的特征提取方法对比，该方法对标准FCM
vmd
- 针对实际中工况复杂难以提取齿轮故障特征频率的问题，提出一种变分模态分解-(variational mode decomposition, VMD)
shiyutezheng
- 振动信号时域特征提取，用于故障诊断，包括十余种特征提取算法-Time domain features vibration signals for fault diagnosis, including more than ten kinds of feature extraction algorithm
pinyutezheng
- 一维信号频域特征提取，可用于轴承故障诊断和趋势预测-Wherein the one-dimensional frequency domain signal extraction, can be used to predict bearing Fault Diagnosis and
RSSD
- 该代码针对滚动轴承故障振动信号呈现出非线性、非平稳性及噪声背景较强等特点，为了有效提取故障特征，使用的一种共振稀疏分解（Resonance-based sparse signal decomposition，RSSD）与小波变换相结合的振动信号特征提取技术的相关仿真实验程序和轴承数据分解程序。其中，共振稀疏分解是基于品质因子可调小波变换与形态分量分析的一种新的信号分解方法，与常规的基于频带划分的信号分解方法不同，它依据信号各分量的振荡形态不同对信号进行分解。 同时还提供了可调谐 Q 因子小波
基于小波包提取轴承故障
- 基于小波包变换对信号进行分解，提取机器轴承故障的特征信号进行损伤识别，(The signal is decomposed based on wavelet packet transform, and the characteristic signals of machine bearing faults are extracted to identify the damage,)