对设备进行故障诊断的主要方法就是测量故障
设备的振动或噪声, 并对其进行分析, 从而找出故障原因。然而振动或噪声信号中除了对分析故障有用的信息外, 还有大量的噪声成分。只有有效地滤除噪声, 才能获得有用的信息, 从而得到可靠的分析结论。传统的滤噪方法是将被噪声污染的信号通过一个滤波器, 滤掉噪声频率成分。但对于短时瞬态信号、非平稳信号、含宽带噪声的信号, 采用传统处理方法有着明显的局限性。小波变换为信号去噪提供了一种有效的方法, 小波阈值去噪具有传统方法不可比拟的优越性。但是小波分解的频域重叠性和阈值选取的不确定性, 使得小波阈值去噪法有也不能得到理想效果。
Equipment fault diagnosis method is to measure the fault
Equipment vibration or noise, and its analysis in order to identify the cause of the malfunction. Vibration or noise signals, however, in addition to the analyze fault useful information, there is a lot of noise components. Only effectively filter out the noise in order to obtain useful information, to obtain reliable conclusions. Traditional filtering method based noise pollution signal through a filter to filter out the noise frequency components. But for the short-term transient signal, non-stationary signals, including broadband noise signal, using the traditional approach has obvious limitations. The wavelet transform provides an effective method for signal de-noising, wavelet thresholding has incomparable superiority of traditional methods. Wavelet frequency domain overlap threshold uncertainty, the wavelet thresholding method can not get the desired effect. (2013-04-13, matlab, 261KB, 下载21次)
基于平移不变小波变换的多普勒速度声纳输出信号处理.针对水下航行器组合导航系统所使用的多普勒速度声纳输出信号的特点,采用了平移不变小波变换的多分辨率分析的方法,利用Daubechies小波函数,采用了半软阈值去噪的方法,能够在低信噪比的情况下准确地估计多普勒声纳的频移,从含有噪声的多普勒输出信号中提取出原始信号.通过仿真实验表明:采用4层小波分解,算法计算量减小,有效地消除多普勒噪声,从而提高水下组合导航系统的精度.
Doppler speed the sonar output signal processing based on translation invariant wavelet transform. Integrated navigation system for underwater vehicle using the Doppler-velocity sonar output signal using translation invariant wavelet transform multiresolution analysis method using Daubechies wavelet function, using a semi-soft threshold denoising method to accurately estimate the Doppler sonar frequency shift in the case of low signal-to-noise ratio output signal with noise from the Doppler extract the original signal. Simulation results show that: 4 layer wavelet decomposition algorithm to calculate the amount decreases, effectively eliminate the Doppler noise, thereby improving the accuracy of the underwater integrated navigation system. (2012-08-21, Visual C++, 318KB, 下载28次)
为了提高纹理图象分割的边缘准确性和区域一致性以及降低分割错误率, 提出了一种基于小波变换的利
用特征加权来进行纹理分割的方法. 该方法包括特征提取、预分割和后分割 3 个阶段, 其中, 特征提取在金字塔结
构小波变换的基础上进行 预分割利用均值聚类算法来对原始图象进行初步的分割 后分割则根据预分割的结果
对特征进行加权, 然后利用最小距离分类器来实现图象的最后分割. 与传统的方法相比, 该方法在分割错误率、边
缘准确性以及区域一致性等方面均有明显的改善
To imp rove the accuracy of boundary locat ions and region homogeneity as w ell as to reduce the er ro r
rate in texture image segmentat ion, a novel app roach based on w avelet2t ransfo rm and using feature w eigh t ing is
p ropo sed in th is paper . Th is new technique contains th ree consecut ive stages: feature ext ract ion, p re2segmentat ion
and po st2segmentat ion . In the feature ext ract ion stage, texture features are ext racted by using the pyram id2st ruc2
tured w avelet t ransfo rm. The o r iginal image is then segmented init ially using themeans cluster ing algo r ithm in the
p re2segmentat ion stage . A cco rding to the p re2segmentat ion results, the ext racted features are w eigh ted and the
p re2segmented image is fur ther p rocessed w ith a m inimum distance classif ier in the po st2segmentat ion stage to f i2
nally get the segmented image . A ll technical po ints are clear ly descr ibed and p resented in detail . Some segmenta2 (2012-07-20, PDF, 151KB, 下载13次)
关于二维小波变换的程序 [精华]
说明：此算法重在概念，速度并不是很快。因为FOR循环的缘故。此程序从循环矩阵的观点出发，把圆周卷积和快速幅里叶变换建立了联系。实现了分解和无失真重构。它只做了一层分解，即将256x256图形分解成为64x64的四个图形，避免了使用WKEEP()的困惑。主要思想为用小波滤波器族构造正交阵W,变换写为B=W*A*W ,反变换为：A=W *A*W,这与所有正交变换无异。W为循环正交矩阵，因此可用FFT实现快速运算，难点就在重构矩阵上。若用矩阵概念明确，一个共扼转置可以搞顶。但FFT的使用必须找到与分解序列的关系。
on Wavelet Transform procedures [best] Note : This algorithm important concept is not speed quickly. Because FOR cycle nowadays. This program cycle from the point of view of Matrix, circular convolution and fast Fourier transform is established links. To achieve the decomposition and reconstruction without distortion. It only had one decomposition, 256x256 graphics will be 64x64 decomposition of the four graphics, avoiding the use of WKEEP () confusion. The main idea of using wavelet filter generator orthogonal array W, write to transform B = W* A* W, anti-Transform : A = W* A* W, which is orthogonal transformation all the same. W cycle orthogonal matrix, can be used to achieve rapid FFT computation, on the difficult reconstruction matrix. If a clear matrix concept, a home to a total o (2005-09-22, matlab, 3KB, 下载142次)