Feature extraction is an important part of signal processing,which is significant for signal detection,classification,and recognition.The nonlinear dynamic analysis method can extract the nonlinear characteristics of ...Feature extraction is an important part of signal processing,which is significant for signal detection,classification,and recognition.The nonlinear dynamic analysis method can extract the nonlinear characteristics of signals and is widely used in different fields.Reverse dispersion entropy(RDE)proposed by us recently,as a nonlinear dynamic analysis method,has the advantages of fast computing speed and strong anti-noise ability,which is more suitable for measuring the complexity of signal than traditional permutation entropy(PE)and dispersion entropy(DE).Empirical wavelet transform(EWT),based on the theory of wavelet analysis,can decompose a complex non-stationary signal into a number of empirical wavelet functions(EWFs)with compact support set spectrum,which has better decomposition performance than empirical mode decomposition(EMD)and its improved algorithms.Considering the advantages of RDE and EWT,on the one hand,we introduce EWT into the field of underwater acoustic signal processing and fault diagnosis to improve the signal decomposition accuracy;on the other hand,we use RDE as the features of EWFs to improve the signal separability and stability.Finally,we propose a novel signal feature extraction technology based on EWT and RDE in this paper.Experimental results show that the proposed feature extraction technology can effectively extract the complexity features of actual signals.Moreover,it also has higher distinguishing ability for different types of signals than five latest feature extraction technologies.展开更多
The non-linear dynamic theory brought a new method for recognizing and predicting complex non-linear dynamic behaviors. The non-linear behavior of vibration signals can be described by using fractal dimension quantita...The non-linear dynamic theory brought a new method for recognizing and predicting complex non-linear dynamic behaviors. The non-linear behavior of vibration signals can be described by using fractal dimension quantitatively. In this paper, a fractal dimension calculation method for discrete signals in the fractal theory was applied to extract the fractal dimension feature vectors and classified various fault types. Based on the wavelet packet transform, the energy feature vectors were extracted after the vibration signal was decomposed and reconstructed. Then, a wavelet neural network was used to recognize the mechanical faults. Finally, the fault diagnosis for a wind power system was taken as an example to show the method's feasibility.展开更多
A novel technique for the video watermarking based on the discrete wavelet transform (DWT) is present. The intra frames of video are transformed to three gray image firstly, and then the 2th-level discrete wavelet dec...A novel technique for the video watermarking based on the discrete wavelet transform (DWT) is present. The intra frames of video are transformed to three gray image firstly, and then the 2th-level discrete wavelet decomposition of the gray images is computed, with which the watermark W is embedded simultaneously into and invert wavelet transform is done to obtain the gray images which contain the secret information. Change the intra frames of video based on the three gray images to make the intra frame contain the secret information. While extracting the secret information, the intra frames are transformed to three gray image, 2th-level discrete wavelet transform is done to the gray images, and the watermark W’ is distilled from the wavelet coefficients of the three gray images. The test results show the superior performance of the technique and potential for the watermarking of video.展开更多
针对水电机组振动信号故障特征提取难,提出一种融合小波变换(Wavelet Transform,WT)和奇异值分解(Singular Value Decomposition,SVD)相结合的故障特征提取方法。首先,通过小波阈值降噪消除强噪声对模型特征提取的干扰,再利用小波变换...针对水电机组振动信号故障特征提取难,提出一种融合小波变换(Wavelet Transform,WT)和奇异值分解(Singular Value Decomposition,SVD)相结合的故障特征提取方法。首先,通过小波阈值降噪消除强噪声对模型特征提取的干扰,再利用小波变换将降噪信号分解成不同频率的模态子序列,应用SVD理论提起子序列的SVD值作为特征,最终将特征输入RF模型中实现水电机组故障的快速识别与诊断。通过在公开数据集和真实机组案例中应用,验证了对水电机组故障诊断的高效性。展开更多
基金the supported by National Natural Science Foundation of China(No.61871318 and 11574250)Scientific Research Plan Projects of Shaanxi Education Department(No.19JK0568).
文摘Feature extraction is an important part of signal processing,which is significant for signal detection,classification,and recognition.The nonlinear dynamic analysis method can extract the nonlinear characteristics of signals and is widely used in different fields.Reverse dispersion entropy(RDE)proposed by us recently,as a nonlinear dynamic analysis method,has the advantages of fast computing speed and strong anti-noise ability,which is more suitable for measuring the complexity of signal than traditional permutation entropy(PE)and dispersion entropy(DE).Empirical wavelet transform(EWT),based on the theory of wavelet analysis,can decompose a complex non-stationary signal into a number of empirical wavelet functions(EWFs)with compact support set spectrum,which has better decomposition performance than empirical mode decomposition(EMD)and its improved algorithms.Considering the advantages of RDE and EWT,on the one hand,we introduce EWT into the field of underwater acoustic signal processing and fault diagnosis to improve the signal decomposition accuracy;on the other hand,we use RDE as the features of EWFs to improve the signal separability and stability.Finally,we propose a novel signal feature extraction technology based on EWT and RDE in this paper.Experimental results show that the proposed feature extraction technology can effectively extract the complexity features of actual signals.Moreover,it also has higher distinguishing ability for different types of signals than five latest feature extraction technologies.
基金Sponsored by the National Science Foundation (61004118)the Natural Science Foundation Project of CQ CSTC (2011A70007)+1 种基金the Science and Technology Research Project of Chongqing Municipal Education Commission (KJ120422)the Science Foundation Project of Chongqing Jiaotong University Open Research Fund of Key Laboratory of Bridge Structural Engineering of Chongqing Jiaotong University (CQSLBF-Y11-5)
文摘The non-linear dynamic theory brought a new method for recognizing and predicting complex non-linear dynamic behaviors. The non-linear behavior of vibration signals can be described by using fractal dimension quantitatively. In this paper, a fractal dimension calculation method for discrete signals in the fractal theory was applied to extract the fractal dimension feature vectors and classified various fault types. Based on the wavelet packet transform, the energy feature vectors were extracted after the vibration signal was decomposed and reconstructed. Then, a wavelet neural network was used to recognize the mechanical faults. Finally, the fault diagnosis for a wind power system was taken as an example to show the method's feasibility.
基金Supported by the Science and Technology Plan Foundation of GuangDong (No. 2004B16001006) and the Science and Technology Plan Foundation of Dongguan (No. 2004D1015)
文摘A novel technique for the video watermarking based on the discrete wavelet transform (DWT) is present. The intra frames of video are transformed to three gray image firstly, and then the 2th-level discrete wavelet decomposition of the gray images is computed, with which the watermark W is embedded simultaneously into and invert wavelet transform is done to obtain the gray images which contain the secret information. Change the intra frames of video based on the three gray images to make the intra frame contain the secret information. While extracting the secret information, the intra frames are transformed to three gray image, 2th-level discrete wavelet transform is done to the gray images, and the watermark W’ is distilled from the wavelet coefficients of the three gray images. The test results show the superior performance of the technique and potential for the watermarking of video.
文摘针对水电机组振动信号故障特征提取难,提出一种融合小波变换(Wavelet Transform,WT)和奇异值分解(Singular Value Decomposition,SVD)相结合的故障特征提取方法。首先,通过小波阈值降噪消除强噪声对模型特征提取的干扰,再利用小波变换将降噪信号分解成不同频率的模态子序列,应用SVD理论提起子序列的SVD值作为特征,最终将特征输入RF模型中实现水电机组故障的快速识别与诊断。通过在公开数据集和真实机组案例中应用,验证了对水电机组故障诊断的高效性。
