Papers by Keyword: Wavelet Packet

Abstract: The friction welded joints made by GH4169 heat metal alloys are detected by U1traPAC system of the ultrasonic wave explore instrument. Aimed at the blemish signal characteristics, this article introduce Support Vector Machine (SVM) theory, which is based on statistical theory and structural risk minimization principle, to carry out multi-classification study of the detection signal. We decompose de-noising signals with wavelet packet transform, and extract energy eigenvalues according to "energy- defects". In accordance with designed "1-to-v" SVMs scheme, we respectively input normalized eigenvector to the SVM model to obtain the Forecast data. It is verificated that the limited existing data and information is well used by SVM and the signal is accurately been classificated. All of these verify that SVM has a strong generalization ability.

Abstract: The growth process of diamond single crystals under HPHT was tested with acoustic emission (AE) technology, and the AE signals were analyzed with fast Fourier transform and wavelet packet analysis. The results show that there are many new frequency peaks in the frequency range that is higher than 80 kHz, and comparative analysis shows that these new frequency peaks are caused from the growth process of diamond crystals. The value of the signal energy and peak in different frequency bands are compared along with the diamond growth process. And it has reflected the dynamic changes in the time domain of the acoustic emission signals stimulated by the different acoustic emission sources. It also shows that the frequency of acoustic emission signals could be used as the effective means to distinguish the different acoustic emission sources in the diamond growth process.

Abstract: In this paper, a new method using wavelet packet energy spectrum to identify transformer inrush and internal fault current was proposed. Wavelet packet transform respectively decomposed inrush and fault current, then calculated the energy of each frequency band of decomposed signal. Finally, the conclusion showed that the energy of internal fault in high frequency band is much less than that of inrush. The difference was quantified and it could be observed intuitively. Through extensive simulations, this paper proves that the method in terms of identifying transformer inrush is accurate and effective.

Abstract: In this paper, the author introduces the principles of wavelet packet denoising, conducts a simulated analysis on the improved performance of wavelet packet denoising and develops the source Matlab program. In addition, the measured acoustic signals of seafloor sediments are denoised using wavelet packet. It is feasible to apply the wavelet packet denoising technique in a wide range of engineering testing fields involving denoising operation.

Abstract: Using wavelet packet neural network method which is consist of wavelet packet and BP neural network to diagnose large rotors by vibration signal .Firstly , according to the spectrum characteristic of large rotors’ common vibration fault ,using the improved wavelet packet method to compute the energy of the spectrum that can reflect the fault information .And then make the feature vector as the input to establish a model of improved wavelet packet neural network for fault diagnosis . Collect the data of five working conditions from the test bench , establish a improved wavelet packet neural network model, and then use the model to diagnose fault. The experimental results show that this method improves the accuracy obviously and calculate fast.

Abstract: Rotation machine plays an important role in the production of electric power, chemical industry etc... In the methods of fault diagnosis, the selection of the Pc and Pm of common genetic algorithm will influence its convergence and is easy to be trapped into the local optimum to propose an adaptive genetic algorithm of the fault diagnosis; and in the implementation of system function, it takes the S3C2410 chip as the core of the microprocessor and uses the embedded Linux as the operating system as the software development platform. In this paper ,it introduces the design of the various parts of the system hardware in details, achieves the Boot Loader through combination of the hardware platform and successfully transplants the Linux operating system and builds a root file system, with the combination of the Linux operating system platform, it achieves the LCD frame buffer display device frame buffer, touchscreen A/D converter and development of Ethernet driver program, and the develops the data acquisition, wavelet packet analysis and Ethernet driver program etc. based on the system functions.

Abstract: In order to improve the correct recognition rate of EEG(Electroencephalogram,EEG) signals to meet the needs of Brain-Computer Interface system,this paper put forward a new method of signal recognition which combines wavelet packet decomposition and LVQ neural network.First,using the method of wavelet packet to analyze the signal,and then extract the specific frequency band’s energy of wavelet packet as characteristics.Then using the LVQ neural network model to study the distinguishing between the two EEG datas of Motor Imagery.The simulation experiment uses Matlab software to design LVQ neural network model to judge the two kinds of Motor Imagery task.In the process of judgment,respecti-vely to classify the data by using BP neural network and LVQ neural network.Experimental results show that the LVQ neural network can have a higher correct accuracy to recognize the motor imaginary task than BP neural.

Abstract: When bearing rotates, it comes with elastic hydrodynamic lubrication effect. Interaction between the effect and the bearing vibration leads to the change of lubricant film thickness, thus, contact stiffness of contact pair changes along with the rotation speed of the bearing, and then the resonance frequencies of the bearing system changes according to the rotation speed. In addition, the impact signal of varying speed bearing damage point no longer has the periodic characteristics. Based on the analysis of the bearing failure mechanism, this paper proposed a varying speed bearing vibration signal fault model, and also utilizes wavelet packet to extract the bearing fault signal by means of a variable speed rolling bearing vibration experiment table.

Abstract: Although many wavelet de-noising methods have been studied and proposed, the parameters of them are obtained by experience mostly, which makes the de-noising effect instable. To solve the issues, the solutions, such as the selection of wavelet function and threshold function, the calculation of decomposition levels, the optimal wavelet packet basis and the thresholds obtained based on QPSO, have been studied in this paper. Every parameter is obtained by calculation. This method is applied to the de-noising experiment of sine and vibration signals. Through the experimental verification, the effect of this de-noising method is obvious.

Abstract: In this paper, we propose novel sub-band spectral centroid weighted wavelet packet cepstral coefficients (W-WPCC) for noise-robust speech emotion recognition. Experimental results show that the W-WPCC feature demonstrates better noise-robustness in noisy environments.