The removal of the high-frequency motion-induced noise in helicopter-borne transient electromagnetic data based on wavelet neural network

Geophysics ◽  
2019 ◽  
Vol 84 (1) ◽  
pp. K1-K9 ◽  
Author(s):  
Xin Wu ◽  
Guoqiang Xue ◽  
Pan Xiao ◽  
Jutao Li ◽  
Lihua Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
High Frequency ◽  
Field Data ◽  
Original Data ◽  
Wavelet Neural Network ◽  
Time Frequency ◽  
Second Stage ◽  
Transient Electromagnetic ◽  
Data Segment ◽  
Academy Of Sciences

In helicopter-borne transient electromagnetic (HTEM) signal processing, removal of motion-induced noise is one of the most important steps. A special type of short-term noise, which could be classified as high-frequency motion-induced noise (HFM noise) based on its cause and time-frequency features, was observed in the field data of the Chinese Academy of Sciences-HTEM system. Because the HFM noise is an in-band noise for the HTEM response, it usually remains after the normal denoising procedure developed for the conventional motion-induced noise. To solve this problem, we have developed a three-stage workflow to remove the HFM noise using the wavelet neural network (WNN). In the first stage, the WNN training is performed, and the data segment in which the HFM noise is dominant is selected as the sample set. In the second stage, the HFM noise corresponding to the data segment in which the earth’s response coexisted with the HFM noise is predicted using the well-trained WNN. In the last stage, the predicted HFM noise is removed from the corresponding original data. As an example, we applied our workflow in the field data observed in Inner Mongolia, the HFM noise is removed effectively, and the results provide a strong data foundation for the subsequent processing procedures.

The Coal Mine Flooding Emergency Ability Evaluation Based on GA-WNN

2012 ◽  
Vol 452-453 ◽  
pp. 782-788
Author(s):  
Jin Feng Wang ◽  
Li Jie Feng ◽  
Zhao Hui Li
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Coal Mine ◽  
Evaluation Model ◽  
Wavelet Neural Network ◽  
Time Frequency ◽  
Model Based ◽  
Time Frequency Localization ◽  
Mine Flooding ◽  
Ability Evaluation

For the coal resources working which are affected by the coal mine flooding seriously, this paper make an analysis on the factors which affect the coal mine flooding emergency ability evaluation model based on GA-WNN is established through the wavelet neural network value which is optimized with genetic algorithm. This model combined the global optimization ability of genetic algorithm with the time-frequency localization of wavelet neural network. This combination can make up for many defects (for example, the neural network structure should be given artificially, the function can got local minimum easily and so on). Therefore, the local mine flooding emergency ability evaluation model based on genetic algorithm and wavelet neural network have higher reliability and calculation ability, and is beneficial to the pre-control management for coal mine flooding rescue.

Adaptive BP Wavelet Neural Network Method for Soft Fault Diagnosis in Analog Circuit

2013 ◽  
Vol 307 ◽  
pp. 327-330
Author(s):  
Wei Cong ◽  
Bo Jing ◽  
Hong Kun Yu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Adaptive Learning ◽  
Analog Circuit ◽  
Wavelet Neural Network ◽  
Learning Ability ◽  
Time Frequency ◽  
Soft Fault ◽  
Time Frequency Localization ◽  
Soft Fault Diagnosis

Because of the diversity and complexity of soft fault in analog circuit, the rapid and accurate diagnosis is very difficult. For this, an adaptive BP wavelet neural network diagnosis method of soft fault is proposed. It combines the time-frequency localization characteristics of wavelet and the self-learning ability of neural network in soft fault diagnosis of analog circuit, and by introducing the adaptive learning rate the diagnosis ability of BP wavelet neural network model can effectively be improved. In addition, PSPICE software is used to obtain the simulation data of actual analog circuit for the experiment. The results also verify the validity of the proposed method.

Research on the Parameters Identification of Direct Thrust Control System Using Wavelet Neural Network

2013 ◽  
Vol 336-338 ◽  
pp. 794-798
Author(s):  
Li Jun Zhao
Keyword(s):  
Neural Network ◽  
Control System ◽  
Linear Motor ◽  
Wavelet Neural Network ◽  
Good Effect ◽  
Identification System ◽  
Primary Resistance ◽  
Time Frequency ◽  
Thrust Control ◽  
Direct Thrust Control

Wavelet neural network is used in the direct thrust control system of linear motor in this paper, as wavelet theory has the characteristic of the time frequency location characteristic, the strong approximation and fault-tolerant capability. The observation of flux linkage is improved by accurate identification of primary resistance, and the direct thrust control performance of linear motor is further improved. This paper used wavelet neural network to realize the identification signal of resistance. The simulation results show that the identification system has good effect in primary resistance identification. The direct thrust control system based on resistance identification can efficiently improve the control system performances of linear motor, and offer a novel design opinion for improving the low-speed performances of linear motor.

Study of a New Wavelet Neural Network of Image Compression Simulation

2012 ◽  
Vol 490-495 ◽  
pp. 623-627
Author(s):  
Xue Zhang Zhao ◽  
Qun Qi
Keyword(s):  
Neural Network ◽  
Image Compression ◽  
Bp Neural Network ◽  
Local Area ◽  
Wavelet Neural Network ◽  
Convergence Speed ◽  
Good Time ◽  
Time Frequency ◽  
Hidden Layer ◽  
Self Learning

In the practical need in order to make the most effective image compression in this paper, a new image compression used wavelet neural network model, and gives the corresponding calculation formula and algorithm procedures, By using wavelet transform good time-frequency local area on the characteristics and neural network self-learning function characteristics, overcome traditional BP neural network of hidden-layer points are difficult to be determined and the convergence speed is slow and easy to converge to a local minimum points shortcomings. The results of the simulation experiment prove wavelet neural network image compression characteristic and the convergence speed are much better than traditional BP neural network, and show that the algorithm is effective and feasible.

Study on the Onset of Nucleate Boiling in Narrow Annular Channel by Using Wavelet and Wavelet Neural Network

2009 ◽  
Author(s):  
Huiming Wei ◽  
G. H. Su ◽  
S. Z. Qiu ◽  
Xingbo Yang
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Annular Channel ◽  
Nucleate Boiling ◽  
Wavelet Neural Network ◽  
Frequency Space ◽  
Time Frequency ◽  
Annular Channels ◽  
System Pressure ◽  
Artificial Neural

In this study, the local modulus maxima of cubic B-spline wavelet transform are introduced to determine the location of onset of nucleate boiling (ONB). Wavelet transformation has the ability of representing a function and revealing the properties of the function in the joint local regions of the time frequency space. Based on wavelet and artificial neural network, a Wavelet Neural Network (WNN) model predicting ONB for upward flow in vertical narrow annuli with bilateral heating has been developed. The WNN mode combining the properties of the wavelet transform and the advantages of Artificial Neural Networks (ANN) has some advantages of solving non-linear problem. The methods of establishing the model and training of wavelet neural network are discussed particularly in the article. The ONB prediction is investigated by WNN with distilled water flowing upward through narrow annular channels with 0.95 mm, 1.5 mm and 2.0mm gaps, respectively. The WNN prediction results have a good agreement with experimental data. At last, the main parametric trends of the ONB are analyzed by applying WNN. The influences of system pressure, mass flow velocity and wall superheat on ONB are obtained. Simulation and analysis results show that the network model can effectually predict ONB.

scholarly journals Artificial Neural Network Classification of Motor-Related EEG: An Increase in Classification Accuracy by Reducing Signal Complexity

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Vladimir A. Maksimenko ◽  
Semen A. Kurkin ◽  
Elena N. Pitsik ◽  
Vyacheslav Yu. Musatov ◽  
Anastasia E. Runnova ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Motor Imagery ◽  
High Frequency ◽  
Classification Accuracy ◽  
Eeg Signals ◽  
Pass Filter ◽  
Time Frequency ◽  
Artificial Neural

We apply artificial neural network (ANN) for recognition and classification of electroencephalographic (EEG) patterns associated with motor imagery in untrained subjects. Classification accuracy is optimized by reducing complexity of input experimental data. From multichannel EEG recorded by the set of 31 electrodes arranged according to extended international 10-10 system, we select an appropriate type of ANN which reaches 80 ± 10% accuracy for single trial classification. Then, we reduce the number of the EEG channels and obtain an appropriate recognition quality (up to 73 ± 15%) using only 8 electrodes located in frontal lobe. Finally, we analyze the time-frequency structure of EEG signals and find that motor-related features associated with left and right leg motor imagery are more pronounced in the mu (8–13 Hz) and delta (1–5 Hz) brainwaves than in the high-frequency beta brainwave (15–30 Hz). Based on the obtained results, we propose further ANN optimization by preprocessing the EEG signals with a low-pass filter with different cutoffs. We demonstrate that the filtration of high-frequency spectral components significantly enhances the classification performance (up to 90 ± 5% accuracy using 8 electrodes only). The obtained results are of particular interest for the development of brain-computer interfaces for untrained subjects.

scholarly journals Fault Diagnosis Based on an Approach Combining a Spectrogram and a Convolutional Neural Network with Application to a Wind Turbine System

Energies ◽  
2018 ◽  
Vol 11 (10) ◽  
pp. 2561 ◽  
Author(s):  
Wenxin Yu ◽  
Shoudao Huang ◽  
Weihong Xiao
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Wind Turbine ◽  
Back Propagation ◽  
Original Data ◽  
Back Propagation Neural Network ◽  
Support Vector ◽  
Time Frequency ◽  
Wind Turbine System

To investigate problems involving wind turbines that easily occur but are hard to diagnose, this paper presents a wind turbine (WT) fault diagnosis algorithm based on a spectrogram and a convolutional neural network. First, the original data are sampled into a phonetic form. Then, the data are transformed into a spectrogram in the time-frequency domain. Finally, the data are sent into a convolutional neural network (CNN) model with batch regularization for training and testing. Experimental results show that the method is suitable for training a large number of samples and has good scalability. Compared with Back Propagation Neural Network (BPNN), Support Vector Machine (SVM), Extreme Learning Machine (ELM), and other fault diagnosis methods, the average diagnostic correctness rate is higher; so, the method can provide more accurate reference information for wind turbine fault diagnosis.

scholarly journals Speech Enhancement Using Wavelet Neural Network with Sub-Band Adaptive Matched Filter

2011 ◽  
Vol 2-3 ◽  
pp. 127-130
Author(s):  
Dan Yang ◽  
Bin Xu ◽  
Lin Lin Ye ◽  
Xu Wang
Keyword(s):  
Neural Network ◽  
Speech Enhancement ◽  
Wavelet Decomposition ◽  
Matched Filter ◽  
Noise Pollution ◽  
Wavelet Neural Network ◽  
Signal Frequency ◽  
Analysis Method ◽  
Time Frequency ◽  
Adaptive Matched Filter

Wavelet Neural Network (WNN) Is a Time-frequency Analysis Method, which Detects the Subtle Small Changes in the Signal Frequency Domain. Adaptive Filter Provides a Kind of Simple and Applied Method for Processing Signals in Noise. in this Paper, we Proposed a New Speech Enhancement Technique which Is Based on Wavelet Neural Network Using Adaptive Matched Filter Adjusting Weight. we Choose the Signal with Noise Pollution as the Input Signal and then Put it to the Trained Wavelet Neural Network. Wavelet Decomposition and Wavelet Neural Network Weights Processing Adopt Signal Sub-band Adaptive Matched Filter, the Output Signal of Wavelet Neural Network Is an Approximation Form of Original Signal. the Results Show that the WNN Is a Quite Effective Method for the Speech Enhancement and Improving the Ration of Signal to Noise.

Sign in / Sign up

Export Citation Format

Share Document