The Ultrasonic Signal Identification of the Nickel-Based Superalloy Based on the Wavelet Neural Network

2010 ◽  
Vol 37-38 ◽  
pp. 1581-1584
Author(s):  
Xin Yin ◽  
Yuan Peng Liu
Keyword(s):  
Neural Network ◽  
Wavelet Transformation ◽  
Wavelet Neural Network ◽  
Ultrasonic Signal ◽  
Good Time ◽  
Signal Identification ◽  
Time Frequency ◽  
Learning Function ◽  
Nickel Based Superalloy ◽  
Self Learning

By using the good time-frequency localized nature of the wavelet transformation and self-learning function of the traditional artificial neural network, this paper constructed a wavelet neural network model for the blemish signals in ultrasonic testing of the nickel-based superalloy GH4169, and it could recognize types of the blemish signals. The results show that the method is effective in fault diagnosis. Finally the article has confirmed its feasibility and superiority.

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.

The Slope Deformation Forecast Model Based on Kalman Filter and Wavelet Neural Network

2013 ◽  
Vol 671-674 ◽  
pp. 323-327
Author(s):  
Bing Jun Shi ◽  
Yong Fen Ruan ◽  
Qi Li ◽  
Yong Hong Wu
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Geotechnical Engineering ◽  
Forecast Model ◽  
Wavelet Neural Network ◽  
Slope Deformation ◽  
Time Frequency ◽  
Learning Function ◽  
Time Frequency Localization ◽  
Self Learning

Deformation is the macroscopic index for the structure of geotechnical engineering, it is important for the design and construction of geotechnical engineering to monitor the deformation and analyze the monitored data. Kalman filter can enhance the effectiveness of the monitored data and wavelet neural network has the favorable time－frequency localization features and self－learning function. Firstly, the monitored data has been filtered by Kalman filter, and then a deformation forecast model will be established by means of combining with neural network wavelet to predict the deformation of actual engineering. The result shows that the forecast model is successful and effective to forecast the slope deformation.

High-Power AC Servo System Identification Research Based on Wavelet Neural Network

2012 ◽  
Vol 220-223 ◽  
pp. 997-1002 ◽  
Author(s):  
Run Min Hou ◽  
Rong Zhong Liu ◽  
Yuan Long Hou ◽  
Qiang Gao
Keyword(s):  
Neural Network ◽  
System Identification ◽  
High Power ◽  
Servo System ◽  
Wavelet Neural Network ◽  
Good Time ◽  
Approximation Accuracy ◽  
Ac Servo System ◽  
Time Frequency ◽  
Ac Servo

As a result of the non-linear characteristics and the uncertain disturbances in high-power AC servo system, it is difficult to construct an accurate mathematical model. In order to solve this problem, this article proposes a system identification method based on wavelet neural network. It makes full use of the advantages of the wavelet which combines neural network good time-frequency localization property and volatility of wavelet function and the nonlinear mapping capacity, self-learning and adaptive capacity of neural networks to solve the problem of non-unique RBF neural network approximation function expression. The simulation results show that the convergence rate, robustness and approximation accuracy of this method are better than the traditional neural network.

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.

Short-Term Gas Load Forecasting Based on Wavelet BP Neural Network Optimized by Genetic Algorithm

2014 ◽  
Vol 631-632 ◽  
pp. 79-85 ◽  
Author(s):  
Feng Yu ◽  
Zhi Qing Wang ◽  
Xiao Zhong Xu
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Bp Neural Network ◽  
Load Forecasting ◽  
Learning Ability ◽  
Time Frequency ◽  
Proposed Model ◽  
Real Coded Genetic Algorithm ◽  
Self Learning ◽  
Single Neural Network

Aiming at the limitations of a single neural network for effective gas load forecasting, a combinational model based on wavelet BP neural network optimized by genetic algorithm is proposed. The problems that traditional BP algorithm converges slowly and easily falls into local minimum are overcame. The wavelet neural network strengthens the function approximation capacity of the network by combining the well time-frequency local feature of wavelet transform with the self-learning ability of neural network. And optimized by the real coded genetic algorithm, the network converges more quick than non-optimized one. This proposed model is applied to daily gas load forecasting for Shanghai and the simulation results indicate that this algorithm has excellent prediction effect.

Sign in / Sign up

Export Citation Format

Share Document