scholarly journals Cavitation Detection in Centrifugal Pump Based on Interior Flow-Borne Noise Using WPD-PCA-RBF

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Liang Dong ◽  
Kan Wu ◽  
Jian-cheng Zhu ◽  
Cui Dai ◽  
Li-xin Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Wavelet Packet ◽  
Noise Analysis ◽  
Basic Function ◽  
Operating Efficiency ◽  
Centrifugal Pumps ◽  
Time Frequency ◽  
Interior Flow ◽  
Cavitation Detection

Cavitation detection is particularly essential for operating efficiency and stability of pumps. In this work, to improve the accuracy and efficiency of identification, an approach combining wavelet packet decomposition (WPD) with principal component analysis (PCA) and radial basic function (RBF) neural network is introduced to detect the cavitation status for centrifugal pumps. The cavitation performance and interior flow-borne noise are measured under three different flow conditions. Then, time-frequency domain analysis is performed on the interior flow-borne noise signal using WPD, and the energy coefficient of each node is calculated to determine the optimal decomposition frequency band. Six-feature parameters are extracted based on frequency-division statistics, including three time-domain features and three wavelet packet features. After that, the PCA is applied for dimensionality reduction. Finally, three cavitation statuses of noncavitation, inception cavitation, and serious cavitation are identified adopting RBF neural network. The results show that the comprehensive identification rate of the proposed method for three cavitation statuses reaches 98.2% with low identification error. The method based on interior flow-borne noise analysis can be well applied for on-line monitoring and diagnosis of pump industry.

Wavelet Packet Analysis Based Feature Extraction of Vehicular Acoustic Signal

2011 ◽  
Vol 55-57 ◽  
pp. 1593-1598
Author(s):  
Xiao Xuan Qi ◽  
Jian Wei Ji ◽  
Xiao Wei Han ◽  
Zhong Hu Yuan
Keyword(s):  
Acoustic Signal ◽  
Rbf Neural Network ◽  
Wavelet Packet ◽  
Wavelet Packet Analysis ◽  
Moving Vehicle ◽  
Time Frequency ◽  
Vehicle Type ◽  
Feature Information ◽  
Vehicle Type Classification ◽  
Type Classification

In this paper, an approach based on wavelet packet analysis is proposed to deal with the problem that acoustic signal of moving vehicle is easily influenced by environmental noise in vehicle type classification. Wavelet packet analysis is applied to extract local and detail feature information of acoustic signal in the time-frequency domain. Firstly, raw acoustic signal is decomposed into different frequency bands by wavelet packet analysis, and then decomposition coefficients are reconstructed. The energy of every frequency band component is used to form the feature vector. Finally, vehicle type classification is implemented by RBF neural network on the basis of these feature vectors. Experimental results show that the proposed method is feasible and effective.

The Evaluation Model of the Hydropower Project Financing Risk Based on AHP-RS and RBF Neural Network

2011 ◽  
Vol 474-476 ◽  
pp. 2243-2246 ◽  
Author(s):  
Hui Zhao ◽  
Li Ming Chen
Keyword(s):  
Neural Network ◽  
Rough Set Theory ◽  
Rbf Neural Network ◽  
Evaluation Model ◽  
Indicator System ◽  
Basic Function ◽  
Hydropower Project ◽  
Project Financing ◽  
Analytic Hierarchy ◽  
Financing Risk

A evaluation model based on the integration of analytic hierarchy process (AHP)-rough set theory (RS) and radial basic function (RBF) neural network is put forward for grasping the hydropower project financing risk. Firstly, the evaluation indicator system is constructed by AHP, then the evaluation indicators are discretized by RS neural network. And then, RBF neural network is used to evaluate the hydropower project financing risk. In order to grasp this evaluation model better, finally, the paper provides an example to demonstrate the application of this evaluation model.

Four-channel sEMG for Elbow Load Recognition

2021 ◽  
Author(s):  
Jiabin Cai ◽  
Junjun Song ◽  
Yuanqiang Long
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Wavelet Packet ◽  
Control Mode ◽  
Support Vector ◽  
Semg Signal ◽  
Joint Force ◽  
Emg Signal ◽  
The Relationship ◽  
Rehabilitation Exercise

Abstract In order to help patients after surgery to carry out reasonable rehabilitation training, avoid joint adhesions and movement disorders, the relationship between surface electromyograph (sEMG) signal changes and the size of the patient ' s joint force in the process of rehabilitation exercise was studied, hoping to use the relationship between them to redesign the control mode of the rehabilitation robot, and a method was proposed to identify the size of the elbow load based on wavelet packet. Firstly, s EMG signals of human elbow joint during stretching and bending under different loads were collected by 4-channel surface electromyography. Then, the wavelet packet decomposition method was used to obtain the feature vector composed of energy(E), variance(VAR) and mean absolute value(MAV) of wavelet packet coefficient. Finally, the improved support vector machine ( ISVM), BP neural network and RBF neural network were used for pattern recognition of three different forces. The experimental results show that the change of sEMG signal is indeed related to the size of joint force. It is feasible to identify the load of s EMG signal.

Diagnosis Technique Based on BP and D-S Theory

2011 ◽  
Vol 179-180 ◽  
pp. 544-548
Author(s):  
Qiu Yun Mo ◽  
Jie Cao ◽  
Feng Gao
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Rbf Neural Network ◽  
Wavelet Packet ◽  
The Neural Network ◽  
Evidential Theory ◽  
The Given ◽  
Fusion Framework ◽  
Level Fusion ◽  
Theory And Experiments

This paper constructs a common data fusion framework of fault diagnosis, by combining local neural networks with dempster-shafer (D-S) evidential theory. The RBF neural network is proposed as a local neural network of the fault pattern recognition, and its input vectors are extracted by the wavelet packet decomposition of various frequency energy. Then, the signal of each sensor separately has a feature level fusion. This method is effective, verified by experiments. The given decision level fusion is based on combining the features of the neural network and the D-S theory, and experiments show the results of the fault diagnosis are more accurate by this method.

Sign in / Sign up

Export Citation Format

Share Document