Leakage Diagnosis Method for Pipelines Based on Multi-Weight Neural Network

2014 ◽  
Vol 697 ◽  
pp. 429-433 ◽  
Author(s):  
Zhi Gang Chen ◽  
Xin Rong Zhong ◽  
Yi Dong Xie
Keyword(s):  
Neural Networks ◽  
Pressure Wave ◽  
Theoretical Basis ◽  
Primary Diagnosis ◽  
Computational Process ◽  
Gas Pipelines ◽  
Characteristic Parameters ◽  
Normal Node ◽  
City Gas ◽  
Diagnosis Method

For reasons of low accuracy of traditional leakage, a pipeline leakage diagnosis method based on multi-weight neural networks is presented to recognized leak signal in city gas pipelines. By using analysis and modeling a multi-weight neural networks are established at normal node to simplify network structure. The Information entropy of leakage characteristic parameters of negative pressure wave was used as input eigenvector respectively for primary diagnosis. It has been applied for leakage diagnosis in city gas pipelines with the whole computational process done by a computer. Results of simulation and tests show that this method has its advantage in dealing with multi-coupled fault situations and is featured by a high probability of accuracy, which not only proves the method to be effective, but also provides a theoretical basis and a new way for leak diagnosis of other pipelines.

A Gas Pipeline Leakage Diagnosis of Fusing BP Neural Network Basing on WSN and D-S Theory

2014 ◽  
Vol 541-542 ◽  
pp. 1442-1446 ◽  
Author(s):  
Ping Ting Liu ◽  
Rui Kun Gong ◽  
Yu Han Gong ◽  
Chong Hao Wang
Keyword(s):  
Neural Networks ◽  
Primary Diagnosis ◽  
Gas Pipeline ◽  
Characteristic Parameters ◽  
Combination Rules ◽  
Normal Node ◽  
Diagnosis Method ◽  
Basic Probability ◽  
Diagnosis Accuracy ◽  
Fusion Theory

For reasons of low accuracy of artificial survey leakage, a gas pipeline leakage diagnosis method based on BP neural networks and D-S theory is presented by introducing WSN and information fusion theory. Two sub-neural networks are established at normal node to simplify network structure. The leakage characteristic parameters of negative pressure wave and acoustic emission signals are used as input eigenvector respectively for primary diagnosis. Through making preliminary fusion result s as the basic probability assignment of evidence, the impersonal valuations are realized. Finally, all evidences are aggregated at normal and sink node respectively by using the improved combination rules. The method makes full use of redundant and complementary leakage information. Numerical example shows that the proposed improves the leakage diagnosis accuracy and decreases the recognition uncertainty.

Classification and Recognition of Plant Leaf Based on Neural Networks

2011 ◽  
Vol 464 ◽  
pp. 38-42 ◽  
Author(s):  
Ping Ye ◽  
Gui Rong Weng
Keyword(s):  
Neural Networks ◽  
Fractal Dimension ◽  
Recognition Rate ◽  
Image Binarization ◽  
Characteristic Parameters ◽  
Moment Invariant ◽  
Plant Leaf ◽  
The Neural Networks ◽  
Novel Method ◽  
The Moment

This paper proposed a novel method for leaf classification and recognition. In the method, the moment invariant and fractal dimension were regarded as the characteristic parameters of the plant leaf. In order to extract the representative characteristic parameters, pretreatment of the leaf images, including RGB-gray converting, image binarization and leafstalk removing. The extracted leaf characteristic parameters were further utilized as training sets to train the neural networks. The proposed method was proved effectively to reach a recognition rate about 92% for most of the testing leaf samples

Using acoustic technique to detect leakage in city gas pipelines

2012 ◽  
Vol 19 (8) ◽  
pp. 2373-2379 ◽  
Author(s):  
Zhi-gang Chen ◽  
Xiang-jiao Lian ◽  
Liang He
Keyword(s):  
Gas Pipelines ◽  
Acoustic Technique ◽  
City Gas

scholarly journals Combined Diagnosis of PD Based on the Multidimensional Parameters

2016 ◽  
Vol 2016 ◽  
pp. 1-12 ◽  
Author(s):  
Mohammad Heidari
Keyword(s):  
Final Diagnosis ◽  
Semisupervised Learning ◽  
Adaptive Mutation ◽  
Characteristic Parameters ◽  
Ultrasonic Signals ◽  
Different Types ◽  
Diagnosis Method ◽  
Characteristic Values ◽  
Types Of Faults ◽  
Frequency Current

This paper presents a comprehensive multiparameter diagnosis method based on multiple partial discharge (PD) signals which include high-frequency current (HFC), ultrasound, and ultrahigh frequency (UHF). The HFC, ultrasound, and UHF PD are calculated under different types of faults. Therefor the characteristic values, as nine basic characteristic parameters, eight phase characteristic parameters, and the like are calculated. Diagnose signals are found with the method based on information fusion and semisupervised learning for HFC PD, adaptive mutation parameters of particle entropy for ultrasonic signals, and IIA-ART2A neural network for UHF signals. In addition, integrate the diagnostic results, which are the probability of fault of various defects and matrix, of different PD diagnosis signals, and analysis with Sugeno fuzzy integral to get the final diagnosis.

Simulation and Analysis about Different Pressure Angle in Involute Gears Based on Neural Network

2014 ◽  
Vol 540 ◽  
pp. 88-91 ◽  
Author(s):  
Jun Xiao ◽  
Xu Lei Deng ◽  
Jia Ning He ◽  
Wu Xing Ma ◽  
Yan Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Learning Process ◽  
Theoretical Basis ◽  
Nonlinear Mapping ◽  
Pressure Angle ◽  
Involute Gear ◽  
Transmission Design ◽  
Involute Gears ◽  
The Neural Networks

This article introduced neural network, discusses the neural networks model and its learning process. Using the MATLAB environment research and analysis the involute gear undercutting relationship, which under different pressure angles. In the number of teeth or modulus has been scheduled environment apply the nonlinear mapping characteristics of neural networks to involute gear undercutting do a more accurate simulation. This provides a theoretical basis for different pressure angle involute gear in gear transmission design.

A Fault Diagnosis Method in VSC-HVDC Simulation System Based on BRBP Neural Networks

2013 ◽  
Vol 860-863 ◽  
pp. 2269-2274
Author(s):  
Hao Yang Cui ◽  
Yong Peng Xu ◽  
Jun Jie Yang ◽  
Jun Dong Zeng ◽  
Zhong Tang
Keyword(s):  
Neural Networks ◽  
Fault Diagnosis ◽  
Back Propagation ◽  
Voltage Source ◽  
Voltage Source Converter ◽  
Hvdc System ◽  
High Voltage Direct Current ◽  
Current Transmission ◽  
Diagnosis Method ◽  
Dc Current

As the feature of faulty signal in high voltage direct current transmission technology based on voltage source converter (VSC-HVDC) system is complicated to extract and its difficult to carry on the fault diagnosis. On the basis of the PSCAD simulation model of VSC-HVDC system, the DC current faulty signal is analyzed. Then, the wavelet analysis method was adopted to extract the eigenvector of faulty signal, and combined with method of Bayesian regularization back-propagation (BRBP) neural networks, the system fault was identified. The simulation results show that the method is more efficiently and more rapidly than the adding momentum BP neural network on the VSC-HVDC system faults diagnosing.

Sign in / Sign up

Export Citation Format

Share Document