Study on Method of Recognizing Characteristics of Pipeline Leakage Acoustic Signals

2006 ◽  
Author(s):  
Likun Wang ◽  
Dongjie Tan ◽  
Yongjun Cai ◽  
SongGuang Fu ◽  
Jian Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Field Experiment ◽  
Frequency Band ◽  
Bp Neural Network ◽  
Acoustic Signals ◽  
Pressure Variation ◽  
Experimental Results ◽  
Acoustic Sensors ◽  
Experiment Data

Wavelet package and neural network are used to recognize the characteristics of pipeline leakage acoustic signals. Acoustic signals produced by pressure variation of pipelines can be detected by the acoustic sensors installed on the pipelines. The detecting accuracy can be increased with recognizing the acoustic signals correctly. The method to detect acoustic signals by combining the wavelet package and neural network is introduced in this paper. The signal is decomposed with wavelet package firstly, then the decomposed coefficients in each frequency band are obtained through reconstruction. As a result, the parameters of the new sequences reconstructed on every decomposed node are acquired, and then these parameters are input to BP neural network to recognize the fault reason intelligently. At the end of the paper, field experiment data and their analyzed results are studied. The experimental results are provided to show that the proposed method can increase the accuracy efficiently.

Creep Behavior Prediction Research of T92 Steel Based on BP Neural Network

2013 ◽  
Vol 467 ◽  
pp. 203-207
Author(s):  
Jian Liu
Keyword(s):  
Neural Network ◽  
Creep Behavior ◽  
Bp Neural Network ◽  
Network Theory ◽  
Experimental Results ◽  
Behavior Prediction ◽  
Forecast Precision ◽  
Network Method ◽  
Simulation Results ◽  
Neural Network Theory

Based on the BP neural network theory, the creep rate prediction model of T92 steel was established under multiple stress levels. Obtained the experimental results and using the model, the experimental results were trained. The results show that the simulation results match the measured results well with a high forecast precision. The BP neural network method can serve as research on T92 steel creep behavior.

Fault Diagnosis for Electrical Control System of Automobile Based on Support Vector Machine

2014 ◽  
Vol 666 ◽  
pp. 203-207
Author(s):  
Jian Hua Cao
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Control System ◽  
Fault Diagnosis ◽  
Bp Neural Network ◽  
Experimental Results ◽  
Support Vector ◽  
Electrical Control ◽  
Diagnosis Method ◽  
The Common

This paper is to present a fault diagnosis method for electrical control system of automobile based on support vector machine. We collect the common fault states of electrical control system of automobile to analyze the fault diagnosis ability of electrical control system of automobile based on support vector machine. It can be seen that the accuracy of fault diagnosis for electrical control system of automobile by support vector machine is 92.31%; and the accuracy of fault diagnosis for electrical control system of automobile by BP neural network is 80.77%. The experimental results show that the accuracy of fault diagnosis for electrical control system of automobile of support vector machine is higher than that of BP neural network.

scholarly journals Insulation Monitoring of Dynamic Wireless Charging Network Based on BP Neural Network

2021 ◽  
Vol 12 (3) ◽  
pp. 129
Author(s):  
Feng Wen ◽  
Wenjie Pei ◽  
Qiang Li ◽  
Zhoujian Chu ◽  
Wenhan Zhao ◽  
...  
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Power Conversion ◽  
Experimental Results ◽  
Calculation Error ◽  
Insulation Resistance ◽  
Wireless Charging ◽  
Monitoring Method ◽  
Insulation Monitoring ◽  
On Line

The transmission cable and power conversion device need to be buried underground for dynamic wireless charging of an expressway, so cable insulation deterioration caused by aging and corrosion may occur. This paper presents an on-line insulation monitoring method based on BP neural network for dynamic wireless charging network. The sampling signal expression of the injection signal is derived, and the feasibility of this method is verified by experiments, which effectively overcomes the problem of large calculation error of insulation resistance when the cable capacitance to ground is large. The experimental results indicate that the error of the proposed method is less than 9%, which can meet the needs of insulation monitoring.

All-Sky Cloud Classification Based on Transparency and Texture Features

2012 ◽  
Vol 235 ◽  
pp. 3-8
Author(s):  
Xiao Ying Chen ◽  
Min Wang ◽  
Shu Dao Zhou
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Recognition Rate ◽  
Color Space ◽  
Texture Features ◽  
Experimental Results ◽  
Second Moment ◽  
Cloud Classification ◽  
Space Method ◽  
Classification Recognition

This paper proposes a new algorithm to classify the cloud of all-sky ground-based based on transparency and texture features. First, we uses the transparency to separate the single sky background and cloud foreground image, which based on the natural matting of perceptual color space method, then analysis the texture features of cloud foreground image with second moment, contrast, correlation and entropy, finally, uses BP neural network to identify the type of the cloud. The experimental results show that the algorithm can separate the sky and cloud effectively, and the cloud classification recognition rate is higher.

Research on Pattern Recognition Based on BP Neural Network

2011 ◽  
Vol 282-283 ◽  
pp. 161-164
Author(s):  
Yong Lin Wang ◽  
Yan Liu ◽  
Sheng Bing Che
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Pattern Classification ◽  
Adaptive Learning ◽  
Bp Neural Network ◽  
Fault Tolerant ◽  
Bp Algorithm ◽  
Experimental Results ◽  
Learning Capacity ◽  
Neural Network Algorithm

BP neural network has strong fault-tolerant and adaptive learning capacity, so it is widely used in pattern recognition. Based on the classic BP neural network, parameters of the BP algorithm has been optimized, which achieved a classification based on the improved BP neural network algorithm. By discussing the use of BP neural network in the application of pattern classification recognition, this paper detailedly studies the recognition effect of various parameters. Experimental results show that the improved algorithms has very good practical value.

Research on the Prediction of Drug Sales Based on Levenberg-Marquardt Algorithm

2012 ◽  
Vol 198-199 ◽  
pp. 1452-1456 ◽  
Author(s):  
Xue Feng Jiang
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Production Planning ◽  
Bp Neural Network ◽  
Bp Algorithm ◽  
Experimental Results ◽  
Drug Production ◽  
Drug Sales ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt

Prediction of drug sales trend is very important for the drug production planning and inventory. The paper studies the BP neural network and presents a kind of method based on reformative neural network to solve the issue of prediction of drug sales. Compare with traditional BP algorithm, the result reveals that this algorithm has structure rationalization and rapid constringency velocity. The experimental results demonstrate that the prediction model based on Levenberg_Marquardt algorithm is good at predicting drug sales.

The Vehicle Adjustable Suspension System Based on Data Mining

2013 ◽  
Vol 416-417 ◽  
pp. 790-795
Author(s):  
Gu Xiong Li ◽  
Kai Huang ◽  
Kan Feng Huang
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Bp Neural Network ◽  
Ride Comfort ◽  
Suspension System ◽  
Experimental Results ◽  
Sensor Data ◽  
Pavement Condition ◽  
Good Outcome ◽  
Control Accuracy

One being developed vehicle adjustable suspension system, need to predict pavement condition then automatically adjust each suspension height, in order to ensure control accuracy and ride comfort. This paper proposed a method using BP neural network to predict the vehicle height sensor data of each wheel suspension. The experimental results show that, the proposed algorithm is practical and reliable, and good outcome have been achieved in the application of instruction carriage.

Multi-View Face Recognition Based on BP Neural Network and KPCA

2014 ◽  
Vol 1030-1032 ◽  
pp. 1737-1740
Author(s):  
Xin Wang ◽  
He Pan
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Face Recognition ◽  
Bp Neural Network ◽  
Recognition Rate ◽  
Principal Component ◽  
Experimental Results ◽  
Kernel Principal Component Analysis ◽  
Face Images ◽  
Network Methods

This paper introduces the research background of computer face recognition technology, and puts forward a method of using kernel principal component analysis (KPCA) method and improved BP neural network methods for analysis and identification of multi view face images. The experimental results show that this algorithm is both effective and accurate. It achieved a higher recognition rate and excellent resistance to noise.

scholarly journals Calculation for Primary Combustion Characteristics of Boron-Based Fuel-Rich Propellant Based on BP Neural Network

2012 ◽  
Vol 2012 ◽  
pp. 1-6 ◽  
Author(s):  
Wu Wan'e ◽  
Zhu Zuoming
Keyword(s):  
Neural Network ◽  
Burning Rate ◽  
Ammonium Perchlorate ◽  
Bp Neural Network ◽  
Calculation Model ◽  
Combustion Characteristics ◽  
Experimental Results ◽  
Calculation Error ◽  
Backpropagation Neural Network ◽  
Practical Scheme

A practical scheme for selecting characterization parameters of boron-based fuel-rich propellant formulation was put forward; a calculation model for primary combustion characteristics of boron-based fuel-rich propellant based on backpropagation neural network was established, validated, and then was used to predict primary combustion characteristics of boron-based fuel-rich propellant. The results show that the calculation error of burning rate is less than %; in the formulation range (hydroxyl-terminated polybutadiene 28%–32%, ammonium perchlorate 30%–35%, magnalium alloy 4%–8%, catocene 0%–5%, and boron 30%), the variation of the calculation data is consistent with the experimental results.

Using the Improved Genetic BP Neural Network Algorithm for Lithologic Identification

2014 ◽  
Vol 1037 ◽  
pp. 389-392 ◽  
Author(s):  
Shui Ming He ◽  
Lu Wen Liu
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Convergence Speed ◽  
Experimental Results ◽  
Crossover Operator ◽  
Generalization Performance ◽  
Algorithm Convergence ◽  
Network Algorithm ◽  
Neural Network Algorithm

in order to fully optimize the BP neural network, and make it have better generalization performance, we improve and design a genetic BP neural network, the algorithm is given, and their crossover operator was improved. And this method is applied in identifying lithology, the experimental results show that this method increases the algorithm convergence speed and effect, and it has certain practical value.

Sign in / Sign up

Export Citation Format

Share Document