Dissertation > Excellent graduate degree dissertation topics show
Oil-water Two Phase Flow Pattern Recognition Based on Electric Conductance Fluctuation Signal
Author: ZhangSongLin
Tutor: ZhouYunLong
School: Tohoku Electric Power University
Course: Detection Technology and Automation
Keywords: Oil-water two-phase flow Flow pattern identification Wavelet packet decomposition Empirical Mode Decomposition Neural Networks
CLC: O359
Type: Master's thesis
Year: 2011
Downloads: 39
Quote: 0
Read: Download Dissertation
Abstract
|
Oil-water two-phase flow is widespread among modern industrial production , have a great impact on the flow -type flow and heat transfer characteristics of , and how to determine the flow pattern of the two-phase flow has been an important topic in the study of two-phase flow . There are two traditional oil-water flow patterns identification method : one is the use of human observation or measurement methods ; Another method is the use of flow pattern transition criteria or flow pattern map . Traditional flow identification method is not only influenced by subjective factors , and the flow - line identification can not be achieved , so the need to improve the traditional identification methods . The experimental study of the experimental stage in the oil-water two-phase flow , and the vertical riser conductance fluctuations of oil-water two-phase flow signal analysis . And the wavelet transform , wavelet packet decomposition , the EMD decomposition and neural network is applied to the flow pattern identification from both experimental and theoretical aspects of the flow - intelligent recognition method . First conductance fluctuating signal denoising using wavelet transform , and then the application of wavelet packet decomposition , EMD decomposition convection conductance fluctuating signal analysis , extraction of wavelet packet energy and the IMF energy as the characteristics of the flow pattern , then using BP , the RBF improved RBF and Elman NN model as the type of oil - water two-phase flow pattern classifier . Finally, the different feature vectors extracted training samples were sent to BP, RBF, improved RBF and Elman neural network training , the trained classifier model as the flow pattern identification . The results show that the identification of the test samples found that IMF - based energy and improved RBF neural network to identify the best . Theoretically and technically intelligent recognition of Multiphase Flow has opened up a new way .
|
Related Dissertations
- High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
- Research on Anti-periodic Solutions of Delayed Cellular Neural Networks without Assuming Global Lipschitz Conditions,TP183
- Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
- The Recognization of License Plate Based on EMD and Its Application,TP391.41
- Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
- Multi- license plate location method based on CNN's Intelligent Transportation Systems Research,TP391.41
- Research on the Models of GPS Height Fitting Based on BP Neural Network and Their Applications,P228.4
- Research of QoS Optimization Based on Neural Network Prediction for Ethernet Passive Optical Network,TN929.1
- Sensitivity Study and Application of Complex Variabal Weight Function Neural Network,TP183
- Researches on the Application of the Neuron-MOS in the Neural Network,TP183
- A Reduction Method for Artificial Neural Network Inputs Based on An Improved Genetic Algorithm,TP18
- On-line Monitoring of Tool Wear for Mass Production,TG71
- Modeling of Photovoltaic Cells and Its Application in Energy Prediction,TM914.4
- Research on Evaluating the Feature Fatigue’s Effect on Customer Equip,F224
- Delay Neutral System Stability Analysis of Neural Networks,O175.13
- One kind of structure in the depth of learning prototype classification method,TP18
- The Design of Identification System for Power Marketing Services,TP391.41
- The Study of Intelligent Intrusion Detection System Based on Neural Network in Linux,TP393.08
- RFID Information Sharing in Supply Chain and Business Valuation Research,F224
- Slurry pipeline transportation system, process monitoring and fault diagnosis,F426.1
- Consider short-term load forecasting PV,TM715
CLC: > Mathematical sciences and chemical > Mechanics > Fluid Mechanics > Multiphase flow
© 2012 www.DissertationTopic.Net Mobile
|