Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
Add to Favorite Get Latest Update

Application of Improved BP Neural Network on Intelligent Identification of Flow Regime of Oil Gas Water Multiphase Flow

Wu Haojiang,Hu Zhihua,Zhou Fangde(Xi′an Jiaotong University, Xi′an 710049, China)  
BP (back propagation) neural network encounters local minimum, slow convergence speed and convergence instability. The shortcomings can be overcome by application of the nonlinear square method. The convergency speed of the modified BP neural network is increased by one or two orders of magnitude. Pressure signals of oil gas water multiphase flow are measured with a piezo resistance pressure transducer. The characteristic vectors are extracted by using the reconstructing phase space method in fractal theory. The characteristic vectors are then fed into the modified BP neural network which leads to the intelligent identification of flow regime of oil gas water multiphase flow. Experimental results shows that the modified BP neural network can effectively and automatically send out the imformation of flow regime.
【Fund】: 国家自然科学基金!59236131
【CateGory Index】: O359.1
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved