Development of HT - BP neural network system for the identification of well test interpretation model

W. Sung, U. Hanyang, I. Yoo, S. Ra, U. Hanyang, H. Park

Research output: Contribution to conferencePaperpeer-review

8 Scopus citations

Abstract

Neural network technique has proved to be a good model classifier in all areas of engineering and has gained a considerable acceptance in well test interpretation model identification of petroleum engineering. This paper develops back propagation (RP) neural network with Hough transform (HT) technique to overcome data selection problem and to use single neural network rather than sequential nets. The Hough transform method is proved to be a powerful tool for the shape detection in image processing and computer vision technologies. With the aid of a HT method, one simple pattern can be extracted from the full set of data of pressure derivative type curve containing noisy and extraneous points. By using extracted pattern from HT method, the number of data points when BP neural network is performed for the identification process can then be minimized.

Original languageEnglish
Pages7-13
Number of pages7
StatePublished - 1995 Jan 1
EventProceedings of the 1995 Eastern Regional Conference - Morgantown, WV, USA
Duration: 1995 Sep 181995 Sep 20

Other

OtherProceedings of the 1995 Eastern Regional Conference
CityMorgantown, WV, USA
Period95/09/1895/09/20

Fingerprint Dive into the research topics of 'Development of HT - BP neural network system for the identification of well test interpretation model'. Together they form a unique fingerprint.

Cite this