Abstract
ABSTRACT In welltest interpretation the model identification was soon foreseen as a possible "Artificial Intelligence" (AI) application. As in most other fields of application of AI, both symbolic and connectionist (neural networks) approaches have been tried. Both have structural and complementary qualities and limitations. The objective of K.I.W.I., a research project presented in this paper, was to develop an efficient AI module and integrate it in an operational welltest software. This module should identify the shape of even a noisy response, select possible models and estimate parameters with the highest possible success ratio. The only user input would be to select between models suggested by the module. Only a combination of symbolic and connectionist approaches (a hybrid system) could meet these requirements. After introducing the project specifications and the basic programming tools used in it, this paper presents the different steps of the research and describes how such a hybrid system was developed.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
