IDENTIFICATION OF GEOLOGICAL AND GEOPHYSICAL PARAMETERS FOR MATHEMATICAL MODELS

摘要

A neuro-fuzzy network technology (soft computing) for identification of the geological and geophysical parameters for mathematical models of natural reservoirs in the exploitation of oil and gas deposits is proposed and verified. The effectiveness of the technology is demonstrated, especially in the early stage of prospecting, when information is uncertain and limited. With sufficient information, it is proposed that a recursion algorithm be used to identify the coefficients from measurements of the input and output coordinates of this generalized model in the presence of measurement noise.