Hybrid method of genetic algorithm and artificial neural network for PEF and CGR logs prediction in one of fracture reservoir in south iran

WELL logging has been in use for almost one centuray as an essential tool for determinatio of potential production in hydrocarbon reservoirs. Sometimes because of the lack or badness of data of logging tools for example in old wells some logs have not been run, or because of the failure of logging tool or bad hole conditions or loss of data due to inappropriate storage data have not the desired quality to evaluate the petrophysical properties it seems to be necessary to seek a way to botain a valid approximation of data. despite of the wide range of applications and flexibility of artificial neural networks ANNs, there is still no general framework or procedure through which the appofpiate network for a specific task can be designed . design and structural optimization of neural networks is still strongly dependent upon the designers experience. this is an obvious barrier to the wider applications of neural network. to mitigate this problem a new method for the auto -design of neural networks was used based on genetic algorithm GA.

Keywords:

artificial intelligence , artificial neural network , genetic algorithm , neuron , computed gamma ray log , photoelectric factor log