A multi-well complex lithology intelligent identification method and system based on logging data

Abstract

The invention relates to a multi-well complex lithology intelligent identification method and system based on logging data. The method comprises the following steps: firstly, determining a target logging data file and carrying out format conversion and normalization preprocessing; performing feature screening and / or feature combination expansion on the logging curve data according to the known lithology of the key coring well in the whole region in the coring well section to obtain the logging curve data sensitive to the lithology; performing labeling calibration on the logging curve data sensitive to the lithology response to form a sample database, and forming a to-be-tested database by using the logging curve data which are not labeled in the whole region; utilizing data of the sample databaseto carry out machine learning training by combining a plurality of machine learning algorithms, and then automatically establishing a plurality of lithology recognition models. An optimal modelis selected through a classification performance evaluation rule, the optimal model is used for carrying out lithology prediction on the data in the database to be tested so as to realize intelligentidentification of multi-well complex lithology in the whole region, and the method is efficient, convenient, applicable in the whole region and very accurate in automatic intelligent prediction result.

Description

technical field [0001] The invention relates to the technical field of geological engineering lithology identification, in particular to an intelligent identification method and system for multi-well complex lithology based on logging data. Background technique [0002] Lithology identification has always been a key analysis problem in geological engineering research, and for reservoir description, the most basic problem is to solve the lithology problem of multiple wells in the work area. Lithology identification in the prior art mainly includes geological research method, intersection map method, and lithology identification using mathematical algorithms. The lithology of the cored section can be obtained by observing the cored samples for analysis, but the cost of coring is high and difficult, and the prior art for lithology identification is only a single key well, each time only A very small number of cores can be taken, which means that the lithology data of most well...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a method based on well logging data to solve the defects in the prior art that the cost of coring in the whole area is too high, the identification of lithology in the whole area is difficult, and the characteristic logging curve is too single, which leads to the low accuracy of lithology identification results. Multi-well complex lithology intelligent identification method, which reasonably and effectively introduces technical principles such as artificial intelligence machine learning training, intelligent analysis and comparison, and automatic prediction results based on models, to efficiently, quickly and reliably complete the intelligent identification of multi-well complex lithology in the whole area. identification, greatly improving the speed and accuracy of lithology identification

Images