Logging lithology recognition method based on convolutional neural network learning

Abstract

The invention discloses a logging lithology recognition method based on convolutional neural network learning. The method comprises the following steps: 1, taking a data curve acquired for drilling coring as an input feature; taking a drilling lithology result as an input feature label, cleaning the sample data, and establishing a learning data sample; 2, sequentially arranging the three-porositycurve, the three-resistivity curve and the three-lithology curve, dividing drilling lithology into four types, and dividing learning data samples into a training set and a test set; 3, extracting feature parameters through one-time convolution and one-time pooling, linking a Softmax regression layer, and establishing a convolutional neural network model; 4, training the convolutional neural network model, testing the accuracy of the convolutional neural network model by using the test set; if the required accuracy is met, putting the convolutional neural network model into use, and if the required accuracy is not met, increasing the training amount; and 5, identifying the lithology of the new well by using the trained convolutional neural network model. Rock stratum information can be identified more accurately, and the convergence speed is high.

Description

technical field [0001] The invention belongs to the field of rock formation exploration, and relates to a logging lithology identification method based on convolutional neural network learning. Background technique [0002] Lithology is the overall reflection of the sedimentation, structure, structure and mineral combination of underground rocks. Accurate identification of lithology is of great significance for reservoir division, oil and gas layer identification and reservoir evaluation. [0003] Formation lithology identification has many methods such as field outcrop, drilling coring, seismic inversion and logging interpretation, etc. Logging interpretation is usually based on one or two empirical formulas of logging curves, by calculating mud, coal, calcite and The content of dolomite and other components can be used to identify lithology, and there are also identification methods such as cross-plot method and formation element logging, but these methods cannot fully exc...

AI Technical Summary

Problems solved by technology

[0003] Formation lithology identification has many methods such as field outcrop, drilling coring, seismic inversion and logging interpretation, etc. Logging interpretation is usually based on one or two empirical formulas of logging curves, by calculating mud, coal, calcite and The content of dolomite and other components can be used to judge lithology, and there are also identification methods such as cross-plot method and formation element logging, but these methods cannot fully excavate the lithology information in all logging curves, and have certain limitations

Secondly, there are methods such as support vector machine, random forest, and BP neural network for automatic identification of lithology in well logging curves, but these methods converge slowly, and are prone to gradient disappearance and gradient explosion, and their generalization is not very ideal.

Images