A lithology identification method and system based on measured analog drilling feature unification

By constructing and processing a simulated drilling dataset, combining a one-dimensional convolutional neural network and a bidirectional long short-term memory network, and using an adversarial training mechanism to eliminate data distribution differences, high accuracy and robustness of lithology identification were achieved, solving the time-consuming and labor-intensive problem of lithology identification in tunnel construction.

CN122174028BActive Publication Date: 2026-07-24SHANDONG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHANDONG UNIV
Filing Date
2026-05-12
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing lithology identification methods are time-consuming, labor-intensive, and costly in tunnel construction. Machine learning models rely on a large number of field samples for training, but their accuracy is low in small sample scenarios. Simulated data and measured data are difficult to mix directly to improve model performance.

Method used

By constructing field datasets and simulated datasets, physical features are derived and preprocessed. One-dimensional convolutional neural networks and bidirectional long short-term memory networks are combined to extract drilling data features. Adversarial training and gradient inversion mechanisms are used to eliminate the distribution differences between simulated data and measured data, thereby achieving feature unification.

Benefits of technology

High accuracy and robustness of lithology identification were achieved with limited field data, overcoming the bottleneck of traditional methods that rely on large amounts of field-labeled data, and improving the model's adaptability and generalization ability in real engineering scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122174028B_ABST
    Figure CN122174028B_ABST
Patent Text Reader

Abstract

The application provides a lithology identification method and system based on unified drilling characteristics of measured simulation, which comprises deriving physical characteristics of drilling parameters in pretreated field data sets and simulation data sets, and splicing derivative physical quantities and basic drilling parameters; performing two-stage feature extraction on the newly spliced field data sets and simulation data sets to obtain hidden features; inputting the hidden features into a label classifier and a domain discriminator to calculate classification loss and adversarial loss respectively; training and performance verifying the model by using back propagation and an optimizer based on the classification loss and the adversarial loss; performing unified drilling characteristics of measurement and simulation based on the model verified in performance to obtain common characteristics; and identifying the lithology of unexcavated sections by using drilling parameters. The application eliminates the distribution difference between simulation drilling data and measured drilling data, and can realize accurate identification of lithology under the condition of less field sample quantity.
Need to check novelty before this filing date? Find Prior Art