A drilling speed modeling method based on improved bat algorithm and support vector regression

By combining the improved bat algorithm with support vector regression, abnormal data is identified and replaced, and hyperparameters are optimized. This solves the problem of nonlinearity and high-dimensional variation in drilling rate models in deep geological drilling, and achieves high-precision drilling rate prediction and parameter guidance.

CN119808550BActive Publication Date: 2026-06-05CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA UNIV OF GEOSCIENCES (WUHAN)
Filing Date
2024-12-18
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

In deep geological drilling, the complex rock mechanics environment leads to nonlinear and high-dimensional variations in the drilling process, making it difficult to construct a high-precision drilling rate model and affecting the effective guidance of the drilling process.

Method used

An improved bat algorithm and support vector regression method are used to construct a drilling rate prediction model by identifying and replacing abnormal data. The improved bat algorithm with partial population update, iterative search and chaotic perturbation mechanism is designed to optimize hyperparameters and improve model accuracy.

Benefits of technology

It effectively eliminates abnormal drilling data, improves the accuracy and reliability of the drilling rate model, and provides effective guidance for subsequent drilling processes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119808550B_ABST
    Figure CN119808550B_ABST
Patent Text Reader

Abstract

The present application relates to the field of geological exploration, especially to a drilling speed modeling method based on improved bat algorithm and support vector regression. The method first identifies and corrects abnormal data according to the interval anomaly detection method. Then, the support vector regression method is used to build a drilling speed model. Finally, an improved bat algorithm is designed to determine the optimal parameter value of the drilling speed model. The drilling speed modeling method described in the present application can effectively eliminate abnormal drilling data and ensure drilling characteristics, while building a high-precision drilling speed model to accurately predict drilling speed and provide a reliable basis for drilling operation and adjustment.
Need to check novelty before this filing date? Find Prior Art