Intelligent ultra-deep gas well tubular column leakage identification method based on time sequence data and time-frequency fusion BiLSTM model

By constructing a time-series data and time-frequency fusion BiLSTM model and combining it with a multi-module deep learning method, the problem of identifying leaks in ultra-deep gas well tubing was solved, achieving high-precision identification of leak location and size, especially accurate detection of small-sized leaks.

CN121997035AActive Publication Date: 2026-05-08CHINA UNIV OF PETROLEUM (EAST CHINA)
6 Cites 3 Cited by

Patent Information

Application Number
CN202610466400.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-10
Publication Date
2026-05-08
Estimated Expiration
2046-04-10

AI Technical Summary

Technical Problem

Existing technologies struggle to efficiently identify the location and size of leaks in production tubing in ultra-deep gas wells, especially small-sized leaks. Furthermore, existing models cannot fully capture transient and full-process leak characteristics, leading to difficulties in quantitative identification.

Method used

We employ a method based on time-series data and time-frequency fusion BiLSTM model, combining multi-scale CNN, fast Fourier transform (FFT), bidirectional long short-term memory network (BiLSTM), adaptive multi-head attention mechanism (AMA) and gated information fusion architecture (GRN) to construct a composite deep learning model. We then use this multi-module fusion integrated deep learning model to identify leaks.

Benefits of technology

It achieves high-precision identification of leak location and size, especially sub-millimeter level detection accuracy for small and medium-sized leaks, and has good robustness and generalization ability, adapting to complex actual production environments.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to an ultra-deep gas well tubular column leakage intelligent identification method based on time series data and a time-frequency fusion BiLSTM model, and belongs to the technical field of petroleum engineering, and the method comprises the steps: 1, obtaining model input physical characteristics, and constructing an experiment data set; 2, constructing and training a multi-module fusion integrated deep learning model; and step 3, intelligent identification of ultra-deep gas well tubular column leakage is carried out through the trained multi-module fusion integrated deep learning model. According to the method, the input physical characteristics can be efficiently learned, and high-precision regression prediction is realized for leakage position and size tasks.
Need to check novelty before this filing date? Find Prior Art