基于时频联合分析的陆相页岩油储层岩相识别方法及系统

By employing a joint time-frequency analysis method, improving the isolated forest algorithm and dynamic window Lagrange interpolation method to handle outliers, and combining TFAA-TCN and Mamba-MHSA neural networks, the problems of insufficient time-frequency feature extraction and adaptability in lithofacies identification of continental shale oil reservoirs are solved, achieving high-precision lithofacies identification and adaptive enhancement.

CN120652572BActive Publication Date: 2026-07-17NORTHEAST GASOLINEEUM UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NORTHEAST GASOLINEEUM UNIV
Filing Date
2025-06-14
Publication Date
2026-07-17

Smart Images

  • Figure CN120652572B_ABST
    Figure CN120652572B_ABST
Patent Text Reader

Abstract

本发明涉及的是于时频联合分析的陆相页岩油储层岩相识别方法及系统，其中基于时频联合分析的陆相页岩油储层岩相识别方法包括如下步骤；基于混合方法构建的数据集预处理模型，构建带标签的测井数据集；基于TFAA‑TCN的测井曲线数据自适应融合模型，全面捕捉岩相变化的多尺度特征；基于Mamba‑MHSA的测井曲线时频信息提取模型，通过Mamba长期依赖关系捕捉和多头注意力机制MHSA特征筛选相结合，挖掘测井曲线的空间信息的长期依赖关系和不同特征之间的注意力权重，对陆相页岩油储层岩相识别。本发明有效地提升陆相页岩油储层岩相识别的准确性，优化测井曲线特征的提取和融合方式，并增强了对复杂储层环境的自适应能力。
Need to check novelty before this filing date? Find Prior Art