Fault Feature Knowledge Graph Construction for Geological Drilling and Its Application to Intelligent Diagnosis
-
摘要: 地质钻进工程难度大、风险高，设计可解释、可交互的钻进故障诊断系统，帮助司钻人员及时发现和排除井下故障，对保障钻进过程的安全和效率意义重大. 围绕这一目标，提出一套针对地质钻进复杂知识和故障机理的结构化表征框架，收集整理钻进故障文献库，针对文献上下文关联强、专业名词形式复杂的特点设计长程依赖关系分析和复合结构实体识别算法，抽取文献中的知识，自动构建钻进故障特征知识图谱，实现知识驱动的钻进故障智能诊断. 对21篇公开出版物进行知识抽取，构建了一个具备3 121个节点、1 301则关系的钻进故障特征知识图谱，故障诊断系统在5项钻进故障知识查询任务上性能达到ChatGPT-5.2同等水平，在2项故障诊断任务上表现优于主流商业大语言模型.Abstract: Geological drilling involves high complexity and risk, making interpretable and interactive fault diagnosis systems essential for ensuring operational safety and efficiency. This paper proposes a structured representation framework for the complex knowledge and failure mechanisms of geological drilling to enable structured representation and storage of drilling knowledge. To construct a knowledge graph for the characteristics of geological drilling faults, long-range dependency analysis and composite-structure entity recognition are developed to automatically extract professional knowledge from drilling fault literature. Based on the constructed knowledge graph, a knowledge-driven drilling fault diagnosis system is further developed.Knowledge extraction from 21 publicly available publications results in a fault feature knowledge graph containing 3 121 nodes and 1 301 relations. Experimental results demonstrate that the proposed system achieves performance comparable to ChatGPT-5.2 on five drilling fault knowledge query tasks and outperforms mainstream commercial large language models on two fault diagnosis tasks.
-
Key words:
- Geological drilling /
- Fault early warning /
- Knowledge graph /
- Large language model /
- Agent
-
图 2 面向地质钻进复杂知识结构和故障机理的钻进故障知识表征框架
Fig. 2. A knowledge framework for the complex knowledge and failure mechanisms of geological drilling
图 4 地质钻进故障特征知识图谱
Fig. 4. Knowledge graph for the characteristics of geological drilling faults
表 1 知识图谱中关系连接数量最多的5个节点
Table 1. The 5 nodes with most relationships in knowledge graph
节点名称 井漏 卡钻 井涌 钻速 神经网络 关系数量 55 51 31 26 19 属性完整度 100% 90% 100% 90% 80% 
下载: 导出CSV
表 2 本文所提方法与其他方法的问答准确率对比实验
Table 2. Comparison of question-answering accuracy in the fault diagnosis domain between the proposed method and other approaches
任务类型 序号 输入指令 所提方法 无RAG 向量库RAG ChatGPT-5.2 Deepseek-V3.2 Qwen3-Max 故障知识查询任务 1 井漏会引发什么后果？ √ √ √ √ √ √ 2 井漏和井涌的成因和现象有何区别？ √ √ √ √ √ √ 3 钻进过程中钻压和转速骤降，扭矩增加，可能发生了什么故障？ √ × × √ × × 4 发生井涌时，泵量和泥浆流量会如何变化？ √ × √ √ × √ 5 哪些井壁稳定性建模算法能够预警井壁坍塌事故？ √ × × √ × × 故障诊断任务 6 深度：……. 钻压：……. 转速：……. 根据数据判断，现在井下可能发生了什么故障？ √ × × × × × 7 泵量：……. 出口流量：……. 泥浆的泵量和出口流量出现了不平衡，可能发生了什么故障？ √ × × √ × ×
下载: 导出CSV
-
Achiam, J., Adler, S., Agarwal, S., et al., 2023. GPT-4 Technical Report. arXiv preprint arXiv: 2303.08774. https://doi.org/10.48550/arXiv.2303.08774 Chen, B. Y., Shao, H. D., Qin, Y., et al., 2025. A Domain Knowledge-Guided Industrial Large Model Framework: a Case Study in Battery Health Estimation and Recycling. IEEE Transactions on Industrial Informatics, 21(10): 8080-8090. https://doi.org/10.1109/TII.2025.3584498 Chen, D., Xiao, Y. S., Yin, Z. Y., et al., 2025. Intelligent Fault Diagnosis Method of Drilling Top Drive Based on Knowledge Graph. Natural Gas Industry, 45(2): 125-135(in Chinese with English abstract). Chen, D., Xiao, Y. S., Yin, Z. Y., et al., 2025. Intelligent Fault Diagnosis Method of Drilling Top Drive Based on Knowledge Graph. Natural Gas Industry, 45(2): 125-135(in Chinese with English abstract). He, T. T., Zhang, Q., 2024. Application Status and Development Trend of Knowledge Graph in Petroleum Exploration and Development. Natural Gas Industry, 44(9): 55-67(in Chinese with English abstract). Hu, W. K., Wang, J. D., Yang, F., et al., 2022. Analysis of Time-Varying Cause-Effect Relations Based on Qualitative Trends and Change Amplitudes. Computers & Chemical Engineering, 162: 107813. https://doi.org/10.1016/j.compchemeng.2022.107813 Li, J. Y., Fei, H., Liu, J., et al., 2022. Unified Named Entity Recognition as Word-Word Relation Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10): 10965-10973. https://doi.org/10.1609/aaai.v36i10.21344 Li, Y. P., Cao, W. H., Gopaluni, R. B., et al., 2023. False Alarm Reduction in Drilling Process Monitoring Using Virtual Sample Generation and Qualitative Trend Analysis. Control Engineering Practice, 133: 105457. https://doi.org/10.1016/j.conengprac.2023.105457 Li, Y. P., Cao, W. H., Gopaluni, R. B., et al., 2024. Drilling Process Monitoring Based on Operation Mode Recognition and Dynamic Feature Extraction. IEEE Transactions on Industrial Electronics, 71(7): 7876-7885. https://doi.org/10.1109/TIE.2023.3310010 Li, Y. P., Cao, W. H., Hu, W. K., et al., 2020. Diagnosis of Downhole Incidents for Geological Drilling Processes Using Multi-Time Scale Feature Extraction and Probabilistic Neural Networks. Process Safety and Environmental Protection, 137: 106-115. https://doi.org/10.1016/j.psep.2020.02.014 Li, Y. P., Cao, W. H., Hu, W. K., et al., 2021. Incipient Fault Detection for Geological Drilling Processes Using Multivariate Generalized Gaussian Distributions and Kullback-Leibler Divergence. Control Engineering Practice, 117: 104937. https://doi.org/10.1016/j.conengprac.2021.104937 Lian, Z., Zhou, Z. J., Hu, C. H., et al., 2025. Transparent Fault Diagnosis for Complex Equipment Considering Expert Reliability Based on Belief Rule Base and Linguistic Z-Number. IEEE Transactions on Automation Science and Engineering, 22: 3887-3900. https://doi.org/10.1109/TASE.2024.3402099 Liu, P. F., Qian, L., Zhao, X. W., et al., 2024a. Joint Knowledge Graph and Large Language Model for Fault Diagnosis and Its Application in Aviation Assembly. IEEE Transactions on Industrial Informatics, 20(6): 8160-8169. https://doi.org/10.1109/TII.2024.3366977 Liu, A., Feng, B., Xue, B., et al., 2024b. Deepseek-v3 Technical Report. arXiv preprint arXiv: 2412.19437. https://doi.org/10.48550/arXiv.2412.19437 Lu, C. D., Gan, C., Chen, L. F., et al., 2023. Development and Prospect of Intelligent Control of Geological Drilling Process. Coal Geology & Exploration, 51(9): 31-43(in Chinese with English abstract). Lü, Q. T., Yan, J. Y., Chen, X. H., et al., 2020. Progress of Deep Geological Survey Project under the China Geological Survey. China Geology, 3(1): 153-172. https://doi.org/10.31035/cg2020001 Shi, L. Y., Zuo, R. G., 2026. Foundation Model for Mineral Prospectivity Mapping. Earth Science, 51(3): 832-848(in Chinese with English abstract). Wang, H., Li, C. X., Li, Y. F., 2024. Large-Scale Visual Language Model Boosted by Contrast Domain Adaptation for Intelligent Industrial Visual Monitoring. IEEE Transactions on Industrial Informatics, 20(12): 14114-14123. https://doi.org/10.1109/TII.2024.3441638 Wang, Y. C., Yu, B. W., Zhu, H. S., et al., 2021. Discontinuous Named Entity Recognition as Maximal Clique Discovery. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Online Association for Computational Linguistics: 764-774. 10.18653/v1/2021.acl-long.63 Wu, R. Z., Li, H., Mei, H. B., et al., 2025. A Landslide Monitoring and Early Warning System with Retrieval-Augmented Generation Enhanced by Knowledge Graph. Earth Science, 50(10): 4125-4136(in Chinese with English abstract). Xi, Z. H., Chen, W. X., Guo, X., et al., 2025. The Rise and Potential of Large Language Model Based Agents: a Survey. Science China Information Sciences, 68(2): 121101. https://doi.org/10.1007/s11432-024-4222-0 Xu, J., Wen, J., Sun, X., et al., 2017a. A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text. arXiv preprint arXiv: 1711.07010. https://doi.org/10.48550/arXiv.1711.07010 .Xu, X. J., Yan, X. P., Sheng, C. X., et al., 2017b. A Belief Rule-Based Expert System for Fault Diagnosis of Marine Diesel Engines. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 50(2): 656-672. https://doi.org/10.1109/TSMC.2017.2759026 Yang, A., Li, A. F., Yang, B. S., et al., 2025a. Qwen3 Technical Report. arXiv preprint arXiv: 2505.09388. https://doi.org/10.48550/arXiv.2505.09388 Yang, Y. L., Cao, W. H., Gan, C., et al., 2024. Advances in Research on Stratigraphic Characteristic Parameter Modeling and Safety Early Warning for Deep Geological Drilling Processes. Coal Geology & Exploration, 52(10): 195-206(in Chinese with English abstract). Yang, Y. L., Cao, W. H., Li, Y. P., et al., 2025b. OD-Mind: an Ocean Drilling Expert Knowledge Query System Driven by Knowledge Graph. Ocean Engineering, 339: 122135. https://doi.org/10.1016/j.oceaneng.2025.122135 Zhang, Z., Lai, X. Z., Du, S., et al., 2023. Early Warning of Loss and Kick for Drilling Process Based on Sparse Autoencoder with Multivariate Time Series. IEEE Transactions on Industrial Informatics, 19(11): 11019-11029. https://doi.org/10.1109/TII.2023.3242772 Zhao, J. C., Yue, J. Q., Zhao, C. H., et al., 2025. Adjust to Reality: LLM-Driven Test-Time Semantic Adjustment for Zero-Shot Fault Diagnosis. Control Engineering Practice, 164: 106406. https://doi.org/10.1016/j.conengprac.2025.106406 陈冬, 肖远山, 尹志勇, 等, 2025. 基于知识图谱的钻井顶部驱动装置故障智能诊断方法. 天然气工业, 45(2): 125-135. 和婷婷, 张强, 2024. 知识图谱在油气勘探开发中的应用现状与发展趋势. 天然气工业, 44(9): 55-67. 陆承达, 甘超, 陈略峰, 等, 2023. 地质钻进过程智能控制研究进展与发展前景. 煤田地质与勘探, 51(9): 31-43. 师路易, 左仁广, 2026. 矿产预测大模型. 地球科学, 51(3): 832-848. doi: 10.3799/dqkx.2025.190 吴润泽, 李浩, 梅红波, 等, 2025. 基于知识图谱检索增强生成的滑坡监测预警系统. 地球科学, 50(10): 4125-4136 doi: 10.3799/dqkx.2025.127 杨豫龙, 曹卫华, 甘超, 等, 2024. 深部地质钻进过程地层特征参数建模与安全预警研究进展. 煤田地质与勘探, 52(10): 195-206. -
点击查看大图
图(5) / 表(2)
计量
- 文章访问数: 185
- HTML全文浏览量: 31
- PDF下载量: 25
- 被引次数: 0
