Intelligent Monitoring Model for Lost Circulation Based on Unsupervised Time Series Autoencoder

被引:0
|
作者
Wu, Liwei [1 ,2 ]
Wang, Xiaopeng [1 ,2 ]
Zhang, Ziyue [3 ]
Zhu, Guowei [1 ,2 ]
Zhang, Qilong [1 ,2 ]
Dong, Pinghua [1 ,2 ]
Wang, Jiangtao [4 ]
Zhu, Zhaopeng [3 ]
机构
[1] State Key Lab Offshore Oil & Gas Exploitat, Beijing 102209, Peoples R China
[2] CNOOC China Ltd, Tianjin Branch, Tianjin 300459, Peoples R China
[3] China Univ Petr, Sch Petr Engn, Beijing 102249, Peoples R China
[4] China France Bohai Geoserv Co Ltd, Tianjin 300456, Peoples R China
基金
中国国家自然科学基金; 美国国家科学基金会;
关键词
lost circulation monitoring; unsupervised; time series autoencoder; BiLSTM-AE;
D O I
10.3390/pr12071297
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Lost circulation, a common risk during the drilling process, significantly impacts drilling safety and efficiency. The presence of data noise and temporal evolution characteristics pose significant challenges to the accurate monitoring of lost circulation. Traditional supervised intelligent monitoring methods rely on large amounts of labeled data, which often do not consider temporal fluctuations in data, leading to insufficient accuracy and transferability. To address these issues, this paper proposes an unsupervised time series autoencoder (BiLSTM-AE) intelligent monitoring model for lost circulation, aiming to overcome the limitations of supervised algorithms. The BiLSTM-AE model employs BiLSTM for both the encoder and decoder, enabling it to comprehensively capture the temporal features and dynamic changes in the data. It learns the patterns of normal data sequences, thereby automatically identifying anomalous risk data points that deviate from the normal patterns during testing. Results show that the proposed model can efficiently identify and monitor lost circulation risks, achieving an accuracy of 92.51%, a missed alarm rate of 6.87%, and a false alarm rate of 7.71% on the test set. Compared to other models, the BiLSTM-AE model has higher accuracy and better timeliness, which is of great significance for improving drilling efficiency and ensuring drilling safety.
引用
收藏
页数:15
相关论文
共 50 条
  • [21] Condition Monitoring with Time Series Data Based on Probabilistic Model
    Soh, Jaehyun
    Kim, DaeEun
    2021 24TH INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS (ICEMS 2021), 2021, : 2630 - 2634
  • [22] Unsupervised Satellite Image Time Series Clustering Using Object-Based Approaches and 3D Convolutional Autoencoder
    Kalinicheva, Ekaterina
    Sublime, Jeremie
    Trocan, Maria
    REMOTE SENSING, 2020, 12 (11)
  • [23] Unsupervised feature learning for online voltage stability evaluation and monitoring based on variational autoencoder
    Yang, Haosen
    Qiu, Robert C.
    Shi, Xin
    He, Xing
    ELECTRIC POWER SYSTEMS RESEARCH, 2020, 182
  • [24] An autoencoder-based model for forest disturbance detection using Landsat time series data
    Zhou, Gaoxiang
    Liu, Ming
    Liu, Xiangnan
    INTERNATIONAL JOURNAL OF DIGITAL EARTH, 2021, 14 (09) : 1087 - 1102
  • [25] Diverse Relevance Feedback for Time Series with Autoencoder Based Summarizations
    Eravci, Bahaeddin
    Ferhatosmanoglu, Hakan
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2018, 30 (12) : 2298 - 2311
  • [26] Time series prediction method based on Convolutional Autoencoder and LSTM
    Zhao, Xia
    Han, Xiao
    Su, Weijun
    Yan, Zhen
    2019 CHINESE AUTOMATION CONGRESS (CAC2019), 2019, : 5790 - 5793
  • [27] Analysis of massive unsupervised text sentiment based on rough set time series model
    Du Baochen
    PROCEEDINGS OF THE 2017 2ND INTERNATIONAL CONFERENCE ON AUTOMATION, MECHANICAL CONTROL AND COMPUTATIONAL ENGINEERING (AMCCE 2017), 2017, 118 : 910 - 914
  • [28] Time Series Forecasting Based on Structured Decomposition and Variational Autoencoder
    Zhang, Zhiyuan (zyzhangcauc@163.com), 1600, Institute of Electrical and Electronics Engineers Inc.
  • [29] Unsupervised diffusion based anomaly detection for time series
    Zuo, Haiwei
    Zhu, Aiqun
    Zhu, Yanping
    Liao, Yinping
    Li, Shiman
    Chen, Yun
    APPLIED INTELLIGENCE, 2024, 54 (19) : 8968 - 8981
  • [30] Vector Quantized Variational Autoencoder-Based Compressive Sampling Method for Time Series in Structural Health Monitoring
    Liang, Ge
    Ji, Zhenglin
    Zhong, Qunhong
    Huang, Yong
    Han, Kun
    SUSTAINABILITY, 2023, 15 (20)