1 Chongqing Gas Mine of Southwest Oil and Gas Field Branch of PetroChina, Chongqing 400021, China
2 College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, China
Show less
文章历史+
Received
Published
Revised
2025-06-11
2026-04-28
2025-11-19
Online Date
2026-05-29
PDF (9211K)
摘要
管道与阀室压力的联合预测和实时预警是保障天然气管网输送系统安全高效运行的关键环节。传统的物理建模难以捕捉非线性、非平稳的动态压力特征,现有数据驱动方法对管道与阀室之间复杂的时空耦合关系建模不足。针对上述问题,基于真实作业数据提出一种动态卷积神经网络-双向长短时记忆网络(dynamic convolutional neural network-bidirectional long short-term memory,DCNN-BiLSTM)的压力预测方法:动态卷积能够根据输入数据的波动自适应调整卷积核权重,从而增强对非平稳和局部动态特征的提取能力;双向长短时记忆网络则通过捕捉双向时间依赖结构,提高对复杂时序规律的建模精度。该方法在压力预测任务中取得了决定系数R2为0.998、均方根误差为8.632×10-3的优异性能,优于其他主流对比模型。基于此,设计了一种动态预警机制,利用工况数据自适应更新阈值,实现98.23%的异常识别准确率。所设计开发的压力预测预警系统已部署于真实作业场景,能够有效提升天然气输送系统的智能化监测与安全预警能力,具有广泛的工程应用价值与现实意义。
Abstract
Joint prediction and real-time warning of pipeline and valve-chamber pressures are essential for the safe and efficient operation of natural gas transmission systems. Traditional physical modeling has difficulty capturing the nonlinear and nonstationary characteristics of pressure dynamics, and existing data-driven approaches are often limited in modeling the complex spatiotemporal coupling between pipelines and valve chambers. To address these issues, a dynamic convolutional bidirectional long short-term memory (DCNN-BiLSTM) method was proposed for pressure prediction based on real operational data. The DCNN component adapted convolutional kernel weights to input fluctuations, improving the extraction of nonstationary and local dynamic features, while the BiLSTM component models bidirectional temporal dependencied to better represent time-series patterns. The method achieves an coefficient of determination R2 of 0.998 and an root mean square error of 8.632×10-3 on the pressure prediction task, performing favorably compared with several commonly used baseline models. Building on this, a dynamic warning mechanism was designed to adaptively update pressure thresholds using operational data, achieving an anomaly detection accuracy of 98.23%. The developed pressure prediction and early-warning system has been deployed in real operational environments, contributing to improved intelligent monitoring and safety management in natural gas transmission systems.
WU Qian-ying, SONG Lin-long, HU Chang-quan, ZHANG Yi-li, YE Fu-ming, YIN Ai-jun.
DCNN-BiLSTM-driven Integrated Pressure Prediction and Anomaly Detection for Natural Gas Pipeline Networks[J].
Science Technology and Engineering, 2026, 26(12): 5063-5071 DOI:10.12404/j.issn.1671-1815.2504372
现有管网监测方式多样化,从监测方式可划分为基于管道外部和基于管道内部的监测方法[4]。外部监测方法包括声学传感器[5]、光纤传感器[6]等,以探测管道异常变化实现异常报警。内部监测方法通过监测管道压力[7]、流量[8]等运行参数的实时变化实现安全预警。其中,压力等内部监测方法因不易受外界环境干扰,依托现有数据采集与监视控制系统(supervisory control and data acquisition,SCADA)系统,部署成本低,及迅速、稳定的监测效果成为主要研究方向。
LiYuan. Development status and prospect analysis of natural gas chemical industry in China[J]. Low-Carbon Chemistry and Chemical Engineering, 2024, 49(1): 105-112.
ZhouDake, YangJia, LiuWei, et al. Planning and layout method of China's medium-and long-term natural gas trunk pipeline network[J]. Oil & Gas Storage and Transportation, 2025, 44(3): 301-310.
[5]
JiangW, LiZ, YuanQ, et al. Robust pressure prediction of oil and gas pipeline networks based on equipment embedding neural network[J]. Physics of Fluids, 2024, 36(4): 043104.
[6]
KorlapatiN, KhanF, NoorQ, et al. Review and analysis of pipeline leak detection methods[J]. Journal of Pipeline Science and Engineering, 2022, 2(4): 100074.
ZhangMei, ZhangShuangshuang, YuanHongyong, et al. Research on infrasonic source localization algorithm for gas pipeline leakage[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(3): 187-194.
GaoWenao, LiuYang, LiDengke, et al. Study on gas pipeline leakage based on optical fiber monitoring technology[J]. China Safety Science Journal, 2019, 29(8): 67-72.
[11]
LiuC, LiY, FangL, et al. Leakage monitoring research and design for natural gas pipelines based on dynamic pressure waves[J]. Journal of Process Control, 2017, 50: 66-76.
[12]
KimJ, ChaeM, HanJ, et al. The development of leak detection model in subsea gas pipeline using machine learning[J]. Journal of Natural Gas Science and Engineering, 2021, 94: 104134.
[13]
ZhouH, LiP, WuL. Research on a model-based burst pressure prediction method for pipelines with corrosion defects[J]. Journal of Mechanics, 2022, 38: 315-322.
[14]
LiangJ, LiangS, MaL, et al. Leak detection for natural gas gathering pipeline using spatio-temporal fusion of practical operation data[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108360.
[15]
AdenubiS, AppahD, OkaforE, et al. A review of leak detection systems for natural gas pipelines and facilities[J]. International Journal of Energy Technology and Policy, 2023, 13: 9-19.
[16]
GongF, ZhaoX, DuC, et al. Pressure and temperature prediction of oil pipeline networks based on a mechanism-data hybrid driven method[J]. Information, 2024, 15(11): 709.
[17]
YusufA, HasmawatiH, IhsanA. Comparison of KNN and LSTM on the prediction of the operational conditions of natural gas pipeline transmission networks[J]. JIPI (Jurnal Ilmiah Penelitiandan Pembelajaran Informatika), 2024, 9(2): 476-486.
[18]
CuiZ, KeR, PuZ, et al. Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide tra-ffic state with missing values[J]. Transportation Research Part C: Emerging Technologies, 2020, 118: 102674.
[19]
SunZ, LiuZ, ZhangC, et al. Dynamic spatio-temporal adaptive convolutional neural networks for traffic flow prediction[C]//Proceedings of the 2024 IEEE 27th International Conference on Inte-lligent Transportation Systems (ITSC). Edmonton, AB: IEEE, 2024: 945-951.
FuGuozhong, DuHua, ZhangZhiqiang, et al. Remaining useful life prediction of rolling bearing based on attention mechanism and CNN-BiLSTM model[J]. Nuclear Power Engineering, 2023, 44(S2): 33-38.
WangKongxian, ShaoYing, WangLiming. Noise reduction of single-phase grounding fault current based on improved variational mode decomposition and wavelet threshold method[J]. Science Technology and Engineering, 2023, 23(29): 12556-12566.
[26]
VilimekD, KubicekJ, GolianM, et al. Comparative analysis of wavelet transform filtering systems for noise reduction in ultrasound images[J]. PLoS One, 2022, 17(7): e0270745.