Dynamic Flow Field Prediction Method for Compressed Air Storage Tanks Using Dynamic Mode Decomposition and Long Short-Term Memory Network

SU Hao; WANG Tongsheng; ZOU Hansen; YU Keyu; XI Guang; YAO Erren

doi:10.7652/xjtuxb202603011

您当前的位置：

首页 >

文章列表页 >

Dynamic Flow Field Prediction Method for Compressed Air Storage Tanks Using Dynamic Mode Decomposition and Long Short-Term Memory Network

更新时间：2026-03-09

- Dynamic Flow Field Prediction Method for Compressed Air Storage Tanks Using Dynamic Mode Decomposition and Long Short-Term Memory Network
- Journal of Xi'an Jiaotong University Vol. 60, Issue 3, Pages: 110-121(2026)
- 作者机构：
  
  西安交通大学能源与动力工程学院，710049，西安
  西安交通大学未来技术学院，710049，西安
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202603011
  CLC： TK02
- Received：14 May 2025，
  
  Published：10 March 2026
- 稿件说明：
移动端阅览
SU Hao, WANG Tongsheng, ZOU Hansen, et al. Dynamic Flow Field Prediction Method for Compressed Air Storage Tanks Using Dynamic Mode Decomposition and Long Short-Term Memory Network[J]. Journal of Xi'an Jiaotong University, 2026, 60(3): 110-121.
DOI：

SU Hao, WANG Tongsheng, ZOU Hansen, et al. Dynamic Flow Field Prediction Method for Compressed Air Storage Tanks Using Dynamic Mode Decomposition and Long Short-Term Memory Network[J]. Journal of Xi'an Jiaotong University, 2026, 60(3): 110-121. DOI： 10.7652/xjtuxb202603011.

摘要

针对压缩空气储能系统储气装置内运行参量瞬态演化特性难以快速精准预测的问题，提出了一种基于动力学模态分解和长短期记忆神经网络的流场降阶预测模型，实现了储气装置内复杂非线性流场时空演化特征的解耦建模，建立了储气装置内全局运行参量精准表征与快速流场预测方法。采用动力学模态分解对储气装置内工质合速度、温度和压力等关键物理量的时空全阶数据集解耦降阶，实现表征流场演化特征主导模态的准确提取；通过构建长短期记忆神经网络模型预测低维动力系统的时序演化特性，重构高维时空流场并实现流场全阶参数的动态精准预测。实验结果表明，储气装置压力场预测的平均相对误差为0.05%，速度场预测的平均相对误差为0.19%，体积分数场预测的平均相对误差为0.83%，模型在保证预测精度的同时计算成本降低4个数量级。该方法可实现压缩空气储能系统储气装置内流场的高精度实时预测，在确保预测精度的同时显著提升了计算效率，为实现系统全工况灵活高效调控提供了参考。

Abstract

To address the challenge of rapidly and accurately predicting the transient evolution of operational parameters in within the air storage tanks of compressed air energy storage (CAES) systems

this study proposes a reduced-order flow field prediction model based on dynamic mode decomposition (DMD)and long short-term memory (LSTM)network.This model achieves decoupled modeling of the spatiotemporal evolution features of the complex nonlinear flow fields inside storage tanks and establishes a method for accurate global parameter characterization and rapid flow field prediction.DMD decouples and reduces the full-order spatiotemporal datasets of key physical quantities (e.g.

velocity

temperature

and pressure)within the storage tanks

enabling accurate extraction of dominant modes governing flow field evolution.An LSTM network model is then constructed to predict the temporal evolution characteristics of the low-dimensional dynamical system

reconstruct high-dimensional spatiotemporal flow fields

and achieve dynamic and precise prediction of full-order flow parameters.The experimental results demonstrate that the average relative errors for pressure field prediction is 0.05%

0.19% for the velocity field

and 0.83% for the volume fraction field.The model reduces computational cost by four orders of magnitude while maintaining prediction accuracy.This method enables high-precision real-time flow field prediction for the air storage tanks of CAES systems

significantly improving computational efficiency without sacrificing prediction accuracy

and provides valuable insights for flexible and efficient regulation of such systems under all operating conditions.

关键词

Keywords

references

YAO Erren, ZHONG Like, ZHANG Shuqi, et al. Off-design performance evaluation of a combined heating and power system based on compressed air and thermochemical energy storage under optimized operation strategy[J].Journal of Energy Storage, 2025, 130：117485.

郭丁彰，尹钊，周学志，等.压缩空气储能系统储气装置研究现状与发展趋势[J].储能科学与技术，2021，10(5)：1486-1493.

GUO Dingzhang，YIN Zhao，ZHOU Xuezhi，et al. Status and prospect of gas storage device in compressed air energy storage system[J].Energy Storage Science and Technology，2021，10(5)：1486-1493.

GHANBARZADEH T, HABIBI D, AZIZ A.Addressing reliability challenges in generation capacity planning under high penetration of renewable energy resources and storage solutions：a review[J].Renewable and Sustainable Energy Reviews, 2025, 212：115461.

姚尔人，仲理科，邹瀚森，等.压缩空气与热化学复合储能系统反应器动态性能研究[J].西安交通大学学报，2024，58(2)：1-11.

YAO Erren，ZHONG Like，ZOU Hansen，et al. Dynamic thermodynamic performance study of the reactor within the combined compressed air and thermochemical energy storage system[J].Journal of Xi’an Jiaotong University，2024，58(2)：1-11.

KUSHNIR R, DAYAN A, ULLMANN A.Temperature and pressure variations within compressed air energy storage caverns[J].International Journal of Heat and Mass Transfer, 2012, 55(21/22)：5616-5630.

ZHOU Shuwei, XIA Caichu, DU Shigui, et al. An analytical solution for mechanical responses induced by temperature and air pressure in a lined rock cavern for underground compressed air energy storage[J].Rock Mechanics and Rock Engineering, 2015, 48 (2 )：749-770.

RAJU M, KUMAR KHAITAN S.Modeling and simulation of compressed air storage in caverns：a case study of the Huntorf plant[J].Applied Energy, 2012, 89(1)：474-481 .

蒋中明，廖峻慧，肖喆臻，等.压缩空气储能地下储气库热力学改进模型研究[J].长沙理工大学学报（自然科学版），2024，21（2）：32-41 .

JIANG Zhongming，LIAO Junhui，XIAO Zhezhen，et al. Study on improved model for the thermodynamics of compressed air energy storage underground cavern[J]. Journal of Changsha University of Science & Technology（Natural Science），2024，21（2）：32-41.

蒋中明，郭菁，唐栋.压气储能地下储气库压缩湿空气热力学模型[J].储能科学与技术，2021，10(2)：638-646 .

JIANG Zhongming，GUO Jing，TANG Dong.A thermodynamic model of compressed humid air within an underground rock cavern for compressed air energy storage[J].Energy Storage Science and Technology，2021，10(2)：638-646.

YANG Chunhe, WANG Tongtao.Deep underground energy storage：aiming for carbon neutrality and its challenges[J].Engineering, 2023, 29(10)：11-14.

惠心雨，袁泽龙，白俊强，等.基于深度学习的非定常周期性流动预测方法[J].空气动力学学报，2019，37(3)：462-469.

HUI Xinyu，YUAN Zelong，BAI Junqiang，et al. A method of unsteady periodic flow field prediction based on the deep learning[J].Acta Aerodynamica Sinica，2019，37(3)：462-469.

袁晓明，刘存飞，肖浩阳，等.基于降阶预测模型的自激振荡消防喷嘴流场预测[J/OL].机械工程学报.

(2025-04-09)[2025-04-16].https：//link.cnki.net/urlid/11.2187.TH.20250409.1406.040. YUAN Xiaoming，LIU Cunfei，XIAO Haoyang，et al. Self-oscillating fire nozzle flow field prediction based on reduced order prediction model[J/OL].Journal of Mechanical Engineering.(2025-04-09)[2025-04-16]. https：//link.cnki.net/urlid/11.2187.TH.20250409. 1406 .040.

舒航，钟文琪，陈曦，等.基于POD和TFM的气固流化床流场压力分布预测研究[J].工程热物理学报，2024，45(11)：3391-3397.

SHU Hang，ZHONG Wenqi，CHEN Xi，et al. Predictive study of pressure distribution in gas-solid fluidized bed flow field based on POD and TFM[J].Journal of Engineering Thermophysics，2024，45 (11 )：3391-3397.

沙杨扬.基于模态分解方法的串列双圆柱绕流流场特性分析[D].哈尔滨：哈尔滨工业大学，2021 .

LI Dandan, ZHAO Bidan, LU Shuai, et al. A datadriven method for fast predicting the long-term hydrodynamics of gas-solid flows：optimized dynamic mode decomposition with control[J].Physics of Fluids, 2024, 36(10)：103332.

邵昱昌，王彤.基于动态模式分解的离心压缩机动态流场分析[J].热能动力工程，2018，33(5)：55-62.

SHAO Yuchang，WANG Tong.Dynamic flow field analysis of centrifugal compressor based on DMD[J]. Journal of Engineering for Thermal Energy and Power，2018，33(5)：55-62.

PAN Shaowu, ARNOLD-MEDABALIMI N, DURAISAMY K.Sparsity-promoting algorithms for the discovery of informative Koopman-invariant subspaces[J]. Journal of Fluid Mechanics, 2021, 917：A18.

杨丽，吴雨茜，王俊丽，等.循环神经网络研究综述[J].计算机应用，2018，38(S2)：1-6.

YANG Li，WU Yuqian，WANG Junli，et al. Research on recurrent neural network[J].Journal of Computer Applications，2018，38(S2)：1-6.

JIA Xuyi, GONG Chunlin, JI Wen, et al. An accuracy-enhanced transonic flow prediction method fusing deep learning and a reduced-order model[J].Physics of Fluids, 2024, 36(5)：056101.

VLACHAS P R, BYEON W, WAN Z H, et al. Data driven forecasting of high-dimensional chaotic systems with long short-term memory networks[J].Proceedings of the Royal Society：A Mathematical, Physical and Engineering Sciences, 2018, 474 (2213 )：20170844.

ROWLEY C W, DAWSON S T M.Model reduction for flow analysis and control[J].Annual Review of Fluid Mechanics, 2017, 49：387-417.

TOWNE A, SCHMIDT O T, COLONIUS T.Spectral proper orthogonal decomposition and its relationship to dynamic mode decomposition and resolvent analysis[J].Journal of Fluid Mechanics, 2018, 847：821-867.

郭子漪，赵建福，李凯，等.基于POD-Galerkin降维方法的热毛细对流分岔分析[J].力学学报，2022，54 (5)：1186-1198.

GUO Ziyi，ZHAO Jianfu，LI Kai，et al. Bifurcation analysis of thermocapillary convection based on PODGalerkin reduced-order method[J].Chinese Journal of Theoretical and Applied Mechanics，2022，54 (5 )：1186-1198.

寇家庆，张伟伟.动力学模态分解及其在流体力学中的应用[J].空气动力学学报，2018，36(2)：163-179.

KOU Jiaqing，ZHANG Weiwei.Dynamic mode decomposition and its applications in fluid dynamics[J]. Acta Aerodynamica Sinica，2018，36(2)：163-179.

张驰，郭媛，黎明.人工神经网络模型发展及应用综述[J].计算机工程与应用，2021，57(11)：57-69.

ZHANG Chi，GUO Yuan，LI Ming.Review of development and application of artificial neural network models[J].Computer Engineering and Applications，2021，57(11)：57-69.

杨志刚，李俣静，夏超，等.基于LSTM-POD的汽车湍流尾迹的高时间分辨速度场重构[J].汽车工程，2024，46(7)：1302-1313.

YANG Zhigang，LI Yujing，XIA Chao，et al. A high time-resolution reconstruction on the automotive turbulent wake based onLSTM-POD[J].Automotive Engineering，2024，46(7)：1302-1313.

孔德天，董义道，张来平，等.基于混合神经网络的非定常流场预测方法[J].四川大学学报（自然科学版），2024，61（6）：135-143.

KONG Detian，DONG Yidao，ZHANG Laiping，et al. An unsteady flow-field prediction method based on hybrid neural network[J].Journal of Sichuan University（Natural Science Edition），2024，61（6）：135-143.

YU Yong, SI Xiaosheng, HU Changhua, et al. A review of recurrent neural networks：LSTM cells and network architectures[J].Neural Computation, 2019, 31(7)：1235-1270.

HUANG Zhiwen, LI Tong, HUANG Kexin, et al. Predictions of flow and temperature fields in a T-junction based on dynamic mode decomposition and deep learning[J].Energy, 2022, 261(Part A)：125228.

任甲辉，李嘉成，樊昱豪，等.高压气动减压阀内部湿空气凝结特性[J].液压与气动，2024，48(10)：7584 .

REN Jiahui，LI Jiacheng，FAN Yuhao，et al. Condensation characteristics of wet air within high pressure pneumatic pressure-reducing valve[J].Chinese Hydraulics & Pneumatics，2024，48(10)：75-84.

WANG Zhikai, GONG Ka, FAN Wei, et al. Prediction of swirling flow field in combustor based on deep learning[J].Acta Astronautica, 2022, 201：302-316.

武书弘，邹瀚森，姚尔人，等.压缩空气储能储气装置充气过程的动态热力特性研究[J].西安交通大学学报，2025，59(2)：41-49.

WU Shuhong，ZOU Hansen，YAO Erren，et al. Thermodynamic characteristics of air storage device during charging process[J].Journal of Xi’an Jiaotong University，2025，59(2)：41-49.

GUO Cong, XU Yujie, ZHANG Xinjing, et al. Performance analysis of compressed air energy storage systems considering dynamic characteristics of compressed air storage[J].Energy, 2017, 135：876-888.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on Dynamic Prediction Method of Flow Field in Compressed Air Storage Device Based on Dynamic Mode Decomposition and LSTM Neural Network

Improved Deep Learning Algorithm for Reproduction of Airfoil Flow Field

Reduced-Order Prediction Method for the Dynamic Thermal Response of Phase-Change Cooling Heat Exchangers

Study on Dynamic Characteristics Analysis of 350 MW-Scale Advanced Adiabatic Compressed Air Energy Storage System

Study on Thermo-Moisture-Pressure Coupled Dynamic Characteristics of Adiabatic-Near-Isothermal Hybrid Compressed Energy Storage Process

Related Author

SU Hao

WANG Tonsheng

ZOU Hansen

YU Keyu

YAO Erren

XI Guang

杨从新 1

凌祖光 1

Related Institution

School of Future Technology, Xi’an Jiaotong University

School of Energy and Power Engineering, Xi’an Jiaotong University

中国核动力研究设计院

兰州理工大学能源与动力工程学院

Wuhan Second Ship Design and Research Institute

⁰