Application of Temporal Convolutional Network in Rotor Thermo-Mechanical Coupling Stress Prediction and Life Assessment

LI Weiye; FENG Jianxin; WEN Siguo; ZHANG Xiaolong; YUAN Qi; LI Pu

doi:10.7652/xjtuxb202510008

您当前的位置：

首页 >

文章列表页 >

Application of Temporal Convolutional Network in Rotor Thermo-Mechanical Coupling Stress Prediction and Life Assessment

更新时间：2025-09-28

- Application of Temporal Convolutional Network in Rotor Thermo-Mechanical Coupling Stress Prediction and Life Assessment
- Journal of Xi'an Jiaotong University Vol. 59, Issue 10, Pages: 87-95(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202510008
  CLC： TK14
- Received：02 April 2025，
  
  Published：10 October 2025
- 稿件说明：
移动端阅览
LI Weiye, FENG Jianxin, WEN Siguo, et al. Application of Temporal Convolutional Network in Rotor Thermo-Mechanical Coupling Stress Prediction and Life Assessment[J]. Journal of Xi'an Jiaotong University, 2025, 59(10): 87-95.
DOI：

LI Weiye, FENG Jianxin, WEN Siguo, et al. Application of Temporal Convolutional Network in Rotor Thermo-Mechanical Coupling Stress Prediction and Life Assessment[J]. Journal of Xi'an Jiaotong University, 2025, 59(10): 87-95. DOI： 10.7652/xjtuxb202510008.

摘要

针对透平机械转子启动过程中，瞬态热应力由于计算成本高而难以实现快速预测的问题，提出了一种基于时序卷积网络（TCN）的压缩机转子表面温度场和应力场预测方法。采用有限元方法计算压缩机转子在冷态启动工况下的温度场、应力场和使用寿命，基于TCN模型开展转子的温度场和应力场预测及寿命评估，并与长短时记忆（LSTM）网络、门控循环单元（GRU）和Transformer 3种神经网络模型的预测结果进行对比。模拟结果表明：冷态启动工况下，TCN模型在预测转子瞬态热应力时的性能表现最优，相较于Transformer、LSTM和GRU模型，其热应力预测决定系数分别提高了0.03%、0.60%、0.36%，综合加载等效应力预测决定系数分别提高了0.10%、0.48%、0.02%；与传统的有限元热固耦合分析方法相比，TCN模型的计算效率显著提高，耗时仅为有限元方法的0.25%。所提方法提升了预测的准确性，可为透平机械转子瞬态热应力的快速预测和寿命评估提供技术支撑。

Abstract

To address the challenge of rapidly predicting transient thermal stress during the startup of turbomachinery rotors

which is difficult due to high computational costs

a compressor rotor surface temperature field and stress field prediction method based on temporal convolutional network (TCN) is proposed. The finite element method is utilized to compute the temperature field

stress field

and service life of the compressor rotor under cold startup conditions. A TCN model is then employed for temperature field and stress field prediction and life assessment of the rotor

and the results are compared with those obtained from three other neural network models: long short-term memory (LSTM)

gated recurrent unit (GRU)

and Transformer. Simulation results demonstrate that under cold startup conditions

the TCN model exhibits optimal performance in predicting transient thermal stress of the rotor. Compared to the Transformer

LSTM

and GRU models

the coefficient of determination for thermal stress predictions improves by 0.03%

0.60%

and 0.36%

respectively

while the coefficient of determination for equivalent stress predictions under combined loading increases by 0.10%

0.48%

and 0.02%.Moreover

the computational efficiency of the TCN model is significantly improved compared to traditional finite element thermo-mechanical coupled analysis

with a computation time only 0.25% that of the finite element method. This proposed method enhances prediction accuracy and provides technical support for the rapid prediction of transient thermal stresses and life assessment of turbomachinery rotors.

关键词

Keywords

references

徐宁 , 王庆超 , 刘占生 , 等 . 基于热弹耦合的涡轮转子瞬态热冲击研究 [J ] . 哈尔滨工程大学学报 , 2016 , 37 ( 7 ): 936 - 942 .

XU Ning , WANG Qingchao , LIU Zhansheng , et al . Transient thermal impact research on turbine rotors based on thermoelastic coupling [J ] . Journal of Harbin Engineering University , 2016 , 37 ( 7 ): 936 - 942 .

王军利 , 陆正午 , 李庆庆 , 等 . 基于热分析的双螺杆压缩机转子的应力疲劳研究 [J ] . 机械强度 , 2021 , 43 ( 4 ): 928 - 935 .

WANG Junli , LU Zhengwu , LI Qingqing , et al . Research on stress fatigue of twin screw compressor rotor based on thermal analysis [J ] . Journal of Mechanical Strength , 2021 , 43 ( 4 ): 928 - 935 .

曹源 . 滚动活塞式压缩机转子精准启停控制方法 [J ] . 机械与电子 , 2025 , 43 ( 4 ): 45 - 51 .

CAO Yuan . Precise start stop control method for rolling piston compressor rotor [J ] . Machinery & Electronics , 2025 , 43 ( 4 ): 45 - 51 .

周祚 , 李嘉 , 曾帆 , 等 . 周向拉杆转子瞬态应力分析与启动曲线优化 [J ] . 舰船科学技术 , 2022 , 44 ( 11 ): 125 - 131 .

ZHOU Zuo , LI Jia , ZENG Fan , et al . Transit stress analysis and start-up curve optimization of a circumferential distributed rod fastening rotor [J ] . Ship Science and Technology , 2022 , 44 ( 11 ): 125 - 131 .

陈思远 , 黄畅 , 王卫良 , 等 . 面向新型电力系统汽轮机高压转子蠕变/疲劳寿命损耗研究 [J ] . 热力发电 , 2024 , 53 ( 10 ): 106 - 113 .

CHEN Siyuan , HUANG Chang , WANG Weiliang , et al . Research on creep/fatigue life of high pressure rotor in steam turbine for new power systems [J ] . Thermal Power Generation , 2024 , 53 ( 10 ): 106 - 113 .

黄朝晖 , 袁奇 , 张弘斌 , 等 . 某型火箭发动机涡轮转子流热固耦合强度及疲劳寿命分析 [J ] . 西安交通大学学报 , 2022 , 56 ( 8 ): 73 - 84 .

HUANG Chaohui , YUAN Qi , ZHANG Hongbin , et al . Analysis of fluid-thermal-solid coupling strength and fatigue life of a certain rocket engine turbine rotor [J ] . Journal of Xi'an Jiaotong University , 2022 , 56 ( 8 ): 73 - 84 .

夏雪 , 闫恩来 , 李喜武 . Transformer在时间序列预测中的应用综述 [J ] . 信息技术与信息化 , 2024 ( 3 ): 124 - 128 .

XIA Xue , YAN Enlai , LI Xiwu . Overview of the application of transformer in time series prediction [J ] . Information Technology & Informatization , 2024 ( 3 ): 124 - 128 .

孟祥福 , 石皓源 . 基于Transformer模型的时序数据预测方法综述 [J ] . 计算机科学与探索 , 2025 , 19 ( 1 ): 45 - 64 .

MENG Xiangfu , SHI Haoyuan . Survey of transform er-based model for time series forecasting [J ] . Journal of Frontiers of Computer Science & Technology , 2025 , 19 ( 1 ): 45 - 64 .

YAN Haoran , QIN Yi , XIANG Sheng , et al . Longterm gear life prediction based on ordered neurons LSTM neural networks [J ] . Measurement , 2020 , 165 : 108205 .

杨晨 , 柴京 , 张涛 , 等 . 基于LSTM网络的汽轮机转子热应力预测方法 [J ] . 计算机仿真 , 2023 , 40 ( 2 ): 123 - 127 .

YANG Chen , CHAI Jing , ZHANG Tao , et al . Prediction method of steam turbine rotor thermal stress based on long-short-term memory network [J ] . Computer Simulation , 2023 , 40 ( 2 ): 123 - 127 .

唐成顺 , 孙丹 , 唐威 , 等 . 基于LSTM循环神经网络的汽轮机转子表面应力预测模型 [J ] . 中国电机工程学报 , 2021 , 41 ( 2 ): 451 - 460 .

TANG Chengshun , SUN Dan , TANG Wei , et al . A turbine rotor surface stress prediction model based on LSTM recurrent neural network [J ] . Proceedings of the CSEE , 2021 , 41 ( 2 ): 451 - 460 .

刘辉 , 李永康 , 张淼 , 等 . 基于GWO-TCN网络的HVDC输电线路故障诊断 [J ] . 电子测量技术 , 2021 , 44 ( 22 ): 168 - 174 .

LIU Hui , LI Yongkang , ZHANG Miao , et al . Fault diagnosis of HVDC transmission lines based on GWO-TCN networks [J ] . Electronic Measurement Technology , 2021 , 44 ( 22 ): 168 - 174 .

虞思思 . 卷积神经网络在动态温度测量中的应用 [D ] . 杭州 : 中国计量大学 , 2022 .

邓智 , 王正勇 , 何小海 , 等 . 基于改进TCN的上扣扭矩序列数据分类 [J ] . 电子测量技术 , 2024 , 47 ( 18 ): 1 - 8 .

DENG Zhi , WANG Zhengyong , HE Xiaohai , et al . Classification of make-up torque sequence data based on improvedTCN [J ] . Electronic Measurement Technology , 2024 , 47 ( 18 ): 1 - 8 .

袁安妮 , 邹春明 , 王勇 , 等 . 基于改进TCN的多元时间序列异常检测算法 [J ] . 计算机工程与设计 , 2025 , 46 ( 2 ): 416 - 422 .

YUAN Anni , ZOU Chunming , WANG Yong , et al . Multivariate time series anomaly detection algorithm based on improvedTCN [J ] . Computer Engineering and Design , 2025 , 46 ( 2 ): 416 - 422 .

唐杰 , 孙茹 . 航空管路无扩口管接头寿命预测方法研究 [J ] . 重庆理工大学学报(自然科学) , 2025 , 39 ( 2 ): 154 - 162 .

TANG Jie , SUN Ru . Study on life prediction method of aviation flareless pipe joint [J ] . Journal of Chongqing University of Technology(Natural Science) , 2025 , 39 ( 2 ): 154 - 162 .

史进渊 , 杨宇 , 邓志成 , 等 . 大功率电站汽轮机寿命预测与可靠性设计 [M ] . 北京 : 中国电力出版社 , 2011 .

张蕾 , 季媛媛 , 李娜 , 等 . 基于TCN与双重注意力机制的光伏功率预测模型 [J/OL ] . 计算机技术与发展 . ( 2025-03-10 )[ 2025-04-27 ] . https://doi.org/10.20165/j.cnki.ISSN1673-629 X.2025.0045 .

ZHANG Lei , JI Yuanyuan , LI Na , et al . A photovoltaic power prediction model based on TCN and double attention mechanism [J/OL ] . Computer Technology and Development ( 2025-03-10 )[ 2025-04-27 ] . https://doi.org/10.20165/j.cnki.ISSN1673-629X.2025.0045 .

李吉生 , 于艇 , 岳鹏 , 等 . 一种基于TCN的核电蓄电池异常检测方法 [J ] . 软件导刊 , 2025 , 24 ( 5 ): 40 - 45 .

LI Jisheng , YU Ting , YUE Peng , et al . An anomaly detection method for nuclear power storage batteries based onTCN [J ] . Software Guide , 2025 , 24 ( 5 ): 40 - 45 .

HEATON J . Ian Goodfellow,Yoshua Bengio,and Aaron Courville:deep learning [J ] . Genetic Programming and Evolvable Machines , 2018 , 19 ( 1 ): 305 - 307 .

王竹晴 . 基于神经网络的锂离子电池RUL预测方法研究 [D ] . 太原 : 中北大学 , 2019 .

KÖRDING K P , WOLPERT D M . The loss function of sensorimotor learning [J ] . Proceedings of the National Academy of Sciences , 2004 , 101 ( 26 ): 9839 - 9842 .

KINGMA D P , BA J L . Adam:a method for stochastic optimization [EB/OL ] .( 2014-12-22 )[ 2025-01-12 ] . https://arxiv.org/abs/1412.6980v1 .

李敏 , 李红娇 , 陈杰 . 差分隐私保护下的Adam优化算法研究 [J ] . 计算机应用与软件 , 2020 , 37 ( 6 ): 253 - 258 .

LI Min , LI Hongjiao , CHEN Jie . Adam optimization algorithm based on differential privacy protection [J ] . Computer Applications and Software , 2020 , 37 ( 6 ): 253 - 258 .

LIU Mingliang , GRANA D . Accelerating geostatistical seismic inversion using TensorFlow:a heterogeneous distributed deep learning framework [J ] . Computers & Geosciences , 2019 , 124 : 37 - 45 .

周祚 . 50 MW燃气轮机转子瞬态热应力与结构优化研究 [D ] . 西安 : 西安交通大学 , 2016 .

HARRINGTON P . Machine learning in action [M ] . Beijing : Posts & Telecom Press , 2018 : 15 - 31 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Thermal Stress Analysis of Piezoelectric Force Sensors under Thermal-Structural Coupling

Inner Damage Mechanism of Metal Bar with Thermal Stress

Thermal Stress Analysis of Crystal Morphology in Growth of Silicon Carbide Bulk Crystal by PVT Method

Analysis on Thermal Stress of a Planar Solid Oxide Fuel Cell

Steam Turbine Rotor Thermal Stress Calculation with Thermo-Structural Coupled Model

Related Author

WANG Guicong

LI Hongyu

LI Yingjun

ZHOU Yuanqin

唐勇 2

赵升吨 2

张立军 1

杨建锋

Related Institution

School of Mechanical Engineering, University of Jinan

School of Mechanical and Electronic Engineering, China University of Petroleum

State Key Laboratory for Mechanical Behavior of Materials, Xi'an Jiaotong University

Key Laboratory of Thermo-Fluid Science and Engineering, Ministry of Education, Xi'an Jiaotong University

State Key Lab for Strength and Vibration of Mechanical Structures, Xi'an Jiaotong University

⁰