谢岳生,万震天,李俊昆

• 1:上海发电设备成套设计研究院有限责任公司

摘要(Abstract)：

为实现压气机叶片积垢和喘振故障的提前预警，提出了一种融合热力学模型与人工智能的燃气轮机压气机典型故障预警方法。根据模块化思想搭建燃气轮机热力学性能仿真模型，并利用燃气轮机实际运行数据完成模型的动态标定，形成高精度燃气轮机性能分析模型，实现排气流量、透平进口温度、燃气轮机热耗率等关键指标的计算。在热力性能仿真模型的基础上，结合压气机典型故障专家经验及专业知识确定影响压气机故障的主要特征参数，抽象表征出压气机叶片积垢和喘振的预警模型。选取历史健康数据，采用人工神经网络算法对模型进行训练，获取偏差曲线，通过监测预警模型输出预测值与测量值之间的偏差变化，实现压气机典型故障的提前预警，给出了某GE 9F型燃气轮机压气机的实测数据的有效性验证实例。结果表明：该方法能精准捕捉压气机叶片积垢和喘振故障，相对于传统阈值报警方式，提高预警的时间窗口。该研究成果可直接在燃气轮机电厂侧部署，实时为运维人员的检修和维护决策提供指导。

关键词(KeyWords)： 燃气轮机;压气机;性能仿真;人工神经网络;故障预警

Abstract:

Keywords:

基金项目(Foundation): 上海市青年科技启明星项目（20QB1401900）~~

作者(Author): 谢岳生,万震天,李俊昆

DOI: 10.19666/j.rlfd.202311170

参考文献(References)：

• [1]姚钦博,陈金伟,张会生,等.基于注意力机制的燃气轮机故障诊断方法研究[J].热能动力工程,2021,36(9):21-227.YAO Qinbo,CHEN Jinwei,ZHANG Huisheng,et al.Study on fault diagnosis method of gas turbine based on attention mechanism[J].Journal of Engineering for Thermal Energy and Power,2021,36(9):221-227.
• [2]VUONG T D,KIM K Y.Design optimization of a dual-bleeding recirculation channel to enhance operating stability of a transonic axial compressor[J].Energies,2022,15(1):159.
• [3]王钟.燃气轮机叶片断裂故障机理及识别方法研究[D].北京:北京化工大学,2021:1-2.WANG Zhong.Research on mechanism and identification method of turbine blade[D].Beijing:Beijing University of Chemical Technology,2021:1-2.
• [4]应雨龙,李靖超,庞景隆,等.基于热力模型的燃气轮机气路故障预测诊断研究综述[J].中国电机工程学报,2019,39(3):731-743.YING Yulong,LI Jingchao,PANG Jinglong,et al.Review of gas turbine gas-path fault diagnosis and prognosis based on thermodynamic model[J].Proceedings of the CSEE,2019,39(3):731-743.
• [5]TAHAN M,TSOUTSANIS E,MUHAMMAD M,et al.Performance-based health monitoring,diagnostics and prognostics for condition-based maintenance of gas turbines:a review[J].Applied Energy,2017,198:122-144.
• [6]YANG Z,XI G,WANG Z H,et al.Numerical investigation of deep surge in a centrifugal compressor with vaned diffuser and large plenum[J].Proceedings of the Institution of Mechanical Engineers,2020,234(2):143-155.
• [7]闫斌斌.基于气路性能混合模型的燃气轮机叶片故障预警及诊断方法研究[D].北京:北京化工大学,2021:1.YAN Binbin.Research on early warning and diagnosis method of gas turbine blade fault based on gas path performance hybrid model[D].Beijing:Beijing University of Chemical Technology,2021:137-139.
• [8]梅赫万·P.博伊斯.燃气轮机工程手册[M].4版.丰镇平,李祥晟,邓清华,等译.北京:机械工业出版社,2018:572-578.MEHERWAN P B.Gas turbine engineering handbook[M].4th ed.FENG Zhenping,LI Xiangsheng,DENGQinghua,et al translated.Beijing:Machinery Industry Press,2018:572-578.
• [9]林新智,冯坤,胡明辉,等.基于性能仿真的燃气轮机气路故障预警方法[J].热能动力工程,2020,35(9):36-43.LIN Xinzhi,FENG Kun,HU Minghui,et al.Early warning method of gas path fault of gas turbine based on performance simulation[J].Journal of Engineering for Thermal Energy and Power,2020,35(9):36-43.
• [10]邱振波,张立杰,胡伟,等.基于信息通信技术的燃气轮机远程预警技术研究及应用[J].热力发电,2019,48(2):120-125.QIU Zhenbo,ZHANG Lijie,HU Wei,et al.Research and application of ICT-based remote early warning technology for gas turbines[J].Thermal Power Generation,2019,48(2):120-125.
• [11]彭道刚,姬传晟,涂煊,等.基于LSTM-SVM的燃气轮机压气机故障预警研究[J].动力工程学报,2021,41(5):394-399.PENG Daogang,JI Chuansheng,TU Xuan,et al.Research on gas turbine compressor fault early warning based on LSTM-SVM[J].Journal of Chinese Society of Power Engineering,2021,41(5):394-399
• [12]孙守泰,汤冰,薛亚丽,等.基于混合深度学习的压气机喘振快速诊断及自抗扰控制方法[J/OL].中国舰船研究:1-11.(2023-11-17)[2023-12-26].https://doi.org/10.19693/j.issn.1673-3185.03259.SUN Shoutai,TANG Bing,XUE Yali,et al.Rapid diagnosis and active disturbance rejection control of compressor surge based on hybrid deep learning[J/OL].Chinese Journal of Ship Research:1-11.(2023-11-17)[2023-12-26].https://doi.org/10.19693/j.issn.1673-3185.03259.
• [13]NOGUERAS-RIVERA D I,MOJICA-VAZQUEZ L,BONILLA-ALVARADO H,et al.Hyper-parameter optimization of deep learning models for compressor air leak prediction in a gas turbine[C]//ASME Power Conference.American Society of Mechanical Engineers,2022,85826:V001T04A002.
• [14]靳尧飞,应雨龙,李靖超,等.基于模型与数据混合驱动的燃气轮机气路故障诊断方法[J].热力发电,2021,50(9):66-71.JIN Yaofei,YING Yulong,LI Jingchao,et al.A gas path circuit diagnosis method for gas turbine based on model and data hybrid drive[J].Thermal Power Generation,2021,50(9):66-71.
• [15]陆永卿,涂雷,茅大钧.基于MSET的压气机故障预警研究[J].上海电力大学学报,2021,37(2):133-137.LU Yongqing,TU Lei,MAO Dajun.Research on compressor fault early warning based on MSET[J].Journal of Shanghai University of Electric Power,2021,37(2):133-137.
• [16]闫丽萍,董学智,张永军,等.基于深度置信网络的燃气轮机气路故障诊断方法[J].工程热物理学报,2020,41(4):840-844.YAN Liping,DONG Xuezhi,ZHANG Yongjun,et al.Agas path fault diagnostic method of gas turbine based on deep belief network[J].Journal of Engineering Thermophysics,2020,41(4):840-844.
• [17]万震天,谢岳生,田书耘,等.燃气轮机性能监测与故障预警系统开发及工程应用研究[J].热力发电,2022,51(5):149-155.WAN Zhentian,XIE Yuesheng,TIAN Shuyun,et al.Research on development and engineering application of gas turbine performance monitoring and fault early warning system[J].Thermal Power Generation,2022,51(5):149-155.
• [18]刘尚明,李忠义.基于SIMULNK的单轴重型燃气轮机建模与仿真研究[J].燃气轮机技术,2009,22(3):33-39.LIU Shangming,LI Zhongyi.Modeling and simulation of single shafe heavy duty gas turbine using SIMULINK[J].Gas Turbine Technology,2009,22(3):33-39.
• [19]谢心喻,鲁业明,王晓放,等.基于不同压气机特性曲线预测方法的单轴燃气轮机动态性能仿真研究[J].热能动力工程,2021,36(3):26-34.XIE Xinyu,LU Yeming,WANG Xiaofang,et al.Simulation investigation on dynamic performance of single shaft gas turbine based on different compressor characteristic curve prediction methods[J].Journal of Engineering for Thermal Energy and Power,2021,36(3):26-34.
• [20]何宏.某重型燃气轮机瞬态模型开发与验证[D].上海:上海交通大学,2018:25-29.HE Hong.Transient model development and verification of a heavy duty gas turbine[D].Shanghai:Shanghai Jiao Tong University,2018:25-29.
• [21]郑露霞.重型燃气轮机透平冷却建模与热力性能分析[D].北京:中国科学院工程热物理研究所,2019:13-25.ZHENG Luxia.Cooling turbine modeling and thermal performance analysis for heavy-duty gas turbines[D].Beijing:Institute of Engineering Thermophysics,Chinese Academy of Sciences,2019:13-25.
• [22]乔红,曹越,戴义平.300 MW重型燃气轮机数学建模与动态仿真[J].燃气轮机技术,2016,29(2):28-33.QIAO Hong,CAO Yue,DAI Yiping.Mathematical modeling and dynamic simulation study based on 300 MWheavy-duty gas turbine[J].Gas Turbine Technology,2016,29(2):28-33.
• [23]GHORBANIAN K,GHOLAMREZAEI M.An artificial neural network approach to compressor performance prediction[J].Applied Energy,2009,86(7-8):1210-1221.
• [24]杨天南,蔡晋.积垢对轴流压气机性能的影响分析[J].航空发动机,2017,43(6):39-43.YANG Tiannan,CAI Jin.Effect of fouling on performance of axial compressor[J].Aeroengine,2017,43(6):39-43.
• [25]韩朝兵,朱泓逻,黄伟栋,等.压气机离线水洗后燃气轮机性能衰退分析研究[J].动力工程学报,2019,39(8):626-633.HAN Chaobing,ZHU Hongluo,HUANG Weidong,et al.Performance degradation analysis of a gas turbine after offline water washing of the compressor[J].Journal of Chinese Society of Power Engineering,2019,39(8):626-633.
• [26]刘健鑫,任荣社,仇远旺.燃气轮机压气机喘振故障分析与防喘方法研究[J].内燃机与动力装置,2016,33(6):1-4.LIU Jianxin,REN Rongshe,QIU Yuanwang.Analysis on failure of surge and method of anti-surge for gas turbine compressor[J].Internal Combustion Engine&Power Plant,2016,33(6):1-4.