Residual life prediction method for gas turbine HGP component based on multi-environmental time similarity theory

被引:0
|
作者
Wan, Anping [1 ]
Chen, Jianhong [1 ]
Sheng, Deren [1 ]
Hu, Yacai [1 ]
Yao, Hua [1 ]
Chen, Hui [2 ]
机构
[1] Institute of Thermal Science and Power System, Zhejiang University, Hangzhou 310027, Zhejiang Province, China
[2] Shandong Electric Power Engineering Consulting Institute Corp, Jinan 250013, Shandong Province, China
关键词
Gases; -; Forecasting; Maintenance;
D O I
暂无
中图分类号
学科分类号
摘要
In order to reduce the high costs of gas turbine operation and maintenance management, a novel residual life prediction method for gas turbine based on multi- environmental time similarity (METS) theory was proposed to make scientific and reasonable cost maintenance strategy of gas turbine. This method has introduced a reference gas turbine which has similar operational environment and type of the object gas turbine to obtain similarity coefficient (running hours and start/stop cycles) of the reference unit life evaluation parameters under actual operation conditions and benchmark operation conditions by using experience operational data. Based on the METS theory, the object unit factored running hours and start/stop cycles under benchmark operative conditions were obtained through calculating its actual running hours and start/stop cycles under actual operational conditions. And then the object unit residual life was predicted by comparing with maximum maintenance interval. Furthermore, in order to accurately calculate the object unit actual running hours and start/stop cycles and overcome the deficiency of the traditional statistical manual method, real-time running life and history running life calculation method were proposed to realize the development program. Finally, a factory gas turbine HGP component residual life prediction is provided as the example to verify the scientific validity and feasibility of the prediction method. © 2013 Chinese Society for Electrical Engineering.
引用
收藏
页码:95 / 101
相关论文
共 39 条
  • [21] An energy-based uniaxial fatigue life prediction method for commonly used gas turbine engine materials
    Department of Mechanical Engineering, The Ohio State University, 206 West, 18th Avenue, Columbus, OH 43210, United States
    不详
    J. Eng. Gas Turbines Power, 2008, 6
  • [22] Fusion prediction method of remaining useful life for T/R module based on multi-index similarity
    Hou X.
    Yang J.
    Deng B.
    Xia L.
    Wang T.
    Zhu X.
    Guofang Keji Daxue Xuebao/Journal of National University of Defense Technology, 2019, 41 (04): : 190 - 198
  • [23] State prediction of huge gas turbine machine based on Multi-level recursive method and Experimental Study
    Xu Jinling
    Ma Jie
    Xu Xiaoli
    Wang Shaohong
    INFORMATION TECHNOLOGY FOR MANUFACTURING SYSTEMS, PTS 1 AND 2, 2010, : 414 - +
  • [24] Spherical-dynamic time warping - A new method for similarity-based remaining useful life prediction
    Li, Xiaochuan
    Xu, Shuiqing
    Yang, Yingjie
    Lin, Tianran
    Mba, David
    Li, Chuan
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 238
  • [25] The Method of Multi-sources Fault Diagnosis in Gas Turbine & Compressor Unit Based on SDG and Bayes Theory
    Song, Yong-jie
    Xu, Bao-chang
    PROCEEDINGS OF THE 10TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA 2012), 2012, : 2973 - 2976
  • [26] A hybrid frequency-time domain life prediction method based on the critical plane theory
    Wang, Yantian
    Qiu, Yuanying
    Li, Jing
    Bai, Jin
    FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES, 2024, 47 (07) : 2351 - 2368
  • [27] A prediction method for the real-time remaining useful life of wind turbine bearings based on the Wiener process
    Hu, Yaogang
    Li, Hui
    Shi, Pingping
    Chai, Zhaosen
    Wang, Kun
    Xie, Xiangjie
    Chen, Zhe
    RENEWABLE ENERGY, 2018, 127 : 452 - 460
  • [28] Multi-stage residual life prediction of aero-engine based on real-time clustering and combined prediction model
    Liu, Junqiang
    Yu, Zhuoqian
    Zuo, Hongfu
    Fu, Rongchunxue
    Feng, Xiaonan
    RELIABILITY ENGINEERING & SYSTEM SAFETY, 2022, 225
  • [29] A fatigue life prediction method based on multi-signal fusion deep attention residual convolutional neural network
    Zhao, Chengying
    Wang, Jiajun
    He, Fengxia
    Bai, Xiaotian
    Shi, Huaitao
    Li, Jialin
    Huang, Xianzhen
    APPLIED ACOUSTICS, 2025, 235
  • [30] A multi-time-scale multi-step prediction method for gas utilization rate in a BF based on just-in-time learning
    Zhao, Guoyu
    An, Jianqi
    Guo, Yunpeng
    He, Yong
    Wu, Min
    CONTROL ENGINEERING PRACTICE, 2024, 147