计算机科学 ›› 2015, Vol. 42 ›› Issue (6): 23-27.doi: 10.11896/j.issn.1002-137X.2015.06.005

• 第十届和谐人机环境联合学术会议 • 上一篇    下一篇

数据驱动的燃气涡轮机跳闸预警方法的研究

谢晨,王睿智,李 飏,苗夺谦,焦 娜   

  1. 同济大学电子与信息工程学院 上海200092,同济大学电子与信息工程学院 上海200092;计算智能重庆市重点实验室 重庆400065,同济大学电子与信息工程学院 上海200092,同济大学电子与信息工程学院 上海200092,华东政法大学信息科学与技术系 上海201620
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金项目(61273304),高等学校博士学科点专项科研基金(优先发展领域)(20130072130004),计算智能重庆市重点实验室开放基金项目(CQ-LCI-2013-04)资助

Research of Data Driven Method for Gas Turbine Trip Prediction

XIE Chen, WANG Rui-zhi, LI Yang, MIAO Duo-qian and JIAO Na   

  • Online:2018-11-14 Published:2018-11-14

摘要: 燃气涡轮机已被广泛运用于现代工业中,其跳闸事件的发生将产生巨大的经济损失,因此,对燃气涡轮机的跳闸事件进行预测有重要的经济意义。然而,燃气涡轮机跳闸的预测研究是一个崭新的领域,研究成果非常有限,且缺乏数据驱动的预测方法和理论研究。从数据的预处理开始,研究了从数据的归一化、特征选择到特征值选择、特征值粒化等系列问题,并从各个角度设计了Elman神经网络的预测模型实验,对实验结果进行对比,得到了一系列建立并改善数据驱动的Elman网络跳闸预警系统的方法和有益经验,以供其他相关研究参考。

关键词: 数据驱动,Elman,故障预测,燃气涡轮机,跳闸

Abstract: Gas turbine is the most widely used device for modern industry.Once trips happened,gas turbine engines could cost customers millions dollars.Research on diagnosis and prediction of trips has significant impact.However,prediction of gas turbine trips is a relatively new subject and research finding is limited.So far no data driven solution for prediction of gas turbine trips is literately reported.The research work begines from preprocessing the data:normalization,dimensionality reduction,attribute value resampling and granulating.Experiments were conducted intensively on real datasets by using data-driven prediction methods Elman.The results of experiments on how to set up a better Elman network are valuable to other relative research.

Key words: Data driven,Elman,Fault prediction,Gas turbine,Trip

[1] Schmalzer B.Gas turbines:moving to prime time[J].Turbomachinery International,2010,1(6):10-14
[2] Ardalani-Farsa M,Zolfaghari S.Chaotic time series predictionwith residual analysis method using hybrid Elman-NARX neural networks[J].Neurocomputing,2010,73(13-15):2540-2553
[3] Binsompasong P,Leeragreephol S,Laohasongkram P,et al.Case study of protecting gas turbine trip from damper closing failure and HRSG trip from solenoid coil of hydraulic damper burned[C]∥2006 SICE-ICASE International Joint Conference.Vols 1-13,2006:467-471
[4] Brandstetter G,Oberleitner W,Pichler M.How to change over heat recovery steam generators after gas turbine trip[C]∥Proceedings of the ASME Turbo Expo 2006.Vol 4,2006:723-730
[5] Chen T,Xu X L,Wang S H.An Intelligent Prediction Method Based on Information Entropy Weighted Elman Neural Network[J].Comm Com Inf Sc.2011,135:142-147
[6] Graichen C M,Cheetham W E.Case-based reasoning approachesfor gas turbine trip diagnosis[C]∥Proceedings of the Asme Turbo Expo 2007.Vol 1.2007:721-728
[7] Laohasongkram P,Leeragreephol S.Solving problem of gas turbine and HRSG trip from hydraulic damper closing in Combined Cycle Power Plant[C]∥2007 International Conference on Control,Automation and Systems.2007:1301-1305
[8] Ravi Y B,Pandey A,Jammu V.Prediction of Gas Turbine Trip Due to Electro Hydraulic Control Valve System Failures[C]∥Proceedings of the Asme Turbo Expo 2010,Vol 3.2010:299-306
[9] Tian X,Song W Y,Bai Y S,et al.Research on Reliability Prediction Based on Weighted Elman Network[C]∥2012 InternationalConference on Quality,Reliability,Risk,Maintenance,and Safety Engineering (Icqr2mse).2012:740-743
[10] Elman J L.Finding Structure in Time[M].COGNITIVE SCIENCE.1990,14:179-211
[11] Pandey A K,Jammu V B,Zaremba S M .System and Method for Predication of Gas Turbine Trips Due to Gas Control Valve Failure.http://www.freepatentsonline.com/20090055130.pdf
[12] Milne R.TIGERTM:Knowledge Based Gas Turbine Condition Monitoring[J].Ai Communications,1999,9(3):92-108
[13] De Wbiryb S,Jammu V B,Pandey A K.Richard John Rucigay,Saratoga Springs,NY (U S).System and Method for Prediction of Gas Turbine Trips Due to Thermocoluple Failures.http://www.freepatentsonline.com/7734443.html
[14] Robert Milne CN.TIGERTM:Continuous Diagnosis of Gas Turbines[C]∥Proc.of ECAI/PAIS’00.2000

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!