期刊文献+

传感器故障检测的Powell神经网络方法 被引量:7

Sensor Failure Detection Based on a Powell Neural Network Method
下载PDF
导出
摘要 大型热力控制系统必须能够检测传感器故障 ,并采取相应的措施 ,保证控制过程的顺利进行。提出了一种基于Powell神经网络的故障检测新方法 ,为系统中每一个传感器构造一个神经网络观测器 ,首先离线训练神经网络观测器 ,然后进行故障检测并同时在线训练 ,利用神经网络估计输出代替故障传感器输出 ,保证系统的稳定。神经网络的训练采用Powell方法 ,该训练方法的收敛速度快、过程稳定。本方法具有在线学习、诊断多个传感器故障等优点。锅炉的实际试验结果表明 ,此方法行之有效。 It is essential for the control system of a large sized thermodynamic system to detect sensor failures and then take pertinent measures to ensure the successful implementation of the control process. The authors have come up with a new type of failure detection method based on Powell neural network. Under this method a neural network observer is set up for each sensor of the thermodynamic system, which at first received an off line training. On this basis, failure detection and on line training were conducted simultaneously. The neural network training by the use of the Powell method features a rapid and stable training process. It has the merits of the ability to perform on line learning and diagnose the failure of a multiple of sensors. Actual tests on boilers show that the above method is highly effective.
作者 李明 徐向东
出处 《热能动力工程》 EI CAS CSCD 北大核心 2002年第1期73-75,共3页 Journal of Engineering for Thermal Energy and Power
基金 国家攀登计划B基金资助项目 (85 -3 5 )
关键词 神经网络 故障检测 故障诊断 传感器 大型 热力控制系统 测量控制系统 neural network, failure detection, failure diagnosis, sensor
  • 相关文献

参考文献3

二级参考文献18

  • 1徐嗣鑫,戴友元.前向神经网络的一种快速学习方法及其应用[J].控制与决策,1993,8(4):284-288. 被引量:20
  • 2王耀南,童调生,蔡自兴.基于神经元网络的智能PID控制及应用[J].信息与控制,1994,23(3):185-189. 被引量:44
  • 3钮永胜,赵新民,孙金玮.传感器故障诊断方法研究[J].航天控制,1996,14(4):47-49. 被引量:7
  • 4张立明.人工神经网络的模型及其应用[M].上海:复旦大学出版社,1994..
  • 5钮永胜.基于人工神经网络的传感器故障诊断和信号恢复方法研究:学位论文[M].哈尔滨:哈尔滨工业大学自动化测试与控制系,1997..
  • 6张学峰,1996年
  • 7Chen S,Control,1992年,55卷,5期,1051页
  • 8周东华 孙优贤.控制系统的故障诊断和检测技术[M].北京:清华大学出版社,1994..
  • 9Pham D T,Int J Syst Sci,1996年,27卷,2期,221页
  • 10张立明,人工神经网络的模型及其应用,1994年,8页

共引文献54

同被引文献42

  • 1邓坚,熊瑞庭,全书海.基于ISD1760的智能电梯语音报站系统[J].中国水运(下半月),2009,9(2):120-121. 被引量:9
  • 2邹湘伏,何清华,贺继林.无人机发展现状及相关技术[J].飞航导弹,2006(10):9-14. 被引量:73
  • 3[2]Eemuri A T.Diagnosis of sensor bias faults[C].American Control Conference,1995,(1):460-464.
  • 4[4]Wilisky A S,A survey of design methods for failure detection in dynamic systems [J],Automatica,1976,(12):601-611.
  • 5[8]Agrawal R,Imielinski T,Swanmi A N.Mining association rules be-tween sets of items in large databases[C].Sigmod Conference,1993.
  • 6[9]Rafiei D,Mendelzon A.Similarity-based queries for time series data [C].In Proc. 1997 ACM-SIGMOD Int. Conf. Management of Data, pages 13-23,Tucson,Arizona,1997.
  • 7Elman J L. Finding structure in time [ J ]. Cognitive Science, 1990, 14:179-211.
  • 8Pham D T, Karaboga D. Training Elman and Jordan networks for system identification using genetic algorithms[J]. Artificial Intelligence in Engineering, 1999,13(2) :107 - 117.
  • 9Peter J M, Barry L K. Parallel training of simple recurrent neural networks [ A ]. In: International Symposium on Speech, Image Processing and Neural Networks[ C].New York, 1994. 167 - 170.
  • 10Qin Si-zhao, Su Hong-te, McAvoy Thomas J. Comparison of four neural net learning methods for dynamic system identification [J ]. IEEE Transactions on Neural Networks, 1992,3( l ) :122 - 130.

引证文献7

二级引证文献70

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部