[1]司风琪,李欢欢,徐治皋.基于鲁棒输入训练神经网络的非线性多传感器故障诊断方法及其应用[J].东南大学学报(自然科学版),2011,41(3):574-578.[doi:10.3969/j.issn.1001-0505.2011.03.028]
　Si Fengqi,Li Huanhuan,Xu Zhigao.Nonlinear multi-sensor fault diagnosis method and its application based on robust input-training neural network[J].Journal of Southeast University (Natural Science Edition),2011,41(3):574-578.[doi:10.3969/j.issn.1001-0505.2011.03.028]
点击复制

基于鲁棒输入训练神经网络的非线性多传感器故障诊断方法及其应用()
分享到：

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
41
期数:
2011年第3期
页码:
574-578
栏目:
自动化
出版日期:
2011-05-20

文章信息/Info

Title:
Nonlinear multi-sensor fault diagnosis method and its application based on robust input-training neural network
作者:
司风琪; 李欢欢; 徐治皋
(东南大学能源与环境学院, 南京 210096)
Author(s):
Si Fengqi; Li Huanhuan; Xu Zhigao
(School of Energy and Environment,Southeast University,Nanjing 210096, China)
关键词:
鲁棒输入训练神经网络; 故障诊断; 多传感器; 影响因子; 可靠性系数
Keywords:
robust input-training neural network;  fault diagnosis;  multi-sensor;  influence factor;  reliability coefficient
分类号:
TP206.3
DOI:
10.3969/j.issn.1001-0505.2011.03.028
摘要:
针对非线性系统多传感器故障诊断时出现的检测准确性下降和数据重构产生的残差污染问题,提出了基于鲁棒输入训练神经网络非线性多传感器故障诊断模型.在目标函数中引入影响因子函数和可靠性系数,并通过计算机模拟和仿真确定最佳影响因子函数形式,抑制了多个含有显著误差故障数据的不良影响,并增加了具备高可靠性的重要数据影响权重,大大减小了残差污染,提高了故障诊断的准确性和可靠性.以某300MW机组1#高加测点为对象进行算例分析,验证了该方法对于多传感器故障诊断的可行性和准确性,计算和模拟表明,RITNN方法优于线性PCA和传统ITNN方法,能够更加准确进行多传感器故障的检测和故障数据的重构.
Abstract:
As fault detection accuracy reduces and residual contaminations appear in multi-sensor fault diagnosis, a nonlinear multi-sensor fault diagnosis model based on robust modified input-training neural network is proposed. The best influence factor function chosen from the results of computer simulation and reliability coefficients are introduced into the objective function for the purpose of inhibiting the influence of numerous failure data with significant errors and increasing the influence ratio of some high reliability data, which significantly reduces the residual contaminations and increases the accuracy and reliability of fault diagnosis. The case study was conducted to detect and validate some points from 1# high pressure heater in a 300MW power plant. The results verify the feasibility and accuracy of RITNN(robust input training neural network) in multi-sensor fault diagnosis. Compared to linear PCA(principal component analysis) and ITNN(input-training neural network), the RITNN method can be more effectively used in multi-sensor fault diagnosis and error data reconstruction.

参考文献/References:

[1] 方泽南,傅尚新,张勇.时间序列在故障诊断中的应用[J].清华大学学报:自然科学版,1998,38(9):123-126.
　　Fang Zenan,Fu Shangxin,Zhang Yong.Fault diagnosis based on time series[J].Journal of Tsinghua University:Sci &Tech,1998,38(9):123-126.(in Chinese)
[2] Pham Hong Thom,Yang Bo-Suk.Estimation and forecasting of machine health condition using ARMA/GARCH model[J].Mechanical Systems and Signal Processing,2010,24(2):546-558.
[3] Choi S W,Lee I B.Multiblock PLS-based localized process diagnosis[J].Journal of Process Control,2005,15(3):295-306.
[4] 司风琪,周建新,仇晓智,等.基于APCA的电站热力过程故障传感器自适应检测方法[J].东南大学学报:自然科学版,2009,39(2):282-286.
　　Si Fengqi,Zhou Jianxin,Qiu Xiaozhi,et al.Adaptive detection method of sensor failures based on APCA for the thermodynamic system in power plant[J].Journal of Southeast University:Natural Science Edition,2009,39(2):282-286.(in Chinese)
[5] Ding S,Zhang P,Ding E,et al.On the application of PCA technique to fault diagnosis[J].Tsinghua Science &Technology,2010,15(2):138-144.
[6] Sun Ruixiang,Tsung Fugee,Qu Liangsheng.Evolving kernel principal component analysis for fault diagnosis[J].Computers &Industrial Engineering,2007,53(2):361-371.
[7] Antory David,Irwin George W,Kruger Uwe.et al.Improved process monitoring using nonlinear principal component models[J].International Journal of Intelligent Systems,2008,23(5):520-544.
[8] Zhang Yingwei.Enhanced statistical analysis of nonlinear processes using KPCA,KICA and SVM[J].Chemical Engineering Science,2009,64(5):801-811.
[9] 毕小龙,王洪跃,司风琪,等.基于核主元分析的传感器故障检测[J].动力工程,2007,27(4):555-559.
　　Bi Xiaolong,Wang Hongyue,Si Fengqi,et al.Detection of sensor faults by kernel principal component analysis[J].Journal of Power Engineering,2007,27(4):555-559.(in Chinese)
[10] Javier Sanz,Ricardo Perera,Consuelo Huerta.Fault diagnosis of rotating machinery based on auto-associative neural networks and wavelet transforms[J].Journal of Sound and Vibration,2007,302(4/5):981-999.
[11] 司风琪,徐治皋.基于自联想神经网络的测量数据自校正检验方法[J].中国电机工程学报,2002,22(6):152-155.
　　Si Fengqi,Xu Zhigao.Self-verifying data validation method based on the autoassociative neural network(AANN)[J].Proceedings of the CSEE,2002,22(6):152-155.(in Chinese)
[12] Zhu Qunxiong,Li Chengfei.Dimensionality reduction with input training neural network and its application in chemical process modelling[J].Chinese Journal of Chemical Engineering,2006,14(5):597-603.
[13] Tan Shufeng,Mayrovouniotis Michael L.Reducing data dimensionality through optimizing neural network[J].AIChE Journal,1995,41(6):1471-1480.
[14] Ozyurt Derya B,Pike Ralph W.Theory and practice of simultaneous data reconciliation and gross error detection for chemical processes[J].Computers and Chemical Engineering,2004,28(3):381-402.

相似文献/References:

[1]胡建中,贾民平,许飞云.多诊断方法代理联盟策略研究[J].东南大学学报(自然科学版),2003,33(1):49.[doi:10.3969/j.issn.1001-0505.2003.01.012]
　Hu Jianzhong,Jia Minping,Xu Feiyun.Study on the multi diagnosis method coalition strategy[J].Journal of Southeast University (Natural Science Edition),2003,33(3):49.[doi:10.3969/j.issn.1001-0505.2003.01.012]
[2]姚洪兴,赵林度,盛昭瀚.多级模糊神经网络在故障诊断中的应用[J].东南大学学报(自然科学版),2001,31(2):59.[doi:10.3969/j.issn.1001-0505.2001.02.015]
　Yao Hongxing,Zhao Lindu,Sheng Zhaohan.Application of Multi-Grade Fuzzy Neural Networks in Fault Diagnosis of Large Machinery[J].Journal of Southeast University (Natural Science Edition),2001,31(3):59.[doi:10.3969/j.issn.1001-0505.2001.02.015]
[3]方敏,茹继锋,王峻.基于第一原理的实用故障诊断算法[J].东南大学学报(自然科学版),1999,29(3):83.[doi:10.3969/j.issn.1001-0505.1999.03.016]
　Fang Min,Ru Jifeng,Wang Jun.A Practical Algorithm of Diagnosis from First Principles[J].Journal of Southeast University (Natural Science Edition),1999,29(3):83.[doi:10.3969/j.issn.1001-0505.1999.03.016]
[4]杨建刚,高,曹祖庆,等.集成旋转机械故障诊断的知识表示与推理[J].东南大学学报(自然科学版),1995,25(3):72.[doi:10.3969/j.issn.1001-0505.1995.03.014]
　Yang Jiangang,Gao Wei,et al.An Integrated Knowledge Representation and Inference for Rotating Machinery Fault Diagnosis[J].Journal of Southeast University (Natural Science Edition),1995,25(3):72.[doi:10.3969/j.issn.1001-0505.1995.03.014]
[5]胥建群,孙友源,杨涛,等.基于特性曲线的电站热力系统故障诊断方法[J].东南大学学报(自然科学版),2014,44(4):775.[doi:10.3969/j.issn.1001-0505.2014.04.017]
　Xu Jianqun,Sun Youyuan,Yang Tao,et al.Malfunction diagnosis method for thermal system of power plant based on characteristic curve[J].Journal of Southeast University (Natural Science Edition),2014,44(3):775.[doi:10.3969/j.issn.1001-0505.2014.04.017]

备注/Memo

备注/Memo:
作者简介:司风琪(1973—),男,博士,教授,博士生导师,fqsi@seu.edu.cn.
基金项目:东南大学科技基金资助项目(9203000024).
引文格式: 司风琪,李欢欢,徐治皋.基于鲁棒输入训练神经网络的非线性多传感器故障诊断方法及其应用[J].东南大学学报:自然科学版,2011,41(3):574-578.[doi:10.3969/j.issn.1001-0505.2011.03.028]
更新日期/Last Update: 2011-05-20