基于T-S模糊KPCA模型的分布式控制系统传感器故障诊断

推进技术 ›› 2014, Vol. 35 ›› Issue (7): 988-995.

基于T-S模糊KPCA模型的分布式控制系统传感器故障诊断

王　磊^1,2,谢寿生¹,任立通¹,余　坚¹,崔小军³

空军工程大学航空航天工程学院，陕西西安 710038; 中国人民解放军93704部队，北京 101100;空军工程大学航空航天工程学院，陕西西安 710038;空军工程大学航空航天工程学院，陕西西安 710038;空军工程大学航空航天工程学院，陕西西安 710038;中国人民解放军94175部队，新疆乌鲁木齐 830005

发布日期:2021-08-15
作者简介:王　磊(1983—)，男，博士生，研究领域为航空发动机综合数字控制。

Fault Diagnosis of Sensors in Distributed Control System Based on T-S Fuzzy KPCA Model

The Aeronautics and Astronautics Engineering Institute，Air Force Engineering University，Xi’an 710038，China; Unit 93704 of Chinese People’s Liberation Army，Beijing 101100，China;The Aeronautics and Astronautics Engineering Institute，Air Force Engineering University，Xi’an 710038，China;The Aeronautics and Astronautics Engineering Institute，Air Force Engineering University，Xi’an 710038，China;The Aeronautics and Astronautics Engineering Institute，Air Force Engineering University，Xi’an 710038，China;Unit 94175 of Chinese People’s Liberation Army，Urumchi 830005，China

Published:2021-08-15

摘要/Abstract

摘要： 为减小航空发动机多工况的工作特性和分布式控制系统非线性网络环境对故障诊断系统的影响，针对航空发动机分布式控制系统，提出一种基于T-S模糊KPCA模型的传感器故障诊断方法。首先采用C均值模糊聚类法，以油门杆角度为样本标签，对样本空间进行模糊分类，再通过模糊相似矩阵剔除各样本子空间的野值点；其次建立标称工况的KPCA模型，并利用训练样本对非标称工况的隶属度函数进行辨识，得到全工况T-S模糊KPCA模型；最后利用统计量[T2]和SPE对传感器故障进行检测，并采用数据重构方法对故障传感器进行隔离定位。仿真结果表明该方法对发动机的任意稳定工况具有自适应能力，能够在非线性网络环境下对正常样本和故障样本保持较低的虚警率和漏报率。当多个传感器同时发生故障时，能够准确找到故障源，实现对故障传感器的隔离。

关键词: 航空发动机；分布式控制系统；T-S模糊模型；核主元分析法；传感器故障诊断

Abstract: To reduce the effect of multi-operating conditions characteristic of aero-engine and the nonlinear network environment of distributed control system(DCS)on fault diagnosis system，a sensor fault diagnosis method for aero-engine distributed control system based on T-S fuzzy KPCA model was proposed. The fuzzy C-means clustering algorithm was applied to classify the sample space，in which the throttle lever angle was taken as the sample label. Then the outlier points were removed using the fuzzy similar matrix. Secondly，the KPCA model of nominal operating conditions was built. And the membership function of non-nominal operating conditions was identified with the training samples，then the T-S fuzzy KPCA model of full condition was built. Finally，the statistics [T2] and SPE were applied to detect the sensors fault. The faulted sensors were separated and located by data reconstruction. Simulation result shows that the proposed method is adaptive to any stable operating condition of aero-engine. Lower false alarm rate and missing alarm rate are retained under the nonlinear network conditions. When multiple sensors go wrong synchronously，this method could find and isolate the fault sensors.

Key words: Aero-engine；Distributed control system；T-S fuzzy model；Kernel principal component analysis；Sensor fault diagnosis

王　磊,谢寿生,任立通,余　坚,崔小军. 基于T-S模糊KPCA模型的分布式控制系统传感器故障诊断[J]. 推进技术, 2014, 35(7): 988-995.

WANG Lei^1,2,XIE Shou-sheng¹,REN Li-tong¹,YU Jian¹,CUI Xiao-jun³. Fault Diagnosis of Sensors in Distributed Control System Based on T-S Fuzzy KPCA Model[J]. Journal of Propulsion Technology, 2014, 35(7): 988-995.

参考文献

[1] 杨先勇, 周晓军, 张文斌, 等. 基于局域波法和KPCA-LSSVM的滚动轴承故障诊断 [J].浙江大学学报(工学版), 2010, 44(8): 1519-1524.
[2] Choi S W, Lee C K, Lee J M, et al.Fault Detection and Identification of Nonlinear Processes Based on Kernel PCA [J].Chemometrics and Intelligent Laboratory Systems, 2005, 75(1): 55-67.
[3] 祝志博, 宋执环. 融合FDA-PCMC样本分类的KPCA故障检测新算法 [J].控制与决策, 2010, 25(4): 542-545.
[4] Peiling Cui, Junhong Li, Guizeng Wang. Improved Kernel Principal Component Analysis for Fault Detection [J].Expert Systems with Applications, 2008, 34(5): 1210-1219.
[5] Mehrdad Pakmehr, Nathan Fitzgerald, George Kiwada, et al. Distributed Modeling and Control of Turbofan Systems[C]. Chicago: AIAA Guidance, Navigation, and Control Conference, 2009.
[6] 宋梅村, 蔡琦. 基于动态PCA的核动力装置传感器故障检测 [J].武汉理工大学学报, 2012, 36(6): 1184-1187.
[7] 仇韬, 张清峰, 丁艳军. PCA在非线性系统传感器故障检测和重构中的应用 [J].清华大学学报(自然科学版), 2006, 46(5): 708-711.
[8] Chunhui Zhao, Fuli Wang, Ningyun Lu, et al. Stage-Based Soft-Transition Multiple PCA Modeling and On-Line Monitoring Strategy for Batch Processes [J].Journal of Process Control, 2007, 17(5): 728-741.
[9] 齐咏生, 王普, 高学金, 等. 一种新的多阶段间歇过程在线监控策略 [J].仪器仪表学报, 2011, 32(6): 1290-1297.
[10] 齐咏生, 王普, 高学金. 基于核主元分析-主元分析的多阶段间歇过程故障监测与诊断 [J].控制理论与应用, 2012, 29(6): 754-764.
[11] 谢季坚, 刘承平. 模糊数学方法及其应用 [M].武汉:华中科技大学出版社, 2006.
[12] 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].控制工程, 2007, 27(4): 555-559.
[13] 杨帆, 李应红, 石斌, 等. 一种基于数据重构的KPCA故障识别方法[J].控制工程, 2007, 14(S1): 109-112.
[14] 王姝, 冯淑敏, 常玉清, 等. 改进的基于数据重构的KPCA故障识别方法 [J].东北大学学报(自然科学版), 2012, 33(4): 500-503.
[15] 蔡开龙. 航空推进系统分布式综合控制研究与试验 [D]. 西安: 空军工程大学, 2008.(编辑:梅瑛)收稿日期:2013-06-30；修订日期:2013-09-23。作者简介:王磊(1983—),男,博士生,研究领域为航空发动机综合数字控制。E-mail:zhongwei510@hotmail.com