吉林大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (2): 577-582.doi: 10.13229/j.cnki.jdxbgxb201702032

• • 上一篇    下一篇

SI发动机闭环系统故障检测

邓丽飞1, 石要武1, 朱兰香2, 于丁力3   

  1. 1.吉林大学 通信工程学院,长春 130022;
    2.长春建筑学院 电气信息学院,长春 130604;
    3.利物浦约翰莫尔大学 技术与环境学院, 利物浦 L35UX
  • 收稿日期:2015-10-13 出版日期:2017-03-20 发布日期:2017-03-20
  • 通讯作者: 朱兰香(1965-),女,副教授.研究方向:发动机控制,信号处理.E-mail:519007262@qq.com
  • 作者简介:邓丽飞(1986-),女,博士研究生.研究方向:发动机控制,模式识别与智能系统,信号处理.E-mail:denglifei1987@163.com
  • 基金资助:
    国家自然科学基金项目(11104020).

Failure detection of closed-loop systems and application to SI engines

DENG Li-fei1, SHI Yao-wu1, ZHU Lan-xiang2, YU Ding-li3   

  1. 1.College of Communication Engineering, Jilin University,Changchun 130022, China;
    2.College of Electrical Information,Changchun Architecture and Civil Engineering University, Changchun 130604, China;
    3.School of Technology and Environment, Liverpool John Moores University, Liverpool L35UX,U.K.
  • Received:2015-10-13 Online:2017-03-20 Published:2017-03-20

摘要: 现有的发动机故障检测与隔离方法均是基于开环控制,在闭环控制系统下并不适用,本文研究了一种新的闭环控制系统故障检测和隔离方法。针对现有的故障检测方法是对发动机进行实机测试这一问题,对SI发动机进行了非线性仿真,模拟发动机的不同故障,仿真实验验证了该方法的有效性。建立了基于人工神经网络的发动机气路模型,利用RBF神经网络对SI发动机进行建模,分析了神经网络模型训练数据采集的缺点,提出了一种新的数据采集方法,大大提高了模型精度。

关键词: 控制理论与控制工程, 故障检测, 汽车发动机, 闭环故障检测, 独立的RBF模型

Abstract: The existing methods of engine fault detection and isolation are based on open-loop control, which are not applicable to closed-loop control systems. In this paper a new fault detection and isolation method for closed-loop control systems is presented. The validity of this method is verified by simulation results. First, the method was tested on the nonlinear simulation of SI engines, the Mean Value Engine Model (MVEM) with different faults was simulated. The neural network based engine air path model was constructed, which was trained with engine input/output data. Then Radial Basis Function (RBF) neural network was used to model the SI engine. The drawback of the training data acquisition was analyzed and a new data acquisition method was proposed, that greatly improved the model accuracy.

Key words: control theory and control engineering, fault detection, automotive engines, closed-loop fault detection, independent RBF model

中图分类号: 

  • TP273
[1] Gertler J, Costin M, Fang X,et al. Model based on board fault detection and diagnosis for automotive engines[J]. Control Engineering Practice, 1993,1(1) :3-17.
[2] Gertler J, Costin M, Fang X, et al. Model based diagnosis for automotive engines—algorithm development and testing on a production vehicle[J]. IEEE Trans on Control Systems Technology, 1995,3(1):161-169.
[3] Blanke M, Patton R J. Industrial actuator benchmark for fault detection and isolation[J].Control Engineering Practice, 1995,3(12):1727-1730.
[4] Isermann R. Model-based fault-detection and diagnosis status and applications[J].Annual Reviews in Control, 2005, 29:71-85.
[5] Caprigline D,Liguori C,Pianse C,et al. On-line sensor fault detection, isolation,and accommodation in automotive engines[J].IEEE Trans on Instrumentation and Measurement,2003,52(4):1182-1189.
[6] Caprigline D, Liguori C, Pianse C, et al. Analytical redundancy for sensor fault isolation and accommodation in public transportation vehicles[J].IEEE Trans on Instrumentation and Measurement, 2004,53(4):993-999.
[7] Aprigline D,Liguori C,Pietrosanto A. Real-time implementation of IFDIA scheme in automotive systems[J]. IEEE Trans on Instrumentation and Measurement,2007,56(3):824-830.
[8] 吴志虎,刘志远,裴润.基于模型的汽车发动机速度滚动优化控制[J]. 吉林大学学报:工学版,2009,39(6):1579-1581.
Wu Zhi-hu, Liu Zhi-yuan, Pei Run. Model based moving horizon optimization control of automotive engine speed[J].Journal of Jilin University(Engineering and Technology Edition), 2009,39(6):1579-1581.
[9] Hendricks E, Engler D, Fam M. A generic mean value engine model for spark ignition engines[R]. Proceedings of 41st Simulation Conference,Institute of Automation, Denmark,DUT Lyngby,2000:5192-5218.
[10] 董恩增,陈增强,袁著祉.基于神经网络PID控制器的混沌系统控制与同步[J]. 吉林大学学报:工学版,2007,37(3):646-650.
Dong En-zeng, Chen Zeng-qiang, Yuan Zhu-zhi. Control and synchronization of chaos systems based on neural network PID controller[J]. Journal of Jilin University(Engineering and Technology Edition), 2007,37(3):646-650.
[1] 范成岩, 许树新, 王洪军, 孟繁忠. 三轴正时链系统的磨损及其限定条件[J]. 吉林大学学报(工学版), 2017, 47(1): 122-128.
[2] 曾小华, 蒋渊德, 宋大凤, 彭宇君, 杨南南. 诊断算法在混合动力汽车能量管理策略中的集成开发[J]. 吉林大学学报(工学版), 2016, 46(4): 1030-1037.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!