基于动态云BP网络的液体火箭发动机故障诊断方法
Fault diagnosis method for liquid-propellant rocket engines based on the dynamic cloud-BP neural network
-
摘要: 将云模型与BP(back propagation)神经网络以串联方式有机结合,首先利用云变换方法进行网络的结构辨识和云模型的特征提取,同时通过在输入层引入单位延时环节描述发动机工作过程动态特性,研究提出了基于动态云BP网络的液体火箭发动机故障诊断方法.结合实际试车数据的验证结果表明,该方法能够准确识别发动机已有的3种故障模式,通过在试车数据中添加0期望、0.2标准差的随机噪声的方法来模拟环境噪声和测试过程中产生的随机噪声,根据持续性原则,方法仍能够正确进行故障检测与分类.方法单步运行时长为1.124×10-4s,完全能够满足实时性要求.Abstract: A fault diagnosis method for liquid-propellant rocket engines was proposed based on the dynamic cloud-BP(back propagation) neural network in the way of the integration of cloud model and BP neural network. The Cloud transform method was used to identify the network configuration and to extract the cloud features. And a unit time-delay was also introduced into the input layer to describe the dynamic characteristics of the engine. Results with test data show that the method can isolate the existed 3 fault modes precisely. A 0 expectation, 0.2 standard deviation noise was used to simulate the entironmental noise and stochastic noise, and the method can still detect and classify the fault accurately acount to lasting-rule. The method can run in real-time with the single processing time being 1.124×10-4s.
-
Key words:
- liquid-propellant rocket engine /
- fault diagnosis /
- cloud model /
- neural network /
- fault mode
-
[1] 李德毅,孟海军.隶属云和隶属云发生器[J].计算机研究与发展,1995,32(6):15-20.LI Deyi,MENG Haijun.Membership cloud and membership cloud generators[J].Computer Research & Development,1995,32(6):15-20.(in Chinese) [2] 李德毅.三级倒立摆的云控制方法及动平衡模式[J].中国工程科学,1999,1(2):41-46.LI Deyi.The cloud control method and balancing patterns of triple link inverted pendulum systems [J].Engineering Science,1999,1(2):41-46.(in Chinese) [3] 张飞舟,范跃祖,沈程智,等.利用云模型实现智能控制倒立摆[J].控制理论与应用,2000,17(4):519-523.ZHANG Feizhou,FAN Yuezu,SHEN Chengzhi,et al.Intelligent control inverted pendulum with cloud models [J].Control Theory and Applications,2000,17(4):519-523.(in Chinese) [4] 李德毅,邸凯昌.用语言云模型发掘关联规则[J].软件学报,2000,11(2):143-158.LI Deyi,DI Kaichang.Mining association rules with linguistic cloud models[J].Journal of Software,2000,11(2):143-158.(in Chinese) [5] 徐宗本,樊忠泽.基于云神经网络的空间推进系统故障检测与诊断[J].兵工学报,2009,30(6):727-732.XU Zongben,FAN Zhongze.Cloud neural network based fault detction and diagnosis of space propulsion system[J].Acta Armamentarii,2009,30(6):727-732.(in Chinese) [6] 黄强,吴建军.基于云-神经网络的液体火箭发动机故障检测方法[J].国防科技大学学报,2010,32(1):11-15.HUANG Qiang,WU Jianjun.Fault detection method based on cloud-neural network of liquid-propellant rocket engine[J].Journal of National University of Technology,2010,32(1):11-15.(in Chinese) [7] 田永清.基于云模型的数据挖掘算法的研究与应用[D].上海:上海交通大学,2003.TIAN Yongqing.Research and application of data mining based on cloud model [D].Shanghai:Shanghai Jiaotong University,2003.(in Chinese) [8] 柳炳祥,李海林.基于云理论与神经网络集成的模糊系统[J].计算机应用,2008,36(2):305-306,310.LIU Bingxiang,LI Hailin.Induction of fuzzy system based on cloud theory and neural network[J].Computer Applications,2008,36(2):305-306,310.(in Chinese) [9] 蒋嵘,李德毅.数值型数据的泛概念树的自动生成方法[J].计算机学报,2000,23(5):470-476.JIANG Rong,LI Deyi.Automatic generation of pan-concept-tree on numerical data [J].Chinese J Computers,2000,23(5):470-476.(in Chinese) [10] 葛哲学,孙志强.神经网络理论与MATLAB2007实现[M].北京:电子工业出版社,2007. [11] 秦昆,王佩.基于云变换的曲线拟合新方法[J].计算机工程与应用,2008,44(23):56-74.QIN Kun,WANG Pei.New method of curve fitting based on cloud transform[J].Computer Engineering and Applications,2008,44(23):56-74.(in Chinese) [12] 范大鹏,王雪丹.云模型方法在选煤厂跳汰系统中的故障检测与诊断[J].黑龙江科技学院学报,2011,21(4):289-292.FAN Dapeng,WANG Xuedan.Fault detection and diagnosis for coal preparation plant jigging system based on cloud model and information fusion[J].Journal of Heilongjiang Institute of Science & Technology,2011,21(4):289-292.(in Chinese) [13] 刘洪刚,魏鹏飞,谢廷峰,等.液体火箭发动机地面试车过程的实时故障检测方法研究[J].宇航学报,2007,28(6):1660-1664.LIU Honggang,WEI Pengfei,XIE Tingfeng,et al.Research of real-time fault detction method for liquid propellant rocket engines in ground test[J].Journal of Astronautics,2007,28(6):1660-1664.(in Chinese) [14] LIU Honggang,XIE Tingfeng,et al.A real-time fault detection and post-test diagnosis system for liquid-propellant rocket engines in ground tests[C]//58th International Astronautical Congress.Hyderabad,India:[s.n.],2007:24-28. [15] LIU Honggang,XIE Tingfeng,HUANG Qiang,et al.Real-time on-line fault detection algorithm for liquid-propellant rocket engines[R].Beijing:2007 International Symposium on Space Propulsion,2007.
点击查看大图
计量
- 文章访问数: 1630
- HTML浏览量: 0
- PDF量: 1236
- 被引次数: 0