Condition prediction of liquid propellant rocket engine based on process neural networks
-
摘要: 提出一种基于极限学习算法的离散过程神经网络模型,用于解决液体火箭发动机状态预测这一难题。首先,在历史数据的基础上建立离散过程神经网络(DPNN)预测模型;然后,根据在线更新的数据样本,采用递推极限学习(EL)算法对双并联前馈离散过程神经网络(DPFDPNN)隐层到输出层的权值进行更新,并应用权值更新后的过程神经网络对发动机状态进行预测;最后,以液体火箭发动机状态预测中氢涡轮泵扬程预测为例,分别采用有权值更新和无权值更新两种预测模型进行了试验。结果表明,通过更新过程神经网络权值可以使模型具有更高的预测精度和更好的适应能力,该方法能够为液体火箭发动机状态预测提供一种有效的解决途径。Abstract: Aimed at the problem of liquid propellant rocket engine condition prediction, a double parallel feedforward discrete process neural network (DPFDPNN) model based on extreme learning (EL) algorithm is proposed. The discrete process neural network (DPNN), which was trained via off-line data, is firstly adopted to make prediction of liquid propellant rocket engine condition. In order to improve the accuracy and efficiency of the DPNN for condition prediction, the weights connecting the hidden layer and output layer are then directly updated by the EL algorithm based on recursive algorithm with the real data stream. The corresponding computational steps are given and the DPNN with weights update is compared with the DPNN without weights update by predicting the lift of oxygen turbo pump. The result shows good accuracy and adaptibility of the DPNN with weights update and this work provides an effective way to solve the problem of liquid propellant rocket engine condition prediction.
-
[1] 彭宇,刘大同,彭喜元.故障预测与健康管理技术综述[J].电子测量与仪器学报,2010,24(1):1-9.PENG Y,LIU D T,PENG X Y.A review:Prognostics and health management[J].Journal of Electronic Measurement and Instrument,2010, 24(1):1-9(in Chinese) [2] 田路,张炜,杨正伟.Elman型神经网络在液体火箭发动机故障预测中的应用[J].弹箭与制导学报,2009,29(1):191-194.TIAN L,ZHANG W,YANG Z W.Application of Elman neural network on liquid rocket engine fault prediction[J].Journal of Projectiles,Rockets,Missiles and Guidance,2009,29(1):191-194(in Chinese). [3] 陈世立,陈新民.改进BP神经网络在冲压发动机性能预测中的应用[J].导弹与航天运载技术,2007(3):45-49.CHEN S L,CHEN X M.Improved BP neural network and its application in performance predicting of ramjet[J].Missile and Space Vehcile,2007(3):45-49(in Chinese). [4] 王晔,段志信.基于Matlab和BP神经网络的固体火箭发动机比冲性能的预测[J].内蒙古科技与经济,2007(8):73-74.WANG Y,DUAN Z X.Solid propellant rocket engine specific impulse performance predicting based on Matlab and BP neural network[J].Inner Mongolia Science Technology & Economy,2007(8):73-74(in Chinese). [5] 田干,张炜,杨正伟,等.SVM方法在火箭发动机故障预测中的应用研究[J].机械科学与技术,2010,29(1):63-67.TIAN G,ZHANG W,YANG Z W,et al.Study on SVM methods of liquid rocket engine fault prediction[J].Mechanical Science and Technology for Aerospace Engineering,2010,29(1):63-67(in Chinese). [6] 钟诗胜,李洋.基于小波过程神经网络的飞机发动机状态监视[J].航空学报,2007,28(1):68-71.ZHONG S S,LI Y.Condition monitoring of aeroengine based on wavelet process neural networks[J].Acta Aeronautica et Astronautica Sinica,2007,28(1):68-71(in Chinese). [7] 钟仪华,李榕,张志银,等.基于主成分分析的离散过程神经网络水淹层动态预测方法[J].测井技术,2010,34(5):432-437.ZHONG Y H,LI R,ZHANG Z Y,et al.Dynamic recognition method for water-flooded layer with discrete process neural network based on the principal component analysis[J].Well Logging Technology,2010,34(5):432-437(in Chinese). [8] 金向阳,林琳,钟诗胜,等.航空发动机振动趋势预测的过程神经网络法[J].振动、测试与诊断,2011,31(3):331-336.JIN X Y,LIN L,ZHONG S S,et al.Aeroengine vibration tendency prediction based on process neural network[J].Journal of Vibration,Measurement & Diagnosis,2011,31(3):331-336(in Chinese). [9] 宫唤春.基于双隐层径向基过程神经网络的汽轮机排汽焓在线预测[J].热力发电,2014,43(7):32-36.GONG H C.Double hidden layer RBF process neural network based online prediction of steam turbine exhaust enthalpy[J].Thermal Power Generation,2014,43(7):32-36(in Chinese). [10] 刘菲菲,彭荻,贺彦林,等.基于极限学习的过程神经网络研究及化工应用[J].上海交通大学学报,2014,48(7):977-981.LIU F F,PENG D,HE Y L,et al.Research and chemical application of extreme learning based process neural network[J].Joural of Shanghai Jiao Tong University, 2014,48(7):977-981(in Chinese). [11] 魏鹏飞,吴建军,刘洪刚.液体火箭发动机一种通用模块化仿真方法[J].推进技术,2005,26(2):147-150.WEI P F,WU J J,LIU H G.Investigation of a general model simulation method for liquid propellant rocket engine[J].Journal of Propulsion Technology, 2005,26(2):147-150(in Chinese). [12] 王建波,于达仁,王广雄.液体火箭发动机泄漏故障实时仿真[J].推进技术,1999,20(5):1-5.WANG J B,YU D R,WANG X.Real-time simulation of leak fault of liquid rocket engine[J].Journal of Propulsion Technology,1999,20(5):1-5(in Chinese). [13] 吴建军,张育林,陈启智.液体火箭发动机实时故障仿真系统实现[J].推进技术,1997,18(1):26-30.WU J J,ZHANG Y L,CHNE Q Z.The real-time fault simulation system for liquid propellant rocket engines[J].Journal of Propulsion Technology, 1997,18(1):26-30(in Chinese). [14] 钟诗胜,丁刚,付旭云.过程神经网络模型及其工程应用[M].北京:国防工业出版社, 2014:119-121.ZHONG S S,DING G,FU X Y.Process neural network models and its engineering applications[M].Beijing:National Defense Industry Press,2014:119-121(in Chinese). [15] HAGAN M T,MENHAJ M B.Training feedforward networks with the Marquardt algorithm[J].IEEE Transactions on Neutral Networks,1994,5(6):989-993. [16] HUANG G B,DING X J.Optimization method based on extreme learning machine for classification[J].Neurocomputing,2010,74(1):155-163. [17] LIANG N Y,HUANG G B, SARATCHANDRAN P, et al.A fast and accurate online sequential learning algorithm for feedforward networks[J].IEEE Transactions on Neural Networks,2006,17(6):1411-1423. [18] ZHANG R,LAN Y,HUANG G B.Universal approximation of extreme learning machine with adaptive growth of hidden nodes[J].IEEE Transactions on Neural Networks, 2012,23(2):365-371. [19] 谢光军.液体火箭发动机涡轮泵实时故障检测技术及系统研究[D].长沙:国防科学技术大学, 2006:1-3.XIE G J.Research on real-time fault detection technology and system for liquid rocket engine turbopump[D].Changsha:National University of Defense Technology,2006:1-3(in Chinese). [20] 夏鲁瑞.液体火箭发动机涡轮泵健康监控关键技术及系统研究[D].长沙:国防科学技术大学, 2010:1-3.XIA L R.Research on key technology and system for turbopump health monitoring of liquid rocket engine[D].Changsha:National University of Defense Technology,2010:1-3(in Chinese).
点击查看大图
计量
- 文章访问数: 904
- HTML全文浏览量: 69
- PDF下载量: 482
- 被引次数: 0