基于BP神经网络模型的柔性喷管动力学仿真  

Dynamic Simulation of Flexible Nozzle Based on BP Neural Network Model

作　　者：薛牧遥 胡嘉鑫 张金尧 童悦 李修明 郑庆 任军学[2] XUE Muyao;HU Jiaxin;ZHANG Jinyao;TONG Yue;LI Xiuming;ZHENG Qing;REN Junxue(Shanghai Space Propulsion Technology Research Institute,Shanghai 200125,China;School of Astronautics,Beihang University,Beijing 100191,China)

机构地区：[1]上海航天动力技术研究所,上海200125 [2]北京航空航天大学宇航学院,北京100191

出　　处：《弹箭与制导学报》2021年第3期109-114,共6页Journal of Projectiles,Rockets,Missiles and Guidance

摘　　要：为实现柔性喷管模型在不同摆动振幅、摆动频率、工作压强下更为精确的位置精度控制,基于BP神经网络模型,构造了电液伺服机构-神经网络模型,对柔性喷管摆动迟滞曲线进行模拟,并与实验结果及其它物理模型进行对比。研究表明:电液伺服机构-神经网络模型对迟滞曲线的预测结果与实验结果相吻合,具有很好的仿真精度和泛化能力,为柔性喷管的控制系统设计提供较精确的喷管动力学模型。To achieve a better position accuracy control for flexible nozzle system under different swing amplitude,swing frequency and operating pressure,an electro-hydraulic servo mechanism-neural network model is constructed in this paper.And it is compared with experiment results as well as other physical models.The researches show that the model results of electro-hydraulic servo mechanism-neural network model have a good agreement results with experiment results.The model has good simulation accuracy,generalization ability and can provide accurate dynamic model for flexible nozzle control.

关 键 词：柔性喷管 电液伺服机构 神经网络 迟滞曲线 

分 类 号：V430[航空宇航科学与技术—航空宇航推进理论与工程]