航空发动机神经网络内模控制

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名

邮箱

手机号码

标题

留言内容

验证码

Application of Internal Model Control System Based on Neural Network in Aeroengine

College of Energy and Power,Nanjing University of Aeronautics and Astronautics,Nanjing210016,China

摘要: 基于神经网络内模控制理论研究了神经网络内模控制方法在航空发动机控制系统中的应用,建立了基于Elman网络的航空发动机多变量内模控制系统。采用Elman网络建立发动机内模型和内模控制器,详细介绍了建模、控制的算法及其实现过程。取部分飞行条件下的数据作为学习样本,采用动态BP算法对神经网络权值进行调整,并在飞行包线内其它工作点对整个控制系统进行了仿真。结果表明,使用神经网络建立的航空发动机内模控制系统具有良好的控制品质和较强的自适应能力。
- 航空、航天推进系统 /
- 航空发动机 /
- 内模控制 /
- Elman神经网络 /
- 多变量控制
Abstract: The Internal Model Control(IMC) system based on recurrent neural network and its application to aeroengines were studied.An aeroengine multivariable control system was developed using neural network IMC method.Both the aeroengine internal model and the controller were constructed via Elman neural networks.A recurrent back-propagation algorithm was used to train the weights of the neural network and the control algorithm was analyzed.Numerical simulation results show the effectiveness of this method and self-learning ability of the system.
- aerospace propulsion system /
- aeroengine /
- Internal Model Control(IMC) /
- elman neural network /
- multivariable control

点击查看大图