[1]傅春啸,屈天祥,滕 飞,等.基于 DCNN 的无人直升机自转过程建模[J].机械与电子,2022,(03):8-12.
　FU Chunxiao,QU Tianxiang,TENG Fei,et al.Modeling of Unmanned Helicopter Autorotation Process Based on DCNN[J].Machinery & Electronics,2022,(03):8-12.
点击复制

基于 DCNN 的无人直升机自转过程建模()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2022年03期
页码:
8-12
栏目:
设计与研究
出版日期:
2022-03-25

文章信息/Info

Title:
Modeling of Unmanned Helicopter Autorotation Process Based on DCNN
文章编号:
1001-2257 ( 2022 ) 03-0008-05
作者:
傅春啸; 屈天祥; 滕 飞; 盛守照
南京航空航天大学自动化学院,江苏 南京 210016
Author(s):
FU Chunxiao ;  QU Tianxiang ;  TENG Fei ;  SHENG Shouzhao
( College of Automation Engineering , Nanjing University of Aeronautics and Astronautics , Nanjing 210016 , China )
关键词:
深度卷积神经网络; 直升机自转降落; 系统辨识
Keywords:
deep convolutional neural network ( DCNN );  helicopter autorotation landing ;  system identification
分类号:
TP391 ; V275.1
文献标志码:
A
摘要:
针对小型无人直升机自转着陆过程,在已有的加速度预测模型的基础上,提出了利用深度卷积神经网络来表示系统自转飞行过程中的隐藏状态(气流以及直升机的抖动的影响)。通过与实际自转着陆飞行数据进行对比测试,改进后的模型可以更好地预测各个状态的变化,精度得到了明显提升。
Abstract:
Aiming at the autorotation landing process of small unmanned helicopter , based on the existing acceleration prediction model , a deep convolution neural network is proposed to represent the hidden state(the influence of air flow and helicopter jitter ) in the dynamic flight process of the system.Compared with the actual autorotation landing flight data , the improved model can better predict the changes of each state , and the accuracy has been significantly improved.

参考文献/References:

[ 1 ] 杨慧萍,高贯斌,那靖 . 三自由度直升机实验平台及姿态跟踪控制器设计[ J ] . 机械与电子, 2015 ( 5 ): 69-72.

[ 2 ] 黄正,魏琼,张金姣 . 三旋翼飞行器建模及自抗扰控制[ J ] . 电光与控制, 2021 , 28 ( 6 ): 20-24.
[ 3 ] TANG S , ZHENG Z Q , QIAN S K , et al.Nonlinear system identification of a small-scale unmanned helicopter [ J ] .Control engineering practice , 2004 , 25 : 1-15.
[ 4 ] 孙涛,宋彦国,张呈林 . 模型直升机悬停状态下飞行力学模型辨识[ J ] . 航空学报, 2009 , 30 ( 1 ): 40-45.
[ 5 ] LAI G Y , LIU Z , ZHANG Y , et al.Adaptive position / attitude tracking control of aerial robot with unknown inertial matrix based on a new robust neural identifier[ J ] .IEEE Transactions on neural networks and learning systems , 2016 , 27 ( 1 ): 18-31.
[ 6 ] ABBEEL P , COATES A. , Y.NG A.Autonomous helicopter aerobatics through apprenticeship learning [ J ] . The international journal of robotics research , 2010 , 29( 13 ):1608-1639.
[ 7 ] SETU S , ABHISHEK A , VENKATESAN C.Time domain system identification of helicopters using nonlinear acceleration and jerk prediction model [ J ] .Journal of aircraft , 2019 , 56 ( 3 ): 1272-1280
[ 8 ] LECUN Y , BENGIO Y , HINTON G.Deep learning[ J ] .Nature , 2015 , 521 : 436-444.
[ 9 ] SCHMIDHUBER J.Deep learning in neural networks : an overview [ J ] Neural networks , 2015 , 61 : 85-117.
[ 10 ] KEOGH E.Exact indexing of dynamic time warping [ C ] //28th International Conference on Very Large Data Bases , 2002 : 406-417.
[ 11 ] KANG Y , CHEN S F , WANG X F,et al.Deep convolutional identifier for dynamic modeling and adaptive control of unmanned helicopter [ J ] .IEEE Transactions on neural networks and learning systems , 2019 , 30 ( 2 ): 524-538.

相似文献/References:

[1]吉 哲,吕 飞,王 冕.基于优化 VMD 和深度卷积神经网络的柴油发电机组故障诊断[J].机械与电子,2023,41(08):8.
　JI Zhe,LYU Fei,WANG Mian.Fault Diagnosis of Diesel Generator Set Based on Optimized VMD and Deep Convolution Neural Network[J].Machinery & Electronics,2023,41(03):8.

备注/Memo

备注/Memo:
收稿日期: 2021-09-03
作者简介:傅春啸 ( 1997- ),男,浙江绍兴人,硕士研究生,研究方向为飞行器控制;屈天翔 ( 1996- ),男,河南洛阳人,硕士研究生,研究方向为飞行器控制;滕 飞 ( 1997- ),男,江苏扬州人,硕士研究生,研究方向为导航制导与控制;盛守照 ( 1977- ),男,江苏南京人,教授,博士研究生导师,研究方向为无人机飞行控制与仿真、电动伺服控制技术、液压伺服技术。
更新日期/Last Update: 2022-03-23