[1]高强,金勇,侯远龙,等.某扫雷车扫雷犁电液伺服系统辨识与控制[J].南京理工大学学报(自然科学版),2012,36(02):238-244.
 GAO Qiang,JIN Yong,HOU Yuan-long,et al.Modeling and Control for Mine Sweeping Plough Electro-hydraulic Servo System of Certain Mine-clearing Vehicle[J].Journal of Nanjing University of Science and Technology,2012,36(02):238-244.
点击复制

某扫雷车扫雷犁电液伺服系统辨识与控制
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
36卷
期数:
2012年02期
页码:
238-244
栏目:
出版日期:
2012-04-30

文章信息/Info

Title:
Modeling and Control for Mine Sweeping Plough Electro-hydraulic Servo System of Certain Mine-clearing Vehicle
作者:
高强; 金勇; 侯远龙; 季丽君;
南京理工大学机械工程学院; 总装备部工程兵军代局武汉军代室;
Author(s):
GAO Qiang1JIN Yong2HOU Yuan-long1JI Li-jun1
1.School of Mechanical Engineering,NUST,Nanjing 210094,China; 2.Military Representative Office of the General Armaments Department in Wuhan Area,Wuhan 430073,China
关键词:
扫雷车 扫雷犁 电液伺服系统 神经网络 在线辨识 离线辨识 自适应控制
Keywords:
mine-clearing vehicles mine sweeping ploughs electro-hydraulic servo system neural network on-line modeling off-line modeling adaptive control
分类号:
TJ518
摘要:
针对某扫雷车扫雷犁电液伺服系统存在非线性及时变性的问题,研究了其辨识和控制方案。提出了离线训练与在线微调相结合的神经网络辨识方案,较好地解决了反向传播BP神经网络易陷入局部最小的问题,加速了网络的收敛速度,且离线训练后的权值参数为合理值,避免了在线微调时的振荡现象。研究了神经网络间接模型参考自适应控制方案,该方案利用神经网络在线辨识器为神经网络控制器实时提供梯度信息,使神经网络控制器的学习修正能够正常进行。仿真研究和样机试验结果证明了所提出辨识和控制方案的有效性和正确性。
Abstract:
To control the nonlinearity and time-variation of the mine sweeping plough electro-hydraulic servo system in a certain mine-clearing vehicle,the modeling and control techniques are studied here.First,the neural network identification scheme of the off-line training and on-line minor adjustment is presented.The scheme can offer a better solution to the problem that the back-propagation(BP)neural network is easy to fall into the local minimum and accelerate the convergence of BP algorithm.By keeping the weight value reasonable after the off-line training,the scheme avoids the oscillation when using the on-line minor adjustment.Secondly,the neural network model reference adaptive control is introduced.The on-line neural network identifier offers the real-time gradient information to the neural network controller to guarantee its proper learning and modification.The results of the simulation and the prototype test prove that the proposed modeling scheme and control scheme are effective and suitable.

参考文献/References:

[1] Vossoughi G. Nonlinear analysis and control of electro-hydraulic servo system[A]. Proceedings of the 2nd Biennial European Joint Conference on Engineering Systems Design and Analysis[C]. New York,USA: American Society of Mechanical Engineers, 1994: 59-67.
[2] Bennett S. Brief history of servomechanisms[J]. IEEE Control System Magazine, 1994, 14: 75-79.
[3] Kalyoncu M,Haydim M. Mathematical modelling and fuzzy logic based position control of an electrohydraulic servosystem with internal leakage[J]. Mechatronics, 2009, 19( 6) : 847-858.
[4] 方一鸣,韩永成,赵琳琳,等. 控制量前具有不确定系数的电液伺服系统自适应控制[J]. 控制理论与应用, 2009, 26( 2) : 156-160.
[5] 倪敬,彭丽辉,项占琴. 扩轧管电液伺服系统非线性建模与控制[J]. 机械工程学报,2009,45 ( 5) : 250 -255.
[6] Zhang Xingzhong. H∞ tracking control to electrohydraulic servo system of continuous casting mould based on fuzzy models[A]. The Proceedings of the Fifth World Congress on Intelligent Control and Automation[C]. Hangzhou, China: IEEE, 2004: 769-772.
[7] 姚建均,王立权,王贤成,等. 基于人工神经网络的电液伺服系统加速度谐波辨识[J]. 兵工学报, 2009, 30( 5) : 633-638.
[8] He S,Sepehri N. Modeling and prediction of hydraulic servo actuators with neural networks[A]. Proceedings of American Control Conference[C]. San Diego,USA: IEEE, 1999: 3708-3712.
[9] 张秀玲. 液压弯辊系统的优化神经网络内模控制[J]. 中国机械工程, 2007, 18( 20) : 2419-2421.
[10] 温肇东,王占林,祁晓野,等. 复合舵机的神经网络自校正控制[J]. 北京航空航天大学学报,2007,33 ( 11) : 1295-1298.
[11] Akpan V A,Hassapis G. Adaptive predictive control using recurrent neural network identification[A]. 17th Mediterranean Conference on Control and Automation [C]. Thessaloniki,Greece: IEEE, 2009: 61-66.
[12] Larrea M, Irigoyen E,Gómez V, et al. Nonlinear system control based on neural networks with adaptive predictive strategy[A]. 2010 IEEE Conference on Emerging Technologies and Factory Automation[C]. Bilbao,Spain: IEEE, 2010: 1-7.
[13] Pei Zhongcai,Zhang Yanfang,Tang Zhiyong. Model reference adaptive PID control of hydraulic parallel robot based on RBF neural network[A]. 2007 IEEE International Conference on Robotics and Biomimetics [C]. Sanya,China: IEEE, 2007: 1383-1387.
[14] Faouzi B,Abderrazak C,Tarek G. Internal model control using neural networks[A]. 2004 IEEE International Conference on Industrial Technology[C]. Hammamet,Tunisia: IEEE, 2004,2 : 1121-1126.
[15] Mohieddine J,Andreas K. Hydraulic servo-system modeling, identification and control[M]. London: Springer- Verlag London Limited,Library of Congress Catalogingin- Publication, 2003: 132-134.

更新日期/Last Update: 2012-10-12