Identification of flexible nozzle torque properties based on wavelet neural network optimized by genetic algorithm
-
摘要:
为准确辨识负载力矩并提高主动加载负载模拟的真实度，使用了一种基于遗传算法优化的神经网络辨识方法。使用小波分析方法对测试信号进行预处理，将消噪与分解后得到的信息作为神经网络训练的扩充样本，提高了辨识精度。使用遗传算法选择最优输入信息、网络结构和隐含层规模，加快网络收敛速度并简化计算过程，实现对柔性喷管力矩的快速准确辨识。仿真结果表明该辨识方法可以准确地描述柔性喷管在典型测试信号激励下的力矩特性，平均辨识误差为2%，对于实现精确主动加载控制和验证伺服控制性能具有重要意义。
Abstract:In order to identify the load torque accurately and improve the authenticity of active load simulation，a neural network identification method based on genetic algorithm optimization was used.The wavelet analysis method was used to preprocess the test signal，and the information obtained after de⁃noising and decomposition was used as the expanded sample of neural network training，which improved the identification accuracy.The genetic algorithm was used to select the optimal input information，network structure and hidden layer scale，which can speed up the network convergence speed and simplify the calculation process，so as to realize rapid and accurate identification of the characteristics of flexible nozzle.The simulate results showed that this identification method can accurately reflect the torque characteristics of the flexible nozzle excited by typical test signal，with the average identification error of 2%，proving that it is of great significance to realize precise active load control and accurately verify the servo control performance.
-
Key words:
- servo system /
- flexible nozzle /
- system identification /
- neural network /
- wavelet analysis /
- genetic algorithm
-
图 2 线位移、伺服系统输出力矩和角位移随时间的变化关系
Figure 2. Variation relationship of linear displacement,output torque of servo system and angular displacement with time
图 3 低速摆动时角位移和负载力矩的关系
Figure 3. Relationship of angular displacement and load torque under low speed
图 5 基于拟合系数和神经网络的力矩特性辨识方法
Figure 5. Identification methodof torque properties based on fitting coefficient and neural network
图 6 BP神经网络对柔性喷管负载力矩的辨识结果
Figure 6. Identification results of load torque of flexible nozzle based on BP neural network
图 7 基于小波分析预处理的神经网络对柔性喷管负载力矩的辨识结果
Figure 7. Identification results of load torque of flexible nozzle based on neural network preprocessed by wavelet analysis
图 8 基于遗传算法优化柔性喷管力矩特性辨识网络的流程
Figure 8. Procedure of optimizing the torque properties identification network of flexible nozzle based on genetic algorithm
图 9 基于遗传算法优化的神经网络对柔性喷管负载力矩的辨识结果
Figure 9. Identification results of load torque of flexible nozzle based on neural network optimized by genetic algorithm
-
[1] 杨世学.柔性喷管频响特性及传递函数的分析计算[J].推进技术,1991,10（5）:7⁃15.YANG Shixue.Analysis and calculation of the frequency response characteristics and transfer function of flexible joint nozzle[J].Journal of Propulsion Technology,1991,10（5）:7⁃15.（in Chinese） [2] 刘志武.柔性接头频率特性的计算方法研究[J].固体火箭技术,1998,21（4）:18⁃21.LIU Zhiwu.Study on calculation method of frequency characteristics of flexible joint[J].Journal of Solid Rocket Technology,1998,21（4）:18⁃21.（in Chinese） [3] 史宏斌，侯晓，钟伟芳,等.固体发动机柔性喷管静态刚度和强度研究[J].宇航学报,2001,22（2）:45⁃50.SHI Hongbin,HOU Xiao,ZHONG Weifang,et al.Static stress and stiffness study of flexible nozzle in solid rocket motor[J].Journal of Astronautics,2001,22（2）:45‑50.（in Chinese） [4] 郑开发，王超，郝文强,等.柔性接头迟滞阻尼特性识别[J].航空动力学报,2017,32（2）:486⁃491.ZHENG Kaifa,WANG Chao,HAO Wenqiang,et al.Identification of flexible joint hysteresis damping characteristics[J].Journal of Aerospace Power,2017,32（2）:486⁃491.（in Chinese） [5] 张晓光，刘宇，任军学,等.小型柔性接头推力矢量性能试验[J].航空动力学报,2012,27（12）:2836⁃2841.ZHANG Xiaoguang,LIU Yu,REN Junxue,et al.Experimental investigation of miniature flexible joint thrust vector characteristics[J].Journal of Aerospace Power,2012,27（12）:2836⁃2841.（in Chinese） [6] 王超，任军学，郝文强，等.柔性接头有效摆心漂移特性[J].航空动力学报,2014,29（12）:2993⁃2999.WANG Chao,REN Junxue,HAO Wenqiang,et al.Characteristics of effective pivot point excursion for flexible joint[J].Journal of Aerospace Power,2014,29（12）:2993⁃2999.（in Chinese） [7] 杨敬贤，王超，任军学，等.小型柔性接头力矩特性数值与试验研究[J].固体火箭技术,2015,38（4）:497⁃502.YANG Jingxian,WANG Chao，REN Junxue,et al.Numerical and experimental investigation on properties of miniature flexible joint torque[J].Journal of Solid Rocket Technology,2015,38（4）:497⁃502.（in Chinese） [8] 苏浩，任军学，王雨玮，等.柔性接头摩擦特性与橡胶损耗模量相关性研究[J].固体火箭技术,2017,40（2）:164⁃168.SU Hao,REN Junxue,WANG Yuwei,et al.Study on the correlation between friction properties of flexible joint and loss modulus of rubber[J].Journal of Solid Rocket Technology,2017,40 （2）:164⁃168.（in Chinese） [9] 苏浩，任军学，郑开发，等.温度对小型柔性接头力矩特性的影响[J].航空动力学报,2017,32（4）:976⁃982.SU Hao,REN Junxue,ZHENG Kaifa,et al.Influence of temperature on torque properties of miniature flexible joint[J].Journal of Aerospace Power,2017,32（4）:976⁃982.（in Chinese） [10] ZADEH L A.From circuit theory to system theory[J].Proceedings of the Institute of Radio Engineers,1962,50 （5）:856⁃865. [11] 王琳，马平.系统辨识方法综述[J].电力情报,2001（4）:63‑66.WANG Lin,MA Ping.Review on methods of system identification[J].Information on Electric Power,2001（4）:63⁃66.（in Chinese） [12] 徐小平，王峰，胡刚.系统辨识研究的现状[J].自动化技术,2007,15:112⁃116.XU Xiaoping,WANG Feng,HU Gang.A survey on system identification[J].Techniques of Automation,2007,15:112⁃116.（in Chinese） [13] 许世景.神经网络在系统辨识中的应用研究[J].山西电子技术,2007,1:7⁃8.XU Shijing.Application of neural network in system identification[J].Shanxi Electronic Technology,2007,1:7⁃8.（in Chinese） [14] 李秀英，韩志刚.非线性系统辨识方法的新进展[J].自动化技术与应用,2004,23（10）:5⁃7.LI Xiuying,HAN Zhigang.Advances in nonlinear system identification[J].Techniques of Automation and Applications,2004,23（10）:5⁃7.（in Chinese） [15] 张广莹，邓正隆.小波分析在系统辨识中的应用[J].电机与控制学报,2002,6（1）:64⁃67.ZHANG Guangying,DENG Zhenglong.Applications of wavelet analysis in system identification[J].Electric Machines and Control,2002,6（1）:64⁃67.（in Chinese） [16] 李小玉.基于小波分析和遗传神经网络的模拟电路故障诊断[D].长沙:湖南大学,2012.LI Xiaoyu.Analog circuit fault diagnosis based on wavelet analysis and genetic neural network[D].Changsha:Hunan University,2012.（in Chinese） [17] 杨国军，崔平远，李琳琳.遗传算法在神经网络控制中的应用与实现[J].系统仿真学报,2001,13（5）:567⁃570.YANG Guojun,CUI Pingyuan,LI Linlin.Applying and realizing of genetic algorithm in neural networks control[J].Journal of System Simulation,2001,13（5）:567⁃570.（in Chinese） [18] 张庆红，程国建.基于遗传算法的神经网络性能优化[J].计算机技术与发展,2007,17（12）:125⁃127.ZHANG Qinghong,CHENG Guojian.Neural network optimization based on genetic algorithms[J].Computer Technology and Development,2007,17（12）:125⁃127.（in Chinese） -
下载:
点击查看大图
计量
- 文章访问数: 98
- HTML浏览量: 32
- PDF量: 37
- 被引次数: 0