|
|
|
| Study on Identification Hammerstein Model of Transducer Based on Improved FLANN |
| LIU Tao1,HAN Hua-ting1,MA Jing2,LEI Chao1 |
1.Air Defense and Antimissile Institute, Air Force Engineering University, Xi’an, Shaanxi 710051, China;
2.Science and Technology on Information Assurance Laboratory, Beijing 100072, China |
|
|
|
|
Abstract For identification nonlinear dynamic model of transducer, a method for the nonlinear system one-stage identification by using functional link artificial neural network (FLANN) algorithm is proposed. The nonlinear system is described as a polynomial expression, combining the differential equation of dynamic system to build discrete data expression of input to output, solving the unknown parameters of the model by FLANN training. The convergence speed and the stability of convergence of FLANN algorithm is improved through variable learning factor. Experimental results show that the improved FLANN is simple and effective and has higher convergence rate.
|
|
|
|
|
|
［1］Jung L. System identification: theory for the user (2nd Edition)［M］. New Jersey: Prentice Hal,1999,3-20.
［2］黄正良,万百五,韩崇昭. 辨识Hammerstein模型的两步法［J］.控制理论与应用,1995.12(1):34-38.
［3］徐科军,殷铭.基于FLANN的腕力传感器动态建模方法［J］.仪器仪表学报,2000,20(1):91-94.
［4］吴德会,等.传感器动态建模FLANN方法改进研究［J］.仪器仪表学报,2009, 2(30):362-367.
［5］冯培悌.系统辨识［M］.杭州:浙江大学出版社,1999,3-13.
［6］贾林.传感器动态非线性建模和补偿研究［D］.合肥:合肥工业大学,2003.
［7］李治涛,韩景龙,员海玮.基于Hammerstein模型的非线性气动弹性系统辨识［J］.南京航空航天大学学报,2013,2(45):14-20.
［8］吴德会.基于支持向量机的非线性动态系统辨识方法［J］.系统仿真学报,2007,19(14): 3169-3171. |
|
|
|
2015, Vol. 36 
