介绍一种FIR神经网络模型及其时变反传算法,并把它用于纯滞后非线性MIMO系统模型辨识;以带钢热连轧受控对象为例,建立2机架的小偏差模型,并进行了仿真;使用FIR神经网络模型对仿真数据进行了模型辨识,辨识结果显示了网络良好的性能.
参考文献
| [1] | Wan E A .Times Series Prediction by Using a Connectionist Network With Internal Delay Lines[Z].Times Series Prediction: Forecasting the Future and Understanding the Past,1993. |
| [2] | Wan E A.Temporal Backpropagation for FIR Neural Networks[M].Neural Networks,IJCNN International Joint Conference,1990:575-580. |
| [3] | Stanislav Kaleta;Daniel Novotny;Peter Sincak.Prediction Systems Based on FIR BP Neural Networks[A].Vienna,Austria,2001:725-730. |
| [4] | Hee-yeal Yu;Bang S Y .An Improved Time Series Prediction by Applying the Layer-by-layer Learning Method to FIR Neural Networks[J].International Conference on Neural Information Processing,Hong Kong,1996,2:771-776. |
| [5] | 孙一康.带钢热连轧的模型与控制[M].北京:冶金工业出版社,2002 |
| [6] | 王粉花 .二机架可逆冷连轧板厚板形综合控制系统的研究[D].北京科技大学,2003. |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%