Dynamic data rectification by recurrent neural networks vs. Traditional methods
Dynamic data rectification by recurrent neural networks vs. Traditional methods
复制标题
DOI：
10.1002/aic.690401110
复制
发表时间：
1994-11
期刊：
影响因子：
3.7
通讯作者：
T. Karjala;D. Himmelblau
中科院分区：
文献类型：
--
作者：
T. Karjala;D. Himmelblau
循环神经网络用于演示包含高斯噪声的过程测量的动态数据校正。将这些网络的性能与传统的扩展卡尔曼滤波方法以及用于数据协调的基于模型的非线性编程技术的已发布结果进行比较。与传统方法相比，循环网络架构即使不是更好，也能提供可比的结果。使用传统的非线性编程技术以批量方式对所使用的网络进行训练。
Recurrent neural networks are used to demonstrate the dynamic data rectification of process measurements containing Gaussin noise. The performance of these networks is compared to the traditional extended Kalman filtering approach and to published results for model-based nonlinear programming techniques for data reconciliation. The recurrent network architecture is shown to provide comparable, if not superior, results when compared to traditional methods. The networks used were trained using conventional nonlinear programming techniques in a batch fashion.