Output Over-Sampling Approach to Direct Closed-Loop Identification and Its Performance
Output Over-Sampling Approach to Direct Closed-Loop Identification and Its Performance
复制标题
DOI：
10.3182/20090706-3-fr-2004.00114
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Lianming Sun;A. Sano
中科院分区：
文献类型：
--
作者：
Lianming Sun;A. Sano
多项式输入输出递归模型以其灵活性和表征能力在非线性模型识别中得到了广泛的应用。文献中有几种基于不同标准的模型选择和参数估计的识别算法。先前的工作已经表明了经典预测误差最小化方法的局限性，并建议使用模拟误差最小化方法来更好地选择模型。本文进一步将模型选择过程与面向仿真的参数估计算法相结合。尽管所提出的方法的算法和计算复杂性，但它表明，相对于先前提出的方法，它可以实现显着的性能改进。
Abstract Polynomial input–output recursive models are widely used in nonlinear model identification for their flexibility and representation capabilities. Several identification algorithms are available in the literature dealing both with model selection and parameter estimation, based on various criteria. Previous works have shown the limits of the classical prediction error minimization approach, and suggested the use of a simulation error minimization approach for better model selection. The present paper goes a step further by integrating the model selection procedure with a simulation oriented parameter estimation algorithm. Notwithstanding the algorithmic and computational complexity of the proposed method, it is shown that it can achieve significant performance improvements with respect to previously proposed approaches.