带有工况中心修正的多模型在线建模
Online modeling for multi-model by adjusting the centers of operating ranges
查看参考文献11篇
文摘
|
针对运行工况频繁波动、单一模型难以描述过程特性的问题, 提出了带有工况中心修正的多模型在线建模方案, 包括工况识别机制、局部模型、多模型合成机制. 工况识别机制根据工况特征变量分析工况范围, 由相近度修正工况中心; 局部模型采用Hammerstein模型, 非线性增益由带有稳定学习算法的小波神经网络建立, 线性模型由带控制量的自回归模型(ARX)建立; 多模型合成机制采用加权求和方法. 在线修正工况中心可反映工况的时间变化特性, 参数稳定学习算法改善了模型精度和自适应能力. 采用此方法建立污水处理过程化学需氧量(COD)软测量模型, 结果表明, 模型在工况大范围变化时仍具有满意预测效果. |
其他语种文摘
|
Because a single model cannot represent the characteristics of the complex industrial process in varying operating ranges, we propose an online modeling scheme for multiple models。This scheme includes the recognition mechanism of operating range, the local models and the combination mechanism for multiple models. The recognition mechanism analyzes the operating range according to its characteristic variables and adjusts the center of operating range according to similarity degrees. The local model is actually a Hammerstein model which is the serial connection of a wavelet neural network with a stable learning algorithm and an ARX model. The combination mechanism calculates the weighted sum of the outputs of local models, and online adjusts the centers of operating range to reflect the variation characteristics of the operating range. A stable learning algorithm of parameters improves the prediction accuracy and the adaptation ability. This method is implemented in a wastewater treatment process to measure the concentration of the chemical oxygen demand (COD). Experimental results show that this modeling scheme can obtain satisfactory effect in varying operating ranges. |
来源
|
控制理论与应用
,2013,30(6):773-780 【核心库】
|
DOI
|
10.7641/cta.2013.20695
|
关键词
|
工况
;
多模型
;
建模
;
稳定学习
;
污水处理过程
|
地址
|
1.
中国科学院沈阳自动化研究所信息服务与智能控制技术研究室, 辽宁, 沈阳, 110016
2.
东北大学自动化研究中心, 流程工业综合自动化国家重点实验室, 辽宁, 沈阳, 110819
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1000-8152 |
学科
|
自动化技术、计算机技术 |
基金
|
国家973计划
;
创新引智计划(“111”计划)资助项目
;
国家自然科学基金资助项目
;
中国博士后科学基金
|
文献收藏号
|
CSCD:4876892
|
参考文献 共
11
共1页
|
1.
Johansen T A.
Operating regime based process modeling and identification,1994
|
被引
3
次
|
|
|
|
2.
Ragot J. Modelling of a water treatment plant: a multi-model representation.
Environmetrics,2001,12(7):599-611
|
被引
1
次
|
|
|
|
3.
刘德馨. 基于雷达观测数据的高炉料面多模型控制.
控制理论与应用,2012,29(10):1277-1283
|
被引
12
次
|
|
|
|
4.
贾文君. 稀土串级萃取分离过程元素组分含量的多模型软测量.
控制理论与应用,2007,24(4):568-580
|
被引
1
次
|
|
|
|
5.
Serir L. E2GKpro: an evidential evolving multi-modeling approach for system behavior prediction with applications.
Mechanical Systems and Signal Processing,2012(7):1-13
|
被引
1
次
|
|
|
|
6.
Yoo C K. Nonlinear modeling and adaptive monitoring with fuzzy and multivariate statistical methods in biological wastewater treatment plants.
Journal of Biotechnology,2003,105(1):135-163
|
被引
7
次
|
|
|
|
7.
赵立杰. 污水处理出水水质指标的非线性动态软测量模型.
沈阳化工学院学报,2009,23(3):258-265
|
被引
4
次
|
|
|
|
8.
Lakshminarayanan S. Modeling and control of multivariable processes: dynamic PLS approach.
AIChE Journal,1997,43(9):2307-2322
|
被引
15
次
|
|
|
|
9.
Yu W. Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms.
Information Sciences,2004,158(1):131-147
|
被引
6
次
|
|
|
|
10.
Yao J. Entropy-based fuzzy clustering and modeling.
Fuzzy Sets and Systems,2000,113(3):381-388
|
被引
15
次
|
|
|
|
11.
丛秋梅. 一类污水处理过程水质多模型在线软测量方法.
东北大学学报(自然科学版),2010,31(9):1221-1225
|
被引
6
次
|
|
|
|
|