Inverse Modeling for Superheated Steam Temperature Based on Restricted Memory Extreme Learning Machine

doi:10.7652/xjtuxb201402006

您当前的位置：

首页 >

文章列表页 >

Inverse Modeling for Superheated Steam Temperature Based on Restricted Memory Extreme Learning Machine

更新时间：2025-07-09

- Inverse Modeling for Superheated Steam Temperature Based on Restricted Memory Extreme Learning Machine
- Vol. 48, Issue 2, Pages: 32-37(2014)
- 作者机构：
  
  郑州大学电气工程学院,郑州,450001
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201402006
  CLC： TP273
- Online First：10 February 2014，
  
  Published：2014
- 稿件说明：
移动端阅览
Inverse Modeling for Superheated Steam Temperature Based on Restricted Memory Extreme Learning Machine[J]. 2014, 48(2): 32-37.
DOI：

Inverse Modeling for Superheated Steam Temperature Based on Restricted Memory Extreme Learning Machine[J]. 2014, 48(2): 32-37. DOI： 10.7652/xjtuxb201402006.

摘要

针对常规极限学习机随着学习次数增加增益矩阵慢慢趋于零、学习算法逐渐失去修正能力而出现“数据饱和”的问题

提出了限定记忆极限学习机算法。该算法在学习过程中每增加一个新数据信息

就去掉一个旧数据信息

权值的学习只依赖于限定个数的最新数据信息

从而避免出现“数据饱和”。通过分析隐含层数据矩阵的特点

利用分块矩阵计算方法推导了限定记忆极限学习机在线学习算法。将该算法应用于参数时变的过热汽温对象逆模型的辨识

仿真实验结果表明:该算法能有效克服“数据饱和”问题

提高计算精度

是一种实用有效的过热汽温对象逆建模算法。

Abstract

A restricted memory extreme learning machine is proposed to improve the data saturation problem in the conventional extreme learning machine that is caused by the gain matrix gradually approaching zero as the sampled data increase and the weight values can't be modified by new sampled data. In the proposed algorithm

the neural network's weight values learning only depends on a limited number of new sample data by deleting an old data when a new data is received

and the data saturation is avoided. The characteristics of the hidden layer matrix are analyzed

and the calculation formula of block matrices is used to derive the proposed algorithm. Then the learning algorithm is applied to identify the inverse model of the superheated steam temperature plant. Simulation results show that the proposed learning algorithm overcomes the data saturation problem effectively

and improves the precision of the weight values learning.

关键词

Keywords

references

韩璞, 张海琳, 张丽静. 神经网络自适应逆控制的仿真研究[J]. 华北电力大学学报, 2001, 28(3): 26-30.

HAN Pu, ZHANG Hailin, ZHANG Lijing. Simulation study of neural network based adaptive inverse control[J]. Journal of North China Electric Power University, 2001, 28(3): 26-30.

党映农, 韩崇昭. 基于Volterra基函数网络的自适应逆控制方法[J]. 西安交通大学学报, 2000, 34(9): 8-12.

DANG Yingnong, HAN Chongzhao. Adaptive inverse control based on Volterra polynomial basis function neural networks[J]. Journal of Xi'an Jiaotong University, 2000, 34(9): 8-12.

王广军, 邓良才, 陈红. 锅炉汽温对象逆动力学过程模糊辨识[J]. 中国电机工程学报, 2007, 27(20): 76-80.

WANG Guangjun, DENG Liangcai, CHEN Hong. Fuzzy identification on inverse dynamic process of steam temperature object of boiler[J]. Proceedings of the Chinese Society for Electrical Engineering, 2007, 27(20): 76-80.

GELFAND S B, GMEIER J V. The stability of variable step-size LMS algorithms[J]. IEEE Transactions on Signal Processing, 1999, 47(12): 3277-3288.

罗小东, 贾振红, 王强. 一种新的变步长LMS自适应滤波算法[J]. 电子学报, 2006, 6(6): 1123-1126.

LUO Xiaodong, JIA Zhenhong, WANG Qiang. A new variable step size LMS adaptive filtering algorithm[J]. Acta Electronica Sinica, 2006, 6(6): 1123-1126.

刘亚秋, 马广富, 石忠. NARX网络在自适应逆控制动态系统辨识中的应用[J]. 哈尔滨工业大学学报, 2005, 37(2): 173-176.

LIU Yaqiu, MA Guangfu, SHI Zhong. NARX network for dynamic system identification in adaptive inverse control[J]. Journal of Harbin Institute of Technology, 2005, 37(2): 173-176.

钟伟民, 皮道映, 孙优贤. 基于支持向量机的直接逆模型辨识[J]. 控制理论与应用, 2005, 22(2): 307-310.

ZHONG Weimin, PI Daoying, SUN Youxian. Support vector machine based direct inverse-model identification[J]. Control Theory and Application, 2005, 22(2): 307-310.

HUANG Guangbin, SIEW C K. Extreme learning machine: RBF network case[C]∥Proceedings of the 8th International Conference on Control, Automation, Robotics and Vision. Piscataway, NJ, USA: IEEE, 2004: 1029-1036.

HUANG Guangbin, SIEW C K. Extreme learning machine with randomly assigned RBF kernels[J]. International Journal of Information Technology, 2005, 11(1): 16-25.

HANDOKO S D, KEONG K C, SOON O Y, et al. Extreme learning machine for predicting HLA-peptide binding[C]∥Proceedings of the Advances in Neural Networks. Berlin, Germany: Springer-Verlag, 2006: 716-721.

LIANG Nanying, SARATCHANDRAN P, HUANG Guangbin. Classification of mental tasks from EEG signals using extreme learning machine[J]. International Journal of Neural Systems, 2006, 16(1): 29-38.

HUANG Guangbin, ZHU Qinyu, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1): 489-501.

LIANG Nanying, HUANG Guangbin, SARATCHANDRAN P, et al. A fast and accurate online sequential learning algorithms for feedforward networks[J]. IEEE Transactions on Neural Networks, 2006, 17(6): 1411-1423.

HUANG Guangbin, SARATCHANDRAN P, SUN-

DARAAJAN N. An efficient sequential learning algorithm for growing and pruning RBF(GAP-RBF)networks[J]. IEEE Transactions on System, Man, and Cybernetics, 2004, 34(6): 2284-2292.

FENG Guorui, HUANG Guangbin, LIN Qingping, et al. Error minimized extreme learning machine with growth of hidden nodes and incremental learning[J]. IEEE Transactions on Neural Networks, 2009, 20(8): 1352-1357.

范永胜, 徐治皋, 陈来久. 基于动态特性机理分析的锅炉过热汽温自适应模糊控制系统研究[J]. 中国电机工程学报, 1997, 7(1): 23-28.

FAN Yongsheng, XU Zhigao, CHEN Laijiu. Study of adaptive fuzzy control of boiler superheated steam temperature based on dynamic mechanism analysis[J]. Proceedings of the Chinese Society for Electrical Engineering, 1997, 7(1): 23-28.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

I/O Performance Modeling and Prediction Method for Large-Scale Parallel Applications Using Machine Learning

Numerical Simulation of the Energy Conversion Process in Thermoacoustic Engines with Different Stack Materials

Energy Efficiency Optimization of the Cryogenic Air Separation Process for Electronic-Grade Ultra Pure Nitrogen

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Study on the Thermodynamic Properties in the Anomalous Region of Supercritical Water

Related Author

No data

Related Institution

No data

⁰