Structure design for recurrent RBF neural network based on recursive orthogonal least squares

QIAO Junfei; MA Shijie; YANG Cuili

doi:10.11949/j.issn.0438-1157.20170771

您当前的位置：

首页 >

文章列表页 >

Structure design for recurrent RBF neural network based on recursive orthogonal least squares

更新时间：2025-12-10

- Structure design for recurrent RBF neural network based on recursive orthogonal least squares
- CIESC Journal Issue 3, Pages: 1191-1199(2018)
- 作者机构：
  
  1. 北京工业大学信息学部,北京,100124
  2. 计算智能与智能系统北京市重点实验室,北京,100124
- 作者简介：
- 基金信息：
- DOI：10.11949/j.issn.0438-1157.20170771
  CLC： P183
- Online First：05 March 2018，
  
  Published：05 March 2018
- 稿件说明：
移动端阅览
QIAO Junfei, MA Shijie, YANG Cuili. Structure design for recurrent RBF neural network based on recursive orthogonal least squares[J]. CIESC Journal, 2018, (3): 1191-1199.
DOI：

QIAO Junfei, MA Shijie, YANG Cuili. Structure design for recurrent RBF neural network based on recursive orthogonal least squares[J]. CIESC Journal, 2018, (3): 1191-1199. DOI： 10.11949/j.issn.0438-1157.20170771.

摘要

针对递归RBF神经网络结构难以自适应问题，提出一种基于递归正交最小二乘（recursive orthogonal least squares，ROLS）算法的结构设计方法。首先，利用ROLS算法来计算隐含层神经元的独立贡献度和损失函数，以此判断增加或归为不活跃组的神经元，同时调整神经网络的拓扑结构，并且利用奇异值分解（singular value decomposition，SVD）决定最佳的隐含层神经元个数，以此来删除不活跃组中相对不活跃的神经元，有效地解决了递归RBF神经网络结构冗余和难以自适应问题。其次，利用梯度下降算法更新递归RBF神经网络的参数来保证神经网络的精度。最后，通过对Mackey-Glass时间序列预测、非线性系统辨识和污水处理过程中关键水质参数动态建模，证明了该结构设计方法的可行性和有效性。

Abstract

Aiming at the problem of recurrent radial basis function (RRBF) neural network structure which is difficult to be self-adaptive

this paper proposes a structure design method based on recursive orthogonal least square (ROLS) algorithm. Firstly

ROLS algorithm is used to calculate the contribution and the loss function of hidden layer neurons

which determines to increase or be grouped into inactive neurons

and the topology structure of neural network is adjusted accordingly. At the same time

singular value decomposition (SVD) is applied to determine the best number of hidden layer neurons in order to delete the neurons of the inactive group

which effectively solves the problems of RRBF neural network structure which is redundant and hardly self-adaptive. Secondly

the gradient descent algorithm is utilized to update the parameters of RRBF neural network in order to ensure the accuracy of neural network. Finally

several experiments including the Mackey-Glass time series prediction

nonlinear system identification and key water quality parameters dynamic modeling in wastewater treatment process are conducted

and the simulation results prove the feasibility and effectiveness of the structure design method.

关键词

Keywords

references

Views

225

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Mooney viscosity prediction modeling based on fusion Transformer

A prediction method for effluent ammonia nitrogen concentration based on convolutional layer and attention mechanism long short-term memory network

LiDAR measurement based on model predictive control for boiler combustion optimization

Operation optimization of ethylene cracking furnace based on improved deep reinforcement learning algorithm

Fault diagnosis method of refrigeration and air-conditioning system based on digitized knowledge representation

Related Author

YANG Ye

LU Jiangang

ZHANG Yong

ZHAO Jingbo

QUAN Limin

DONG Yibin

XIONG Jingchao

WANG Jingyu

Related Institution

Sinochem Holdings Corporation Ltd.

College of Control Science and Engineering, Zhejiang University

School of Information and Control Engineering, Qingdao University of Technology

State Key Laboratory of Clean Energy Utilization, Zhejiang University

China City Environment Protection Engineering Limited Company

⁰