GENERALIZED REGRESSION NEURAL NETWORK AND ITS APPLICATION TO DELAYED COKING PROCESS

HAO Xin; CHEN Dezhao; WU Xiaohua; YU Huanjun

您当前的位置：

首页 >

文章列表页 >

GENERALIZED REGRESSION NEURAL NETWORK AND ITS APPLICATION TO DELAYED COKING PROCESS

更新时间：2025-12-10

- GENERALIZED REGRESSION NEURAL NETWORK AND ITS APPLICATION TO DELAYED COKING PROCESS
- CIESC Journal Issue 4, Pages: 608-612(2004)
- 作者机构：
  
  浙江大学化学工程与生物工程学系,浙江,杭州,310027
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Online First：25 April 2004，
  
  Published：25 April 2004
- 稿件说明：
移动端阅览
HAO Xin, CHEN Dezhao, WU Xiaohua, et al. GENERALIZED REGRESSION NEURAL NETWORK AND ITS APPLICATION TO DELAYED COKING PROCESS[J]. CIESC Journal, 2004, (4): 608-612.
DOI：

HAO Xin, CHEN Dezhao, WU Xiaohua, et al. GENERALIZED REGRESSION NEURAL NETWORK AND ITS APPLICATION TO DELAYED COKING PROCESS[J]. CIESC Journal, 2004, (4): 608-612. DOI：

摘要

广义回归神经网络（GRNN）具有明确的概率意义，其参数大多能自动确定，仅光滑因子参数需优化估值.采用优进遗传算法（EGA），将确定性与随机性寻优操作相融合，实现了高效全局搜优，它所基于的优进策略包括设计Powell寻优算子、改进交叉算子、自适应地调整交叉率和变异率等.以推广能力作为优化目标，所建的GRNN有很强的非线性拟合能力和优良的预报性能，将其成功地为延迟焦化过程建模，与径向基网络（RBFN）等相比，显示了明显的优势.

Abstract

This paper describes an optimal generalized regression neural network (GRNN) in which training of the network is optimization of the smoothing factors. A eugenic evolution strategy genetic algorithm (EGA)

which integrates random evolution operation and deterministic optimization operation

is adopted in this paper to realize global optimization in high efficiency. The eugenic evolution strategies used in this paper include adding new deterministic Powell searching operation，improving crossover operation，modifying adaptive crossover probability and mutation probability

and others. The GRNN-EGA

which is based on EGA and provides powerful capacity in non-linear modeling and predicting

is applied to modeling delayed coking process to predict the productivity of coke. The GRNN-EGA prediction results are compared to those obtained with the radial basis function network（RBFN）and the GRNN-Powell

which is based on Powell optimization. The GRNN-EGA model has better prediction performance and stability as compared with the latter two models.

关键词

Keywords

references

Views

163

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Flux prediction of micro-filtration devices based on genetic neural network

A new strategy of optimization control for increasing fermentation unit

Optimal design of water networks by using genetic algorithm based on criterion of maximal water reuse

Soft computing applied to gas-assisted injection molding process optimization

Prediction of reverse osmosis performance based on genetic algorithm and adsorption-diffusion model

Related Author

CUI Yanjie

LIU Xiaopeng

YU Guangyu

WANG Chun

WANG Zhan

ZHANG Canhui

SUN Guangmin

GAO Xuejin

Related Institution

北京工业大学环境与能源工程学院

北京工业大学电子信息与控制工程学院

上海理工大学动力工程学院

浙江大学化工机械研究所，郑州大学国家橡塑模具工程研究中心，陕西理工学院材料科学与工程学院

浙江四通环境工程有限公司

⁰