ON-LINE TRAINING METHOD OF ANN IN DMS

WU Kai; HE Xiaorong; CHEN Bingzhen

您当前的位置：

首页 >

文章列表页 >

ON-LINE TRAINING METHOD OF ANN IN DMS

更新时间：2025-12-10

- ON-LINE TRAINING METHOD OF ANN IN DMS
- CIESC Journal Issue 12, (2001)
- 作者机构：
  
  清华大学化工系
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Online First：25 December 2001，
  
  Published：25 December 2001
- 稿件说明：
移动端阅览
WU Kai, HE Xiaorong, CHEN Bingzhen. ON-LINE TRAINING METHOD OF ANN IN DMS[J]. CIESC Journal, 2001, (12).
DOI：

WU Kai, HE Xiaorong, CHEN Bingzhen. ON-LINE TRAINING METHOD OF ANN IN DMS[J]. CIESC Journal, 2001, (12). DOI：

摘要

基于ANN(artificialneuralnetwork)的分馏塔侧线质量指标动态在线检测系统

简称DMS (dynamicon -linemonitoringsystem)

成功地应用于炼油厂粗汽油干点、柴油凝点、Reid蒸汽压、闪点、冰点等的实时、在线、动态检测

达到很高的预测精度

极大地改善了分馏塔的控制性能

实现了分馏塔的操作优化 .本文提出一种新的网络训练方法———在线训练法

提高了在线检测系统的预测精度 .实际应用表明

这种方法可以有效克服人工神经网络离线训练的不足

提高动态在线检测系统的可靠性

并且省时省力

Abstract

The dynamic on-line monitoring system (DMS) based on on-line training of ANN has been implemented successfully in a refinery for real-time

on-line and dynamic estimation of quality indexes of fractionator side draw

such as end point of raw-gasoline

pour point of diesel-oil

Reid vapor pressure

flash point

freezing point.It improves the control performance and optimizes the operation of the fractionator.To improve the predicted accuracy of DMS and fit the new production cases

a novel ANN training method

on-line training method

has been proposed in this article.This method overcomes the disadvantages of off-line training of ANN effectively.It can save lots of time and effort in contrast to the conventional off-line training of ANN.It improves the performance of DMS.This method includes three main steps:judge when ANN needs to be trained again;get new training patterns on-line;train ANN on-line.Steady state determination of the process is a key procedure in on-line training.A method based on the mathematical theory of evidence is used in steady state determination.This improves the training results of ANN and the reliability of DMS.

关键词

Keywords

references

Views

205

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Thermodynamic performance of tower-type solar-assisted supercritical compression CO2 energy storage system

Recent advances and perspectives on sulfide-based photocatalysts for hydrogen production

Mechanism and regulation of supercooling behavior in imidazolium-based ionic liquids

Prediction of biomass pyrolysis product yield based on machine learning algorithms

Zn-doped PdO/ZrO2 with rich oxygen vacancies for the synthesis of diphenyl carbonate from CO2 and phenol

Related Author

No data

Related Institution

No data

⁰