A NEW TRAINING METHOD OF BACK - PROPAGATION NEURAL NETWORK

何小荣; 陈丙珍; 胡山鹰; 朱振伟

您当前的位置：

首页 >

文章列表页 >

A NEW TRAINING METHOD OF BACK - PROPAGATION NEURAL NETWORK

更新时间：2025-12-16

- A NEW TRAINING METHOD OF BACK - PROPAGATION NEURAL NETWORK
- CIESC Journal Issue 5, (1994)
- 作者机构：
  
  清华大学化工系,清华大学化工系,清华大学化工系,清华大学化工系北京 100084,北京 100084,北京 100084,北京,100084
- 作者简介：
- 基金信息：
- DOI：
  CLC： Q018
- Online First：25 October 1994，
  
  Published：25 October 1994
- 稿件说明：
移动端阅览
何小荣, 陈丙珍, 胡山鹰, et al. A NEW TRAINING METHOD OF BACK - PROPAGATION NEURAL NETWORK[J]. CIESC Journal, 1994, (5).
DOI：

何小荣, 陈丙珍, 胡山鹰, et al. A NEW TRAINING METHOD OF BACK - PROPAGATION NEURAL NETWORK[J]. CIESC Journal, 1994, (5). DOI：

摘要

本文针对BP神经网络培训过程中的局部最优解问题提出了一种新的培训方法——GDR-SA法

分别对1个具有13个决策变量的网络和1个具有108个决策变量的催化裂化分馏塔优化操作建模网络进行了培训。结果表明这一方法可以有效地克服局部最优解给网络培训所带来的困扰。

Abstract

A local optimal solution often occurs in the training process of artificial neural network. To cope with this situation

a new training method of BP net is proposed. The method has been applied to training a net with 13 decision variables and another net for modeling optimizing operation of FCC main fractionator with 108 decision variables. The results show that the method can overcome successfully the problems of local optimal solution and speed up training process.

关键词

Keywords

references

Views

328

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of biomass pyrolysis product yield based on machine learning algorithms

Performance of alkali metal-loaded SrMnO3 oxygen carriers in chemical looping oxidative dehydrogenation of ethylbenzene

Performance analysis and application of thermal and humidity control system cascade driven by waste heat

Methods of adaptive prediction and abnormal states traceability for sulphur content in flue gas desulfurization process

Engineering verification and NO emission control of rare earth Y2O3-based catalytic coatings on a metal fiber surface burner

Related Author

No data

Related Institution

No data

⁰