Prediction of specific resistance for yeast suspensions in dead-end microfiltration

YAO Jinmiao; WANG Zhan; SUN Guangmin; CHU Jinshu; CHEN Deming; ZHANG Hu; LI Zhaohui

您当前的位置：

首页 >

文章列表页 >

Prediction of specific resistance for yeast suspensions in dead-end microfiltration

更新时间：2025-12-10

- Prediction of specific resistance for yeast suspensions in dead-end microfiltration
- CIESC Journal Issue 6, Pages: 1430-1435(2008)
- 作者机构：
  
  1. 北京工业大学环境与能源工程学院化学化工系
  2. 北京工业大学电子信息与控制工程学院
  3. 北京流体过滤与分离技术研究中心
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Online First：05 June 2008，
  
  Published：05 June 2008
- 稿件说明：
移动端阅览
YAO Jinmiao, WANG Zhan, SUN Guangmin, et al. Prediction of specific resistance for yeast suspensions in dead-end microfiltration[J]. CIESC Journal, 2008, (6): 1430-1435.
DOI：

YAO Jinmiao, WANG Zhan, SUN Guangmin, et al. Prediction of specific resistance for yeast suspensions in dead-end microfiltration[J]. CIESC Journal, 2008, (6): 1430-1435. DOI：

摘要

本文首先设计了三因素四水平的正交实验表作为建模样本，其次利用人工神经网络方法和多元线性回归方法分别建立了基于操作条件（压力△P=0.04-0.12 MPa，浓度C = 0.3-2.0 g.L-1，温度T = 20-40℃）的比阻预测模型，以期用于死端微滤过程操作条件的优化，最后以检验样本的相对误差作为衡量指标，分别采用BP人工神经网络方法和多元线性回归方法对死端微滤过滤酵母悬浮液时的比阻进行了预测。研究结果表明：(1) 在本实验范围内，BP人工神经网络模型的最佳拓朴结构为3-7-1，隐层神经元个数为7，学习速率为0.05

学习函数为traingdx

传递函数为Logsig；用多元线性回归方法得到的比阻与操作条件之间的数学关系式为1.639883+44.2 +0.86217 -0.0607 ； (2)利用BP人工神经网络和多元线性回归方法预测死端微滤比阻的平均相对误差分别为3.55％和5.16％.由此可见，这两种方法都可用于死端微滤比阻预测，并且前者优于后者。

Abstract

In order to optimize the operating conditions in dead-end microfiltration

a predicting model relating the specific resistance to the operating conditions based on the BP neural network was firstly developed in this paper

in which the experimental data of an orthonormal design table (5) were used as the input sample data.Then

by using the average relative absolute error of the testing sample as the criterion

a comparison experiment of the predicting for specific resistance of yeast suspensions by using the BP neural network method and the multiple linear regression method had been made.Finally

the predicting precisions of two models had been given.The results showed that the BP neural network method was better than the multiple linear regression method and the average relative absolute errors were 3.55％ and 5.16％ for the BP neural network method and the multiple linear regression method

respectively.

关键词

Keywords

references

Views

161

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Suspension melt crystallization kinetics of p-xylene

Artificial neural network based on hybrid genetic algorithm and prediction of melting points of organic compounds

Physics-informed spatio-temporal graph convolutional network for fermentation processes

A hybrid modeling and optimization strategy for sequential simulated moving bed

Advantages and risks of swirling cooling granulation towers

Related Author

CHEN Liang

XIAO Jian

XIE Zaiku

YU Jianguo

PENG Qianrong

YANG Min

SHI Yanfu

YU Huarui

Related Institution

中国石化上海石油化工研究院

华东理工大学化学工程联合国家重点实验室

四川大学化工学院

四川大学化学学院

贵阳卷烟厂技术中心

⁰