|本期目录/Table of Contents|

[1]程换新,张义民,刘军亮,等.基于DEBP模糊神经网络的醇烯比值控制研究[J].工业仪表与自动化装置,2019,(01):72-75.[doi:1000-0682(2019)01-0000-00]
 CHENG Huanxin,ZHANG Yimin,LIU Junliang,et al.Studies on alcohol alkene ratio control based on DEBP fuzzy neural network[J].Industrial Instrumentation & Automation,2019,(01):72-75.[doi:1000-0682(2019)01-0000-00]
点击复制

基于DEBP模糊神经网络的醇烯比值控制研究

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2019年01期
页码:
72-75
栏目:
出版日期:
2019-02-15

文章信息/Info

Title:
Studies on alcohol alkene ratio control based on DEBP fuzzy neural network
作者:
程换新张义民刘军亮张远绪
青岛科技大学 自动化与电子工程学院,山东 青岛 266061
Author(s):
CHENG Huanxin ZHANG Yimin LIU Junliang ZHANG Yuanxu
College of Automation and Electrical Engineering, Qingdao University of Science and Technology, Shandong Qingdao 266061, China
关键词:
模糊神经网络DEBP算法醇烯比值控制
Keywords:
fuzzy neural network DEBP algorithm alcohol / alkene ratio control
分类号:
TP29
DOI:
1000-0682(2019)01-0000-00
文献标志码:
A
摘要:
在炼油厂轻汽油醚化系统中醇烯比值对烯烃转化率的影响较大,由于实际生产中醇烯比值控制过程具有非线性和大滞后特性,因此传统的PID控制方式对于醇烯比值的控制效果不够稳定。该文提出将基于DEBP算法的模糊神经网络用于轻汽油醚化系统醇烯比值的控制当中。对反应釜内的醇烯比值控制过程构建数学模型,建立模糊神经网络控制器,将差分进化算法与BP算法进行组合形成DEBP算法,利用此算法对模糊神经网络参数进行优化,仿真验证了基于DEBP算法的模糊神经网络控制比传统PID控制效果更好。
Abstract:
In light gasoline etherification system in refinery,the effect of alkene ratio on olefin conversion is larger.Due to the nonlinear and lagging characteristics of the alkene ratio control process in actual production,the control effect of the traditional PID control method on the ratio of alkene is not stable.In this paper,the fuzzy neural network is used to construct the controller to control the ratio of alcohol and alkene.The mathematical model of the alcohol and alkene ratio control process in the reactor is built,and then a fuzzy neural network controller is established. The differential evolution algorithm is combined with the BP algorithm to form the DEBP algorithm, which is used to optimize the parameters of the fuzzy neural network.Simulation results show that the fuzzy neural network control based on DEBP algorithm is better than the traditional PID control.

参考文献/References:

[1] 苗兴东.催化裂化汽油降烯烃技术的现状及发展[J].广州化工,2012,40(7):33-35.

[2] 梁启队.轻汽油醚化装置DCS设计与研究[D].青岛:青岛科技大学,2013.
[3] 李林,唐铭辰,胡炎兴.催化裂化轻汽油醚化催化剂的研究进展[J].能源化工,2012,33(4):44-48.
[4] 温世昌,孙玉玲,刘成军.催化汽油醚化装置的控制方案[J].石油化工自动化,2011,47(5):36-38.
[5] 孙玉琴,石琳,张志宏.基于模糊控制系统的高炉焦比预报研究[J].冶金自动化,2004(s1):451-454.
[6] 张吉礼.模糊-神经网络控制原理与工程应用[M].哈尔滨:哈尔滨工业大学出版社,2004.
[7] 贾震斌,田立炎.基于BP神经网络的身份证号码识别算法[J].苏州市职业大学学报,2006,17(3):92-94.
[8] M H Moradi. New techniques for PID Controller Design [C].Control Applications Proceedings of 2003 IEEE Conference,2003:903-908.
[9] T A Wen, P K Tam. PID tuning for integrating processes [C].Control Applications Proceedings of the1998 IEEE International Conference,1998: 873-876.
[10] 蒋华勤,潘杰.基于MATLAB的参数模糊自整定PID控制器的设计与仿真[J].中原工学院学报,2008,19(8): 68-71.

相似文献/References:

[1]崔丽洁,程换新,宋生建.基于改进PSO算法的模糊神经网络的研究与应用[J].工业仪表与自动化装置,2018,(05):24.[doi:1000-0682(2018)05-0000-00]
 CUI Lijie,CHENG Huanxin,SONG Shengjian.Research and application of fuzzy neural network based on improved PSO algorithm[J].Industrial Instrumentation & Automation,2018,(01):24.[doi:1000-0682(2018)05-0000-00]

备注/Memo

备注/Memo:
收稿日期:2018-05-16
作者简介:程换新(1966),男,浙江大学博士,青岛科技大学教授,硕士生导师,研究方向为智能控制理论及应用。
更新日期/Last Update: 2019-01-15