Study on prediction model of critical deposition velocity in slurry pipeline based on PSO-ELM

WANG Ming-xian; WU Jian-de; WANG Xiao-dong

doi:10.13873/J.1000-9787(2017)03-0066-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Study on prediction model of critical deposition velocity in slurry pipeline based on PSO-ELM

更新时间：2025-09-11

- Study on prediction model of critical deposition velocity in slurry pipeline based on PSO-ELM
- Vol. 36, Issue 3, Pages: 66-69(2017)
- 作者机构：
  
  1. 昆明理工大学信息工程与自动化学院
  2. 云南省矿物管道输送工程技术研究中心
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2017)03-0066-04
  CLC： TP18;U171
- Published：2017
- 稿件说明：
移动端阅览
[1]汪明先,吴建德,王晓东.PSO-ELM的浆体管道临界淤积流速预测模型研究[J].传感器与微系统,2017,36(03):66-69.

WANG Ming-xian, WU Jian-de, WANG Xiao-dong. Study on prediction model of critical deposition velocity in slurry pipeline based on PSO-ELM[J]. 2017, 36(3): 66-69.
[1]汪明先,吴建德,王晓东.PSO-ELM的浆体管道临界淤积流速预测模型研究[J].传感器与微系统,2017,36(03):66-69. DOI： 10.13873/J.1000-9787(2017)03-0066-04.

WANG Ming-xian, WU Jian-de, WANG Xiao-dong. Study on prediction model of critical deposition velocity in slurry pipeline based on PSO-ELM[J]. 2017, 36(3): 66-69. DOI： 10.13873/J.1000-9787(2017)03-0066-04.

摘要

针对浆体管道临界淤积流速预测难度大、精度低等问题

提出了粒子群优化—极限学习机（PSOELM）的临界淤积流速预测模型。利用PSO算法对ELM模型参数输入权值和隐元偏置进行优化

应用优化得到的ELM模型对预测集进行预测。通过实验仿真得到预测结果的最大误差为5.73%

预测效果优于常规的ELM模型和反向传播（BP）神经网络模型。

Abstract

Aiming at problems of great difficulties and low precision in predicting critical deposition velocity of slurry pipeline

a prediction model for critical deposition velocity based on particle swarm optimization and extreme learning machine（ PSO-ELM） is proposed. The method using PSO algorithm to optimize the ELM model parameters such as the input weight and hidden element bias

the optimized ELM model is used to predict prediction set. The maximum error of predicted result is 5. 73 % by experimental simulation

which shows that the prediction effect is superior to the conventional ELM and back propagation（ BP） neural network model.

关键词

Keywords

references

基于人工鱼群算法优化SVM的手部动作sEMG识别 [J]. 洪洁,王璐,汪超,魏伟,叶晔. 传感器与微系统 . 2016(02)

改进BP算法在热流传感器温度补偿中的应用 [J]. 康国炼,杨遂军,叶树亮. 传感器与微系统 . 2016(02)

基于PSO-BP的红外温度传感器环境温度补偿 [J]. 赵斌,王建华. 传感器与微系统 . 2015(02)

PSO-BP神经网络在多元有害气体检测中的应用 [J]. 龚雪飞,徐景,孙寿通,刘萍,简家文. 传感器与微系统 . 2015(02)

物料粒径对浆体管道输送临界流速的影响 [J]. 丁宏达. 水力采煤与管道运输 . 2011(04)

非均质流水平管道临界流速研究 [J]. 汪东. 矿冶工程 . 2008(04)

基于支持向量机和遗传算法的纹理识别 [J]. 李杰,楚恒,朱维乐,彭静. 四川大学学报(工程科学版) . 2005(04)

浆体管道输送临界流速的影响因素及计算分析 [J]. 汪东,许振良,孟庆华. 管道技术与设备 . 2004(06)

基于粒子群优化的神经网络训练算法研究 [J]. 高海兵,高亮,周驰,喻道远. 电子学报 . 2004(09)

浆体的物理特性与管道输送流速 [J]. 费祥俊. 管道技术与设备 . 2000(01)

用人工神经网络法研究大直径浆体输送管道的淤积临界流速 [J]. 韩旭,张奇志,佟庆理. 中国有色金属学报 . 1997(04)

浆体管道的不淤流速研究 [J]. 费祥俊. 煤炭学报 . 1997(05)

Extreme learning machine: Theory and applications [J] . Guang-Bin Huang,Qin-Yu Zhu,Chee-Kheong Siew. Neurocomputing . 2006 (1)

Views

195

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of data fusion of fuzzy neural network in body area networks

Cross antenna array optimization method based on immune PSO algorithm

Soft measurement modeling of ELM based on SFLA

Wind power MPPT control based on RF-GRU wind speed prediction

Soft measurement modeling of alkaline protease fermentation process based on improved LWPLS

Related Author

LAI Jianqiong

ZHOU Jinzhi

TU Daoxin

XU Chaohui

GONG Wanlin

HE Zhiqiu

HUO Da

CHEN Gang

Related Institution

Sichuan Key Laboratory of Special Environmental Robotics

School of Information Engineering,Southwest University of Science and Technology

School of Electronic Information,Wuhan University

Key Laboratory of Advanced Process Control for Light Industry,Ministry of Education

School of Internet of Things Engineering,Jiangnan University

⁰