Application of PSO-BP neural network in multiple harmful gas detection

GONG Xue-fei; XU Jing; SUN Shou-tong; LIU Ping; JIAN Jia-wen

doi:10.13873/J.1000-9787(2015)02-0154-03

Chinese

您当前的位置：

首页 >

文章列表页 >

Application of PSO-BP neural network in multiple harmful gas detection

更新时间：2025-09-11

- Application of PSO-BP neural network in multiple harmful gas detection
- Vol. 34, Issue 2, Pages: 154-156+160(2015)
- 作者机构：
  
  宁波大学信息科学与工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2015)02-0154-03
  CLC： TP183;TP274
- Published：2015
- 稿件说明：
移动端阅览
[1]龚雪飞,徐景,孙寿通,刘萍,简家文.PSO-BP神经网络在多元有害气体检测中的应用[J].传感器与微系统,2015,34(02):154-156+160.

GONG Xue-fei, XU Jing, SUN Shou-tong, et al. Application of PSO-BP neural network in multiple harmful gas detection[J]. 2015, 34(2): 154-156+160.
[1]龚雪飞,徐景,孙寿通,刘萍,简家文.PSO-BP神经网络在多元有害气体检测中的应用[J].传感器与微系统,2015,34(02):154-156+160. DOI： 10.13873/J.1000-9787(2015)02-0154-03.

GONG Xue-fei, XU Jing, SUN Shou-tong, et al. Application of PSO-BP neural network in multiple harmful gas detection[J]. 2015, 34(2): 154-156+160. DOI： 10.13873/J.1000-9787(2015)02-0154-03.

摘要

针对目前常见的多元有害气体检测问题

搭建了一种基于传感器阵列和BP神经网络相结合的多元有害气体检测系统。该检测系统中采用了BP神经网络算法对传感器阵列的4种混合有害气体的响应信号进行回归分析。为了提高BP神经网络的预测准确性

又利用了粒子群优化（PSO）算法对BP神经网络的权值与阈值进行了优化。结果显示:通过PSO优化的BP（PSO-BP）神经网络预测的平均相对误差小于2%

能够有效解决气体传感器交叉敏感问题。

Abstract

Aiming at problem of muliple harmful gas detection

a gas detection system is developed by combining sensor array with BP neural network algorithm. This test system uses BP neural network algorithm for regression analysis on response signal of four kinds of mixture harmful gases measured by sensor array. In order to improve prediction accuracy of BP neural network

adopt PSO algorithm to optimize BP neural network weights value and threshold value. The results show that the average relative error predicted by PSO optimized BP neural network（ PSO-BP） is less than 2 %

it can effectively solve problem of cross-sensing of gas sensor.

关键词

Keywords

references

BP神经网络性能与隐藏层结构的相关性探究 [J]. 杨守建,陈恳. 宁波大学学报(理工版) . 2013(01)

结合面法向和切向接触刚度的MPSO-BP神经网络算法的建模 [J]. 杨红平,傅卫平,王雯,师彪,杨世强. 仪器仪表学报 . 2012(08)

混合有毒气体检测算法研究 [J]. 郑杰. 计算机仿真 . 2011(08)

Using an improved back propagation neural network to study spatial distribution of sunshine illumination from sensor network data [J] . Hu Junguo,Zhou Guomo,Xu Xiaojun. Ecological Modelling . 2013

A hybrid co-evolutionary cultural algorithm based on particle swarm optimization for solving global optimization problems [J] . Yang Sun,Lingbo Zhang,Xingsheng Gu. Neurocomputing . 2012

A memetic particle swarm optimization algorithm for multimodal optimization problems [J] . Hongfeng Wang,Ilkyeong Moon,Shenxiang Yang,Dingwei Wang. Information Sciences . 2012

Views

358

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of Adaboost integrated BP neural network in detecting system of sensor array

Design of signal processing circuit for piezoelectric sensor array based on frequency division multiplexing

Research on detection of harmful mixture gas based on MOS sensor array

Design of high precision indoor trace gas monitoring system

Detection of odorous gas based on sensor array

Related Author

HONG Lei

GONG Xue-fei

SUN Shou-tong

JIAN Jia-wen

何文宇

高国伟

李延生

胡敬芳

Related Institution

Key Laboratory of Modern Measurement and Control Technology,Ministry of Education,Beijing Information Science and Technology University

Key Laboratory of Sensors,Beijing Information Science and Technology University

New Energy Institute, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences

Faculty of Electrical Engineering and Computer Science,Ningbo University

School of Computer and Information Engineering,Beijing Technology and Business University

⁰