基于IPSO-BP模型的火灾气体传感器气压补偿算法

doi:10.16265/j.cnki.issn1003-3033.2022.02.015

中国安全科学学报 ›› 2022, Vol. 32 ›› Issue (2): 107-114.doi: 10.16265/j.cnki.issn1003-3033.2022.02.015

基于IPSO-BP模型的火灾气体传感器气压补偿算法

何永勃(), 曹祝兵^**()

中国民航大学电子信息与自动化学院,天津 300300

收稿日期:2021-11-11 修回日期:2022-01-06 出版日期:2022-08-18 发布日期:2022-08-28
通讯作者: 曹祝兵
作者简介:
何永勃 (1971—),男,陕西蒲城人,博士,副教授,主要从事航空检测技术及智能化仪表方面的研究。E-mail: ybhe@cauc.edu.cn。
基金资助:
民航科技项目基金资助(MHRD20150220)

Pressure compensation algorithm of fire gas sensors based on IPSO-BP model

HE Yongbo(), CAO Zhubing^**()

School of Electronic Information and Automation, Civil Aviation University of China,Tianjin 300300 China

Received:2021-11-11 Revised:2022-01-06 Online:2022-08-18 Published:2022-08-28
Contact: CAO Zhubing

摘要/Abstract

摘要：

为完善飞机火灾检测系统,设计一套方案,模拟试验不同气压下CO、CO₂气体传感器采集气体的体积分数值,并与理论值比较,进而提出一种根据粒子适应度值动态调整学习因子的粒子群算法。采用改进的粒子群(IPSO)算法寻找反向传播(BP)神经网络的最优初始权值阈值,再利用寻优后的BP神经网络修正CO、CO₂气体传感器的检测结果,消除气压对于传感器采集数据的影响。结果表明:经过IPSO-BP算法补偿后,选取的27个气压点下气体体积分数值都接近拟合真实值,其中,CO₂气体传感器经过气压补偿后,测量最大误差从542×10^-4%下降到0.1×10^-4%,CO气体传感器测量最大误差从15.7×10^-4%下降到0.01×10^-4%。与BP神经网络气压补偿模型相比,IPSO-BP神经网络气压补偿模型的精度有明显的提高。

关键词: 改进的粒子群算法(IPSO), 反向传播(BP)神经网络, 气体传感器, 气压补偿, 飞机货舱火灾

Abstract:

In order to improve fire detection system of aircraft, volume fraction values of CO and CO₂ gas sensors under different air pressure were simulated and compared with the theoretical value by designing a set of experimental scheme, and a particle swarm optimization algorithm was proposed to dynamically adjust learning factor according to particle fitness value. Then, IPSO algorithm was used to find optimal initial weight and threshold of BP neural network which, after optimization, was employed to modify detection results of CO and CO₂ gas sensors to eliminate influence of air pressure on sensor data acquisition. The results show that after compensation by IPSO-BP algorithm, gas volume fraction values at the selected 27 pressure points are close to the fitted true value. Among them, the maximum measurement error of CO₂ gas sensor drops from 542×10^-4% to 0.1×10^-4% after pressure compensation, and that of CO gas sensor decreases from 15.7×10^-4% to 0.01×10^-4%. Compared with BP neural network pressure compensation model, the accuracy of IPSO-BP neural network model is significantly improved.

Key words: improved particle swarm optimization (IPSO), back propagation (BP) neural network, gas sensor, pressure compensation, aircraft cargo compartment fire

何永勃, 曹祝兵. 基于IPSO-BP模型的火灾气体传感器气压补偿算法[J]. 中国安全科学学报, 2022, 32(2): 107-114.

HE Yongbo, CAO Zhubing. Pressure compensation algorithm of fire gas sensors based on IPSO-BP model[J]. China Safety Science Journal, 2022, 32(2): 107-114.

图/表 8

图1

表1

图2

图3

图4

图5

图6

表2

参考文献 16

[1]	何永勃, 董玉珊, 雷建, 等. 飞机货舱火灾多传感器探测方法研究[J]. 中国安全科学学报, 2018, 28(5):74-79. doi: 10.16265/j.cnki.issn1003-3033.2018.05.013
	HE Yongbo, DONG Yushan, LEI Jian, et al. Research on multi-sensor method for detecting aircraft cargo fire[J]. China Safety Science Journal, 2018, 28 (5): 74-79. doi: 10.16265/j.cnki.issn1003-3033.2018.05.013
[2]	何永勃, 张文杰, 杨伟, 等. 飞机货舱复合烟雾探测方法研究[J]. 中国安全科学学报, 2019, 29(1):43-48. doi: 10.16265/j.cnki.issn1003-3033.2019.01.008
	HE Yongbo, ZHANG Wenjie, YANG Wei, et al. Research on multi-sensor smoke detection method for aircraft cargo compartment[J]. China Safety Science Journal, 2019, 29(1):43-48. doi: 10.16265/j.cnki.issn1003-3033.2019.01.008
[3]	陈健. 舱室压力对池火燃烧特性的影响研究[D]. 合肥: 中国科学技术大学, 2020.
	CHEN Jian. Study on the effect of chamber pressure on burning characteristics of pool fires[D]. Hefei: University of Science and Technology of China, 2020.
[4]	杨建忠, 邵资焱, 陈希远. 通风对飞机货舱烟雾探测影响研究[J]. 中国安全科学学报, 2019, 29(2):69-75.
	YANG Jianzhong, SHAO Ziyan, CHEN Xiyuan. Researsh on influence of ventilation on detection of smoke in an aircraft cargo compartment[J]. China Safety Science Journal, 2019, 29(2):69-75.
[5]	王洁, 潘杨月, 郑荣, 等. 飞机货舱低气压环境对火灾探测参量影响研究[J]. 火灾科学, 2016, 5(4):213-217.
	WANG Jie, PAN Yangyue, ZHENG Rong, et al. Experimental investigation on the influence of low pressure on fire detection signals in aircraft cargo compartment fire[J]. Fire Safety Science, 2016, 25 (4): 213-217.
[6]	刘伟辉. 硅热式风速传感器的温漂特性及其补偿算法研究[D]. 南京: 东南大学, 2017.
	LIU Weihui. Temperature drift characteristics and compensation algorithm of silicon thermal wind sensor[D]. Nanjing: Southeast University, 2017.
[7]	REN Yijun, ZHAO Guofeng, QIAN Min, et al. A highly sensitive triple-coil inductive debris sensor based on an effective unbalance compensation circuit[J]. Measurement Science and Technology, 2019, 30(1) :015 108-015 116.
[8]	江东, 单薏, 刘绪坤, 等. 函数拟合法力数字传感器的非线性和温度补偿[J]. 传感器与微系统, 2016, 35(2):16-18,22.
	JIANG Dong, SHAN Yi, LIU Xukun, et al. Function fitting method for non-linear and temperature compensation of force digital sensor[J]. Transducer and Microsystem Techologies, 2016, 35 (2): 16-18, 22.
[9]	田伟, 张广祥, 崔炎, 等. 基于牛顿算法的压力传感器温压补偿方法[J]. 仪表技术与传感器, 2019(1):97-99,105.
	TIAN Wei, ZHANG Guangxiang, CUI Yan, et al. Temperature and pressure compensation method for pressure sensor based on newton algorithm[J]. Instrument Technology and Sensor, 2019 (1): 97-99, 105.
[10]	吴小红. 基于神经网络温度软补偿的光纤光栅压力传感器研究[D]. 武汉: 武汉理工大学, 2015.
	WU Xiaohong. Research on fiber bragg grating pressure sensor of temperature soft compensation based on neural network[D]. Wuhan: Wuhan University of Technology, 2015.
[11]	LI Yuanjiang, LI Yuehua, LI Feng, et al. The research of temperature compensation for thermopile sensor based on improved PSO-BP algorithm[J]. Mathematical Problems in Engineering, 2015:DOI: 10.1155/2015/854945. doi: 10.1155/2015/854945
[12]	HAN Zhiming, HONG Li, MENG Juan, et al. Temperature drift modeling and compensation of capacitive accelerometer based on AGA-BP neural network[J]. Measurement, 2020:DOI: 10.1016/j.measurement.2020.108019. doi: 10.1016/j.measurement.2020.108019
[13]	何怡刚, 陈张辉, 李兵, 等. 改进AFSA-BP神经网络的湿度传感器温度补偿研究[J]. 电子测量与仪器学报, 2018, 32 (7):95-100.
	HE Yigang, CHEN Zhanghui, LI Bing, et al. Research on temperature compensation for humidity sensor of improved AFSA-BP neural network[J]. Journal of Electronic Measurement and Instrumentation, 2018, 32 (7): 95-100.
[14]	牛萍娟, 程峥, 田海涛, 等. 非色散红外CO₂传感器温度补偿模型研究[J]. 仪表技术与传感器, 2019(8):17-20.
	NIU Pingjuan, CHENG Zheng, TIAN Haitao, et al. Research on temperature compensation model of non-dispersive infrared CO₂ sensor[J]. Instrument Technology and Sensor, 2019(8):17-20.
[15]	方俊, 袁宏永, 赵建华. 气体传感器及其在火灾探测中的应用[J]. 火灾科学, 2002, 11(3):180-185,191.
	FANG Jun, YUAN Hongyong, ZHAO Jianhua. Gas sensor and its application in fire detection[J]. Fire Safety Science, 2002, 11(3): 180-185,191.
[16]	方丽丽. 基于NDIR的CO₂气体浓度监测的飞机火警探测关键技术研究[D]. 合肥: 中国科学技术大学, 2016.
	FANG Lili. Study on the CO₂ based gas concentration monitoring of key technologies of aircraft fire detection based on NDIR[D]. Hefei: University of Science and Technology of China, 2016.

传感器名称	CO传感器			CO₂传感器
气压值/kPa	理论值	测量值	误差	理论值	测量值	误差
150	1 667	2 209	542	66.7	79.5	12.8
140	1 556	1 961	405	62.3	74.6	12.3
130	1 445	1 743	298	57.8	69.4	11.6
120	1 334	1 620	286	53.4	65.6	12.2
传感器名称	CO传感器			CO₂传感器
110	1 225	1 491	266	48.9	59.7	10.8
100	1 112	1 360	248	44.5	54.1	9.6
90	100	1 244	244	40.1	49.6	9.5
80	889	1 183	223	35.6	45.1	9.5
70	778	1 011	233	31.2	42.1	10.9
60	667	910	243	26.7	37.3	10.6
50	556	786	230	22.3	33.5	11.2
40	445	672	227	17.8	29.8	12
30	334	477	143	13.4	27.2	13.8
20	223	376	153	8.9	24.6	15.7

算法模型	误差平均值/CO	误差平均值/CO₂
BP神经网络	8.606 68	110.423 78
IPSO-BP神经网络	0.617 824	10.653 02

基于IPSO-BP模型的火灾气体传感器气压补偿算法

Pressure compensation algorithm of fire gas sensors based on IPSO-BP model

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 16

相关文章 6

编辑推荐

Metrics

本文评价

[1]	石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型^*[J]. 中国安全科学学报, 2022, 32(1): 27-33.
[2]	宋高峰, 张延兵, 孙培培, 沈硕勋, 王志荣. 大型储罐声发射技术下的安全评价方法[J]. 中国安全科学学报, 2020, 30(3): 60-66.
[3]	郝永梅, 杜璋昊, 杨文斌, 邢志祥, 蒋军成, 岳云飞. 基于改进ELMD和多尺度熵的管道泄漏信号识别[J]. 中国安全科学学报, 2019, 29(8): 105-111.
[4]	宋博. DEA-BP神经网络下地铁车站深基坑施工安全评价[J]. 中国安全科学学报, 2019, 29(5): 91-96.
[5]	冯子健. 基于BP神经网络的铁路货运安全风险评价研究[J]. 中国安全科学学报, 2018, 28(S1): 178-185.
[6]	朱志洁，张宏伟，韩军，宋卫华. 基于PCA-BP神经网络的煤与瓦斯突出预测研究[J]. 中国安全科学学报, 2013, 23(4): 45-.