首页 > 论文 > 激光与光电子学进展 > 57卷 > 7期(pp:71201--1)

基于PCA-BP神经网络对甲醛和甲醇的识别研究

Recognition of Formaldehyde, Methanol Based on PCA-BP Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

当前电子鼻对有毒气体的识别存在数据量少,训练生成的神经网络映射能力差等问题。本文以甲醛和甲醇为目标气体,采用自制的气敏传感器对甲醛和甲醇进行数据采集,并对采集到的数据进行滤波和平滑处理,以提取不同传感器对目标气体的响应值。依据准则函数生成伪随机数,并建立伪随机特征值矩阵以扩大有效数据量。利用主成分分析 (PCA)法对特征值进行降维处理,选择贡献率大的主元成分作为反向传播(BP)神经网络的输入向量,构造PCA-BP神经网络。分别用实测特征值矩阵和伪随机特征值矩阵训练PCA-BP神经网络,通过对比分析两个网络得出,实测特征值矩阵的识别率为92%,而伪随机特征值矩阵的识别率为97%。结果表明,伪随机特征值矩阵能有效提高PCA-BP神经网络的映射能力,提高识别正确率。

Abstract

At present, the identification of toxic gases by electronic noses has a small amount of data, and the ability of neural network mapping generated by training is insufficient. In this work, the formaldehyde and methanol are used as target gases, and collected by self-made gas sensor. After filtering and smoothing the collected data, the different response values are extracted. The pseudo-random numbers are generated according to the criterion function, and the pseudo-random matrix is established to expand the effective data volume.The principal component analysis (PCA) is used to reduce the dimensionality of the eigenvalues, and the principal component score with large contribution rate is selected as the input vector of the back-propagation (BP) neural network to construct PCA-BP neural network, which is trained by using the measured eigenvalue matrix and the pseudo-random eigenvalue matrix respectively. By comparing the two networks, the recognition rate of the measured eigenvalue matrix is 92%, and the recognition rate of the pseudo-random eigenvalue matrix is 97%. The results show that the pseudo-random eigenvalue matrix can effectively improve the mapping ability of BP neural network and the accuracy of recognition.

中国激光微信矩阵
补充资料

中图分类号:X831

DOI:10.3788/LOP57.071201

所属栏目:仪器,测量与计量

基金项目:国家自然科学基金、甘肃省自然科学基金;

收稿日期:2019-10-09

修改稿日期:2019-11-26

网络出版日期:2020-04-01

作者单位    点击查看

宋海声:西北师范大学物理与电子工程学院, 甘肃 兰州 730070
麻林召:西北师范大学物理与电子工程学院, 甘肃 兰州 730070
王一帆:西北师范大学物理与电子工程学院, 甘肃 兰州 730070
朱恩功:西北师范大学物理与电子工程学院, 甘肃 兰州 730070
李承飞:西北师范大学物理与电子工程学院, 甘肃 兰州 730070

联系人作者:麻林召(1093704655@qq.com)

备注:国家自然科学基金、甘肃省自然科学基金;

【1】Peng L Z, Chen W, Liu H, et al. Comparison of the determination methods of formaldehyde value recommended by the national standards China Standardization[J]. 0, 2019(11): 133-135, 157.
彭力争, 陈威, 刘晖, 等. 国标甲醛量值识别方法比较 中国标准化[J]. 0, 2019(11): 133-135, 157.

【2】Huang S H, Han Y, Xu P H, et al. Determination of methanol and formaldehyde in ophthalmic perfluoropropane gas by GC-MS [J]. Chemical Analysis and Meterage. 2019, 28(1): 38-41.
黄书浩, 韩银, 徐萍华, 等. 气相色谱-质谱法测定眼用全氟丙烷气体中甲醇、甲醛 [J]. 化学分析计量. 2019, 28(1): 38-41.

【3】Wang L, Li J C, Qiao L Y, et al. Determination of methanol and ethanol in ShuangWuZhiTong tincture by headspace sampling GC [J]. Strait Pharmaceutical Journal. 2019, 31(8): 106-108.
王璐, 李金慈, 乔立业, 等. 顶空进样-气相色谱法测定双乌止痛酊中甲醇和乙醇含量 [J]. 海峡药学. 2019, 31(8): 106-108.

【4】Luo Z F. Determination of methanol content in cosmetics by chemical method [J]. Chemical Engineering Design Communications. 2019, 45(6): 8-9.
罗志烽. 化学法测定化妆品中甲醇含量的方法 [J]. 化工设计通讯. 2019, 45(6): 8-9.

【5】Zheng H N, Chen Z Z, Shi P Y, et al. Study of toxic gases detection based on miniaturized sensor [J]. Chinese Journal of Sensors and Actuators. 2019, 32(4): 514-519.
郑豪男, 陈珍珍, 施佩影, 等. 基于微纳传感器的有毒有害气体检测方法研究 [J]. 传感技术学报. 2019, 32(4): 514-519.

【6】Qian X R, Wu F. Application of BP neural network in quantitative analysis of indoor formaldehyde [J]. Transducer and Microsystem Technologies. 2018, 37(4): 151-154.
钱小瑞, 吴飞. BP神经网络在室内甲醛定量分析中的应用 [J]. 传感器与微系统. 2018, 37(4): 151-154.

【7】Zhang Q Y, Xie C S, Li D F, et al. Recognition of ethanol, acetone, benzene, toluene and xylene using nano ZnO gas sensor array [J]. Chinese Journal of Sensors and Actuators. 2006, 19(3): 552-554, 558.
张覃轶, 谢长生, 李登峰, 等. 基于纳米ZnO气体传感器阵列的乙醇、丙酮、苯、甲苯、二甲苯的识别研究 [J]. 传感技术学报. 2006, 19(3): 552-554, 558.

【8】He A X, Tang Z A, Wei G F, et al. Study on dynamic signal recognition of gas sensor based on temperature modulation [J]. Transducer and Microsystem Technologies. 2015, 34(6): 24-26.
何爱香, 唐祯安, 魏广芬, 等. 基于温度调制的气体传感器动态信号识别研究 [J]. 传感器与微系统. 2015, 34(6): 24-26.

【9】Wang Y, Xing J G, Fu J, et al. Electronic nose based on flow velocity modulation and its application in beer classification [J]. Transducer and Microsystem Technologies. 2018, 37(11): 158-160.
王雨, 邢建国, 傅均, 等. 基于流速调制的电子鼻及其在啤酒分类中的应用 [J]. 传感器与微系统. 2018, 37(11): 158-160.

【10】Liu J X, Du B, Deng Y Q, et al. Terahertz-spectral identification of organic compounds based on differential PCA-SVM method [J]. Chinese Journal of Lasers. 2019, 46(6): 0614039.
刘俊秀, 杜彬, 邓玉强, 等. 基于差分-主成分分析-支持向量机的有机化合物太赫兹吸收光谱识别方法 [J]. 中国激光. 2019, 46(6): 0614039.

【11】Zhao L Y, Xi X L, Fan Y S, et al. Review of recent progress in the synthesis of nano-tungsten oxide via hydrothermal/solvothermal method and the application [J]. Materials Review. 2019, 33(19): 3203-3209.
赵林艳, 席晓丽, 樊佑书, 等. 纳米氧化钨的水热/溶剂热法制备及应用的综述 [J]. 材料导报. 2019, 33(19): 3203-3209.

【12】Umut Hasan, Mamat Sawut. Hyperspectral estimation of wheat leaf water content using fractional differentials and successive projection algorithm-back propagation neural network [J]. Laser & Optoelectronics Progress. 2019, 56(15): 153002.
马春玥. 基于分数阶微分和连续投影算法-反向传播神经网络的小麦叶片含水量高光谱估算 [J]. 激光与光电子学进展. 2019, 56(15): 153002.

【13】Xu X J, Wang X S, Li A Z, et al. Fast classification of tea varieties based on laser-induced breakdown spectroscopy [J]. Chinese Journal of Lasers. 2019, 46(3): 0311003.
徐向君, 王宪双, 李昂泽, 等. 基于激光诱导击穿光谱的茶叶品种快速分类 [J]. 中国激光. 2019, 46(3): 0311003.

引用该论文

Song Haisheng,Ma Linzhao,Wang Yifan,Zhu Engong,Li Chengfei. Recognition of Formaldehyde, Methanol Based on PCA-BP Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(7): 071201

宋海声,麻林召,王一帆,朱恩功,李承飞. 基于PCA-BP神经网络对甲醛和甲醇的识别研究[J]. 激光与光电子学进展, 2020, 57(7): 071201

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF