粒子群优化BP神经网络在甲烷检测中的应用
|
摘要
为了准确、快速地检测和预测甲烷气体的浓度,设计了基于红外差分吸收法的甲烷浓度检测系统.为了降低系统部件不稳定带来的影响,检测系统采用双气室结构,气室的输入和输出接口处通过渐变折射率透镜连接到传输光纤,以降低光强的损耗.系统对甲烷检测结果的平均误差为0.007 5.基于粒子群优化的误差反向传播神经网络算法构建了甲烷预测模型,以浓度在0.2%～2.0%范围内的甲烷气体为研究对象.在样本训练过程中,预测模型的精度达到10-4,实际输出值与期望值线性回归的相关系数为0.998 8,最大相对标准偏差为0.248%.实验结果表明,在甲烷浓度预测中,相对于误差反向传播神经网络预测模型,粒子群优化误差反向传播神经网络的预测性能更优.
In order to accurately and quickly detect and predict the concentration of methane gas,a methane concentration detection system based on infrared differential absorption method was designed.The detection system adopted a double-chamber structure to reduce the influence of system component instability,and the input and output interfaces of the gas chamber were connected to the transmission fiber through a graded-index lens to reduce the loss of light intensity.The average error of the detection system is 0.007 5.An error back propagation neural network algorithm based on particle swarm optimization was used to construct a prediction model with methane gas in the range of 0.2%～2.0%.In the process of sample training,the accuracy of the prediction model reaches 10-4,the correlation coefficient between the actual output value and the expected linear regression is 0.998 8,and the maximum relative standard deviation is 0.248%.The experimental results show that the prediction performance of particle swarm optimization error back propagation neural network is better than that of error back propagation neural network prediction model in methane concentration prediction.
In order to accurately and quickly detect and predict the concentration of methane gas,a methane concentration detection system based on infrared differential absorption method was designed.The detection system adopted a double-chamber structure to reduce the influence of system component instability,and the input and output interfaces of the gas chamber were connected to the transmission fiber through a graded-index lens to reduce the loss of light intensity.The average error of the detection system is 0.007 5.An error back propagation neural network algorithm based on particle swarm optimization was used to construct a prediction model with methane gas in the range of 0.2%～2.0%.In the process of sample training,the accuracy of the prediction model reaches 10-4,the correlation coefficient between the actual output value and the expected linear regression is 0.998 8,and the maximum relative standard deviation is 0.248%.The experimental results show that the prediction performance of particle swarm optimization error back propagation neural network is better than that of error back propagation neural network prediction model in methane concentration prediction.
引文
[1]TAN W,YU H,HUANG C.Discrepant responses of methane emissions to additions with different organic compound classes of rice straw in paddy soil[J].The Science of the Total Environment,2018,630:141-145.
[2]SHEMSHAD J,AMINOSSADATI S M,KIZIL M S.A review of developments in near infrared methane detection based on tunable diode laser[J].Sensors and Actuators,B:Chemical,2012:77-92.
[3]WEI Ren,LUO Long-qiang,FRANK K T.Sensitive detection of formaldehyde using an interband cascade laser near 3.6μm[J].Sensors Actuators B Chemical,2015,221:1062-1068.
[4]WANG Zhuo,CAO Gu-nian,ZHANG Ke-ke,et al.Detection method of marsh wetland methane gas concentration[J].Instrument Technique and Sensor,2011,3:90-92.王琢,曹家年,张可可,等.沼泽湿地甲烷气体浓度检测[J].仪表技术与传感器,2011,(3):90-92.
[5]YE Wei-lin,LI Chun-guang,ZHENG Chuan-tao,et al.Midinfrared dual-gas sensor for simultaneous detection of methane and ethane using a single continuous-wave interband cascade laser[J].Optics Express,2016,24(15):16973-16985.
[6]SONG Fang,ZHENG Chuan-tao,YAN Wan-hong,et al.Interband cascade laser based mid-infrared methane sensor system using a novel electrical-domain self-adaptive direct laser absorption spectroscopy(SADLAS)[J].Optics Express,2017,25:31876-31888.
[7]LIANG Yong-zhi,LI Mao-dong,XIA Lu-yi,et al.Algorithmic research of detecting gas with infrared methane sensor[J].Instrument Technique and Sensor,2012(11):149-150+165.梁永直,李卯东,夏路易,等.红外甲烷传感器检测中的算法研究[J].仪表技术与传感器,2012,(11):149-150+165.
[8]RUMELHART D E,HINTON G E,WILLIAMS R J.Learning representations by back-propagating errors[J].Nature,1986,323(6088):533-536.
[9]ZHU Jiang-miao,SONG Wen-feng,GAO Yuan,et al.Hydrogen atomic clock difference prediction based on improved back propagation neural network[J].Chinese Journal of Scientific Instrument,2016,37(2):454-460.朱江淼,宋文峰,高源,等.基于改进型BP神经网络的氢原子钟钟差预测[J].仪器仪表学报,2016,37(2):454-460.
[10]CHEN Shan-xue,ZHANG Yang-qi.Hyperspectral image compression based on adaptive band clustering principal component analysis and back propagation neural network[J].Journal of Electronics&Information Technology,2018,40(10):2478-2483.陈善学,张燕琪.基于自适应波段聚类主成分分析和反向传播神经网络的高光谱图像压缩[J].电子与信息学报,2018,40(10):2478-2483.
[11]GAO Fa-rong,WANG Jia-jia,XI Xu-gang,et al.Gait recognition for lower extremity electromyographic signals based on PSO-SVM method[J].Journal of Electronics&Information Technology,2015,37(5):1154-1159.高发荣,王佳佳,席旭刚,等.基于粒子群优化-支持向量机方法的下肢肌电信号步态识别[J].电子与信息学报,2015,37(5):1154-1159.
[12]ZHANG Q,CHANG J,WANG F,et al.Improvement in QEPAS system utilizing a second harmonic based wavelength calibration technique[J].Optics Communications,2018,415:25-30.
[13]LIU Pan,LEI Jia-jie,FANG Bo,et al.Harmonic detection technology of methane molecule at 1.653μm[J].Journal of Applied Optics,2017,38(2):264-269.刘盼,雷佳捷,方波,等.1.653μm处甲烷分子谐波探测技术研究[J].应用光学,2017,38(2):264-269.
[14]WANG Shu-tao,WANG Zhi-fang,LIU Ming-hua,et al.Study of the detecting system of CH4 and SO2based on spectral absorption method and UV fluorescence method[J].Spectroscopy and Spectral Analysis,2016,36(1):287-291.王书涛,王志芳,刘铭华,等.基于光谱吸收法和荧光法的甲烷和二氧化硫检测系统的研究[J].光谱学与光谱分析,2016,36(1):287-291.
[15]QIAN Xiao-rui,WU Fei.Application of BPneural network in quantitative analysis of indoor form aldehyde[J].Transducer and Microsystem Technology,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.
[16]WANG Yan-hu,WANG Xu,YANG Nan,et al.Study on frost heave forecast of artificial saline soil based on BP neural network[J].Subgrade Engineering,2018,(2):14-18.王彦虎,王旭,杨楠,等.基于BP神经网络的人工盐渍土冻胀预测研究[J].路基工程,2018,(2):14-18.
[17]ZENG Yong,SHU Huan,HU Jiang-ping,et al.Adaptive pseudo nearest neighbor classification based on BP neural network[J].Journal of Electronics&Information Technology,2016,38(11):2774-2779.曾勇,舒欢,胡江平,等.基于BP神经网络的自适应伪最近邻分类[J].电子与信息学报,2016,38(11):2774-2779.
[18]LU Yi,ZHANG Pei-pei,WANG Xue-ying,et al.AACMM length error compensation based on PSO-BP neural network[J].Acta Metrologica Sinica,2017,38(3):271-275.陆艺,张培培,王学影,等.基于PSO-BP神经网络的关节臂式坐标测量机长度误差补偿[J].计量学报,2017,38(3):271-275.
[2]SHEMSHAD J,AMINOSSADATI S M,KIZIL M S.A review of developments in near infrared methane detection based on tunable diode laser[J].Sensors and Actuators,B:Chemical,2012:77-92.
[3]WEI Ren,LUO Long-qiang,FRANK K T.Sensitive detection of formaldehyde using an interband cascade laser near 3.6μm[J].Sensors Actuators B Chemical,2015,221:1062-1068.
[4]WANG Zhuo,CAO Gu-nian,ZHANG Ke-ke,et al.Detection method of marsh wetland methane gas concentration[J].Instrument Technique and Sensor,2011,3:90-92.王琢,曹家年,张可可,等.沼泽湿地甲烷气体浓度检测[J].仪表技术与传感器,2011,(3):90-92.
[5]YE Wei-lin,LI Chun-guang,ZHENG Chuan-tao,et al.Midinfrared dual-gas sensor for simultaneous detection of methane and ethane using a single continuous-wave interband cascade laser[J].Optics Express,2016,24(15):16973-16985.
[6]SONG Fang,ZHENG Chuan-tao,YAN Wan-hong,et al.Interband cascade laser based mid-infrared methane sensor system using a novel electrical-domain self-adaptive direct laser absorption spectroscopy(SADLAS)[J].Optics Express,2017,25:31876-31888.
[7]LIANG Yong-zhi,LI Mao-dong,XIA Lu-yi,et al.Algorithmic research of detecting gas with infrared methane sensor[J].Instrument Technique and Sensor,2012(11):149-150+165.梁永直,李卯东,夏路易,等.红外甲烷传感器检测中的算法研究[J].仪表技术与传感器,2012,(11):149-150+165.
[8]RUMELHART D E,HINTON G E,WILLIAMS R J.Learning representations by back-propagating errors[J].Nature,1986,323(6088):533-536.
[9]ZHU Jiang-miao,SONG Wen-feng,GAO Yuan,et al.Hydrogen atomic clock difference prediction based on improved back propagation neural network[J].Chinese Journal of Scientific Instrument,2016,37(2):454-460.朱江淼,宋文峰,高源,等.基于改进型BP神经网络的氢原子钟钟差预测[J].仪器仪表学报,2016,37(2):454-460.
[10]CHEN Shan-xue,ZHANG Yang-qi.Hyperspectral image compression based on adaptive band clustering principal component analysis and back propagation neural network[J].Journal of Electronics&Information Technology,2018,40(10):2478-2483.陈善学,张燕琪.基于自适应波段聚类主成分分析和反向传播神经网络的高光谱图像压缩[J].电子与信息学报,2018,40(10):2478-2483.
[11]GAO Fa-rong,WANG Jia-jia,XI Xu-gang,et al.Gait recognition for lower extremity electromyographic signals based on PSO-SVM method[J].Journal of Electronics&Information Technology,2015,37(5):1154-1159.高发荣,王佳佳,席旭刚,等.基于粒子群优化-支持向量机方法的下肢肌电信号步态识别[J].电子与信息学报,2015,37(5):1154-1159.
[12]ZHANG Q,CHANG J,WANG F,et al.Improvement in QEPAS system utilizing a second harmonic based wavelength calibration technique[J].Optics Communications,2018,415:25-30.
[13]LIU Pan,LEI Jia-jie,FANG Bo,et al.Harmonic detection technology of methane molecule at 1.653μm[J].Journal of Applied Optics,2017,38(2):264-269.刘盼,雷佳捷,方波,等.1.653μm处甲烷分子谐波探测技术研究[J].应用光学,2017,38(2):264-269.
[14]WANG Shu-tao,WANG Zhi-fang,LIU Ming-hua,et al.Study of the detecting system of CH4 and SO2based on spectral absorption method and UV fluorescence method[J].Spectroscopy and Spectral Analysis,2016,36(1):287-291.王书涛,王志芳,刘铭华,等.基于光谱吸收法和荧光法的甲烷和二氧化硫检测系统的研究[J].光谱学与光谱分析,2016,36(1):287-291.
[15]QIAN Xiao-rui,WU Fei.Application of BPneural network in quantitative analysis of indoor form aldehyde[J].Transducer and Microsystem Technology,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.
[16]WANG Yan-hu,WANG Xu,YANG Nan,et al.Study on frost heave forecast of artificial saline soil based on BP neural network[J].Subgrade Engineering,2018,(2):14-18.王彦虎,王旭,杨楠,等.基于BP神经网络的人工盐渍土冻胀预测研究[J].路基工程,2018,(2):14-18.
[17]ZENG Yong,SHU Huan,HU Jiang-ping,et al.Adaptive pseudo nearest neighbor classification based on BP neural network[J].Journal of Electronics&Information Technology,2016,38(11):2774-2779.曾勇,舒欢,胡江平,等.基于BP神经网络的自适应伪最近邻分类[J].电子与信息学报,2016,38(11):2774-2779.
[18]LU Yi,ZHANG Pei-pei,WANG Xue-ying,et al.AACMM length error compensation based on PSO-BP neural network[J].Acta Metrologica Sinica,2017,38(3):271-275.陆艺,张培培,王学影,等.基于PSO-BP神经网络的关节臂式坐标测量机长度误差补偿[J].计量学报,2017,38(3):271-275.