摘要
土壤氮是作物生长发育所必需的营养元素,也是衡量土壤肥力特征的重要指标。为快捷准确测定土壤全氮含量,该研究提出了一种基于热裂解和电子鼻的土壤全氮含量检测方法。采用10种不同类型的气体传感器构建传感器阵列,并对其进行了不同浓度甲烷、氯乙烯和氨气等标准气体的响应测试试验。使用马弗炉裂解土壤样本得到裂解气体,采用气体传感器阵列检测裂解气体的响应曲线。提取响应曲线的平均值(V_(mean))、方差值(V_(vav))、最大梯度值(V_(mgv))、最大值(V_(max))、响应面积值(V_(rav))、第8秒的瞬态值(V_(8))和平均微分系数(V_(mdc))7个特征构建121×10×7(121为土壤样本,10为传感器数量,7为特征)的特征空间,采用GA-BP特征优化方法将特征降至33维,形成121×33的特征空间。GA-BP算法优化结果表明,构建的传感器阵列对该文检测方法无冗余影响,其中传感器TGS826、TGS2603、TGS2611和TGS2600对新特征空间的构建贡献最大,特征V_(mean)、V_(mgv)、V_(rav)、V_(8)和V_(mdc)是反映该文检测方法与土壤全氮含量内在关系的重要特征。采用反向传播神经网络算法(BPNN)、偏最小二乘回归算法(PLSR)和反向传播神经网络与偏最小二乘回归结合算法(PLSR-BPNN)建立特征空间与土壤全氮含量的预测模型,使用决定系数(R^(2))、均方根误差(RMSE)和相对分析误差(RPD)作为模型性能指标。建模结果表明,PLSR、BPNN和PLSR-BPNN模型的R^(2)分别为0.91、0.81和0.93,RMSE分别为0.25、0.37和0.22,RPD分别为3.24、2.19和3.79,PLSR-BPNN模型拥有最高的R^(2)和RPD,最小的RMSE。结果表明,土壤热解气体与土壤全氮含量之间存在较高的相关性,采用该文检测方法建立的PLSR-BPNN模型可以实现土壤全氮含量的准确预测。
Soil nitrogen as an essential nutrient element is one of the most important indexes to measure soil fertility for crop growth and development.In this research,a new detection was proposed to quickly accurately determine the soil total nitrogen(STN)content using pyrolysis and electronic nose.Ten types of gas sensors were used to construct the sensor arrays.A response test was carried out under the different concentrations of methane,vinyl chloride,and ammonia standard gas.The test results showed that there were significant differences in responses of the sensor array to the types and the concentration,where the response intensity increased with the increase of the standard gas concentration.The sensor array also presented a high specificity and cross-sensitivity during data detection.Furthermore,the pyrolysis gas was obtained from the soil samples using the muffle furnace,further to detect the response curve using the gas sensor array.After that,a 121×10×7 feature space(121 soil samples,10 number of sensors,and 7 eigenvalues)was constructed to extract the mean(V_(mean)),variance(V_(vav)),the maximum gradient(V_(mgv)),the maximum(V_(max)),response area(V_(rav)),the eighth of the second transient(V_(8)),and mean differential coefficient(V_(mdc))of the response curve.A genetic algorithm and neural network model(GA-BP)feature optimization was used to reduce the eigenvalue to 33 dimensions,forming a new feature space of 121×33.More importantly,there was no redundant effect of the constructed sensor array on the new detection.Specifically,the sensors of TGS826,TGS2603,TGS2611,and TGS2600 contributed the most to the construction of the new feature space.The V_(mean),V_(mgv),V_(rav),V_(8) and V_(mdc) were the important features to represent the internal relationship between the detection and STN content.The prediction model of feature space and STN content was then established using a back propagation neural network(BPNN),partial least squares regression(PLSR),and a combination of a back propagation neural network and
作者
李名伟
夏晓蒙
朱庆辉
刘鹤
黄东岩
王刚
Li Mingwei;Xia Xiaomeng;Zhu Qinghui;Liu He;Huang Dongyan;Wang Gang(School of Biological and Agricultural Engineering,Jilin University,Changchun 130022,China;Key Laboratory of Bionic Engineering,Ministry of Education,Jilin University,Changchun 130022,China)
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2021年第24期73-84,共12页
Transactions of the Chinese Society of Agricultural Engineering
基金
吉林省科技发展计划项目(20200502007NC)。
关键词
土壤
全氮
传感器
热裂解
电子鼻
特征优化
模式识别
soil
total nitrogen
sensor
pyrolysis
electronic nose
feature optimization
pattern recognition
