基于神经网络的土密实度检测
|
摘要
为了通过神经网络预测土密实度,搭建了土密实度检测装置,采集了土的激光图像,并提取了土的吸收系数、散射系数、激光图像的纹理特征参量和图像的灰度变化率共13个特征参数,通过SPSS降维处理,提取了5个主成分因子作为输入特征;并利用BP神经网络预测密实度.结果表明:经过31次测试后达到了误差要求,预测值与环刀法结果比较的平均绝对误差为7.14%和平均相对误差为7.71%,所建立的预测模型可行;最后通过试验对预测模型进行验证,其预测值与环刀法结果比较的平均绝对误差为8.62%和平均相对误差为8.76%,说明用神经网络预测土密实度是可行的.
In order to test soil compactness by the neural network,a laser image measurement system of soil compactness was established.The thirteen parameters were collected from each image,such as the absorption coefficient,scattering coefficient,texture features and image gray change rate.The SPSS was performed to select five characteristic parameters,and soil compactness was predicted by BP neural networks.The results showed that BP neural networks reached the required error after 31 loops.Compared with the measurement values by using round knife method,the average absolute error was 7.14%,and average relative error was 7.71%,the BP neural network was feasible.The predictive model was verified,the predictive value with cutting ring results in an average absolute error was 8.62%,and average relative error was8.76%.It is suggested that soil compactness by the neural network is feasible.
In order to test soil compactness by the neural network,a laser image measurement system of soil compactness was established.The thirteen parameters were collected from each image,such as the absorption coefficient,scattering coefficient,texture features and image gray change rate.The SPSS was performed to select five characteristic parameters,and soil compactness was predicted by BP neural networks.The results showed that BP neural networks reached the required error after 31 loops.Compared with the measurement values by using round knife method,the average absolute error was 7.14%,and average relative error was 7.71%,the BP neural network was feasible.The predictive model was verified,the predictive value with cutting ring results in an average absolute error was 8.62%,and average relative error was8.76%.It is suggested that soil compactness by the neural network is feasible.
引文
[1]宋先海,肖柏勋,余才盛,等.瞬态瑞雷波反演横波的SVD算法及其应用[J].地质与勘探,2004,40(1):93-96
[2]顾炳其,马荣贵.路基密实度快速测定的瞬态冲击频谱分析法[J].西安公路交通大学学报,1997,12(4):38-41
[3]徐刚,盛安连,姜松,等.新颖的路基密实度测定方法的研究[J].农业机械学报,2001,32(3):20-23
[4]Chen P,Nattuvety V R.Light transmittance through a region of an intact fruit[J].Transaction of the ASAE,1980,23(2):19-522
[5]Iwayan Budiastra,Yoshio Ikeda,Takahisa Nishizu.Optical methods for quality evaluation of fruits(Part I).Optical Properties of selected fruits using the KubelkaMunk theory and their relationships with fruit maturity and sugar content[J].Journal of Japanese Society of Agricultural Machinery,1998,60(2):117-128
[6]Chen B Q,Stamnes K,Stamnes J J.Validity of the diffusion approximation in bio-optical imaging[J].Appl Opt,2001,40(34):6356-6366
[7]陈育彦,屠康.基于激光图像分析的苹果表面损伤和内部腐烂检测[J].农业机械学报,2009,40(7):133-136
[8]Zhang L S,Zhang C P,Wang X Y,et al.Influence of boundary condition and Diffusion theory in steady-state spatially resolved diffuse reflectance of biological tissues[J].Chinese Physics Letters,2002,19(12):18-74
[9]谢中华.MATLAB统计分析与应用[M].北京:北京航空航天大学出版社,2010
[10]肖汉,王国利,王本德.基于因子分析的BP神经网络在需水预测中的应用[J].甘肃农业大学学报,2012,47(5):148-152
[2]顾炳其,马荣贵.路基密实度快速测定的瞬态冲击频谱分析法[J].西安公路交通大学学报,1997,12(4):38-41
[3]徐刚,盛安连,姜松,等.新颖的路基密实度测定方法的研究[J].农业机械学报,2001,32(3):20-23
[4]Chen P,Nattuvety V R.Light transmittance through a region of an intact fruit[J].Transaction of the ASAE,1980,23(2):19-522
[5]Iwayan Budiastra,Yoshio Ikeda,Takahisa Nishizu.Optical methods for quality evaluation of fruits(Part I).Optical Properties of selected fruits using the KubelkaMunk theory and their relationships with fruit maturity and sugar content[J].Journal of Japanese Society of Agricultural Machinery,1998,60(2):117-128
[6]Chen B Q,Stamnes K,Stamnes J J.Validity of the diffusion approximation in bio-optical imaging[J].Appl Opt,2001,40(34):6356-6366
[7]陈育彦,屠康.基于激光图像分析的苹果表面损伤和内部腐烂检测[J].农业机械学报,2009,40(7):133-136
[8]Zhang L S,Zhang C P,Wang X Y,et al.Influence of boundary condition and Diffusion theory in steady-state spatially resolved diffuse reflectance of biological tissues[J].Chinese Physics Letters,2002,19(12):18-74
[9]谢中华.MATLAB统计分析与应用[M].北京:北京航空航天大学出版社,2010
[10]肖汉,王国利,王本德.基于因子分析的BP神经网络在需水预测中的应用[J].甘肃农业大学学报,2012,47(5):148-152