高光谱成像技术实现马铃薯叶片叶绿素无损检测

针对马铃薯叶片，依托高光谱成像技术实现叶片叶绿素含量的无损检测。利用相关性分析获得马铃薯叶片叶绿素敏感波段，结合植被指数，建立基于光谱导数、植被指数的叶绿素含量传统预测模型与贝叶斯正则化-反向传播（BR-BP）神经网络模型。以489 nm光谱一阶导数值、修正型叶绿素吸收植被指数（MCARI）、陆地叶绿素指数（MTCI）为自变量建立BR-BP神经网络模型，其校正集决定系数、预测集决定系数、均方根误差分别为0.8464，0.6804，0.0746。研究表明，传统模型中光谱一阶导数-幂函数模型可较为准确地预测叶绿素含量，BR-BP神经网络模型相比传统预测模型具有更高的预测精度，因此可以实现马铃薯叶片叶绿素无损检测。     

基于RGB颜色信息聚类的光谱反射率重建

针对光谱反射率研究中因训练样本数据量大造成的冗杂等问题，提出了一种基于RGB信息进行聚类的样本分类方法。首先对颜色进行聚类并确定聚类个数，后对每一类光谱反射率使用BP神经网络分别进行重建。对于实验结果，使用ΔE₀₀、均方根误差（RMSE）以及适应度系数等标准进行评价，同时与主成分分析算法进行对比。从实验分析可得出，在聚类数目为7时光谱反射率重建效果最好，这时的平均CIE2000的色差为0.836，平均RMSE为0.0149，平均适应度系数为99.82%，并且，在最后对重建色差较大的色块进行了优化处理。实验证明，颜色聚类方法可以很好的应用于光谱反射率重建。     

基于光谱反射率的茶染宣纸茶水浓度预测

茶染作为植物染色的一大门类,同时具有良好的环保性能和深厚的文化底蕴。为了能够准确描述茶叶染色的光谱变化,本文研究茶染后宣纸的光谱反射率与茶叶浓度的关系。首先采用分光光度计测量400～700 nm波段被茶叶染色后宣纸的光谱反射率,分别基于偏最小二乘回归模型、BP神经网络和连续投影算法(SPA)选择特征波段建立光谱信息与茶叶浓度之间关系的预测模型。然后以光谱反射率作为输入变量,对茶叶浓度进行预测。结果表明：基于偏最小二乘法、BP神经网络和连续投影算法 选择特征波段建立模型,通过茶染宣纸的光谱反射率来预测茶叶浓度具有较高的稳健性和可信度,其中SPA-BP神经网络模型的效果最优,平均预测正确率为98.40%,决定系数为0.9910,均方根误差为0.8433。这说明通过茶染宣纸的光谱数据来预测茶叶浓度具有可行性。     

小型近红外玉米蛋白质成分分析 仪器设计的波段选择

采用傅里叶变换近红外漫反射光谱技术和偏最小二乘法(PLS)建立了玉米蛋白质含量的定标模型。按照预测效果优选光谱波段,为设计小型近红外玉米蛋白质成分分析仪器提供依据。采用多元散射校正方法对光谱进行预处理,然后利用Savitzky-Golay平滑法对原谱、一阶导数谱和二阶导数谱进行平滑处理。选取全谱、合频、一倍频、二倍频和蛋白质基团等5个波段,每个波段分别采用原光谱、一阶导数谱、二阶导数谱,共建立15个定标模型。同时调整Savitzky-Golay平滑点数和PLS因子数,通过多次PLS数值实验比较,按照预测效果确定每个模型的最优平滑点数、因子数,再从中选优。结果表明,采用一阶导数谱的一倍频波段(7 000~5 500 cm^－1)的定标效果最好,模型的预测相关系数、预测均方根偏差、相对预测均方根偏差分别为0.945,0.357,3.340%。一倍频波段可以代替全谱波段并得到更好的定标效果。     

应用近红外漫反射光谱快速测定土壤锌含量

采用近红外漫反射光谱和偏最小二乘法(PLS)建立了土壤锌快速分析的定量模型,并进行了波段优选。首先,基于单波长模型预测效果将全体样品划分为定标集和预测集;然后,采用多元散射校正(MSC)和Savitzky-Golay(SG)平滑方法对光谱进行预处理。选取全谱400~2500nm,400~1100nm,1100~1900nm,1900~2500nm,580~900nm等5个波段,每个波段分别采用原谱、一阶导数谱、二阶导数谱,共建立了15个定标模型。同时调整SG平滑点数和PLS因子数,每个模型分别进行PLS数值实验,按照预测效果进行优选。结果显示,采用1900~2500nm波段一阶导数谱的模型效果最好,预测相关系数(RP)、RMSEP、RRMSEP分别为0.806,31.0mg/kg和19.96%。这些结果表明,1900~2500nm波段可以代替全谱波段得到更好的预测效果,可为设计专用土壤近红外光谱仪提供依据。     

基于梯度折射率光子晶体可调谐亚波长聚焦特性的研究

本文对梯度折射率光子晶体的亚波长聚焦特性进行了研究。该光子晶体是由硅和圆形空气孔构成的平行平板,通过改变空气孔的结构来实现折射率的梯度渐变。采用时域有限差分（finite-different time-domain,FDTD）算法对光子晶体的聚焦过程进行仿真分析。研究发现,适当地修正光程差可以大大地提高聚焦效果,同时焦距和中心空气孔的结构对聚焦效果也有影响。综合以上3种要素,最终设计出的梯度折射率光子晶体平板可实现较好的亚波长聚焦效果,其中在光子晶体外部1.45 λ处的光斑最佳,半宽值可达到0.3447 λ。为了提升应用性能,设计了一个动态的调焦系统。在该光子晶体中加入半导体制冷片来调节温度,通过改变温度可以实现1.1374 λ～2.6264 λ的焦点调谐,同时焦斑半宽均小于0.4 λ。     

寒区高边坡机场坡顶土体振动响应研究

为解决寒区高填方机场坡顶土体安全问题,通过引入土体并联振动模型和快速傅里叶变换（fast Fourier transform, 简称FFT）,分析了振动台试验中冻结土样振动响应在时域和频域内的变化规律,提出了基于响应频率的冻结土样动力稳定性分析方法。研究表明：冻结土样在融化过程中的加速度增长比R_a、频率和频率增长比R_f均明显变大,但加速度幅值变化规律不明显;土样含水率越高,融化时间越短,R_f越大,完全融化后的响应频率值越大,但对加速度放大系数影响不大;在高温冻结阶段,R_f出现突变但R_a变化不显著,表明在频域中分析冻结土样振动响应变化比时域分析中灵敏度更高。振动台试验结果验证了土体振动并联模型的可靠性,对寒区高填方机场坡顶土体安全监测具有一定参考价值。     

基于近红外光谱法快速鉴别转基因油研究

采用近红外光谱法对转基因油/非转基因油的混合溶液进行研究。对采集到的原始光谱分别进行多元散射校正（MSC）、一阶导数（FD）、移动窗口平滑（MWS）、Savitzky-Golay平滑一阶导数（SG1）预处理。研究比较了不同预处理方法对转基因油/非转基因油支持向量机（SVM）建模判别分析的影响，其中MSC预处理后的模型预测效果最好，准确率为91.6%。为了进一步提高模型的精度与稳定性，采用连续投影算法（SPA）对全波长进行特征波长筛选。利用筛选后的15个特征波长输入到SVM中，预测准确率提高到98.3%。实验结果表明，采用近红外光谱法，可以实现对转基因油/非转基因油快速检测，不仅适用于纯转基因油的鉴别，也适用于非转基因油中掺入转基因油的鉴别。     

用BP神经网络预测热镀锌钢板的拉伸强度

运用BP神经网络,建立了热镀锌各工艺参数对热镀锌钢板力学性能影响的数学模型,并与线性回归模型进行了比较.结果表明:BP神经网络预测均方根偏差明显比线性回归预测均方根偏差小,表明该BP神经网络模型用于热镀锌板力学性能预测是可行的,并具有一定的实用性.     

基于深度置信神经网络的变风量空调送风量的预测

送风量的精准预测是实现变风量空调蓄冷量精确控制的重要环节。本文根据变风量空调送风量的影响参数,基于深度置信神经网络方法,建立变风量空调送风量的预测模型。将该模型的预测结果同BP、Elman和模糊神经网络的预测结果进行对比,结果表明,深度置信神经网络的预测精度最高,平均绝对相对误差、均方根相对误差和决定系数分别为1.555%、0.789%和0.9975,由此说明本文建立的模型能够精确有效地预测变风量空调的送风量。     

Application of hybrid neural network in discharge coefficient prediction of triangular labyrinth weir

Discharge coefficient (C_d) is an important parameter of triangular labyrinth weir. It is of great significance to predict the discharge coefficient accurately. In this research, in order to more accurately predict the C_d, in view of the traditional BP neural network is easy to fall into the local minimum in the training process, genetic algorithm (GA) and particle swarm optimization (PSO) are employed to optimize the traditional BP neural network's initial weights and thresholds. Nonlinear regression analysis (NLR) is also added to compare with these intelligent methods and four discharge coefficient prediction models are built, namely the NLR, the BPNN, the GA-BPNN and the PSO-BPNN. After the completion of the model construction, in order to objectively evaluate the performance of these models, the prediction results of these models are compared with the experiment results, and the determination coefficient (R²), the mean absolute error (MAE) and the root mean square error (RMSE) are introduced as the performance indicators to quantify the model performance. The results show that the accuracy and stability of the NLR are much worse than that of the intelligent models. The prediction results of the GA-BPNN and the PSO-BPNN are quite accurate with a higher decision coefficient than the BPNN. Moreover, the MAEs and the RMSEs of the GA-BPNN and the PSO-BPNN were significantly reduced by 25 and 40% compared with BPNN, respectively, and the maximum prediction errors were 4.4% and 2.6%, severally. Meanwhile, the width of error uncertainty band of GA-BPNN and PSO-BPNN is narrower than BPNN. By comparing GA-BPNN and PSO-BPNN with the discharge coefficient prediction models of triangular labyrinth weir in previous literatures, it is found that the mean absolute percentage error (MAPE) values of GA-BPNN and PSO-BPNN are 1.504% and 1.225% respectively, which are lower than other existing models. At the same time, the other performance indexes are better than most existing models, indicating that the genetic algorithm and PSO algorithm are more effective than the traditional BP algorithm in adjusting BP neural network parameters, easier to find the global optimal value, and improve the prediction accuracy and applicability of the model.     

Performance evaluation of two different neural network and particle swarm optimization methods for prediction of discharge capacity of modified triangular side weirs

Technical design of side weirs needs high accuracy in predicting discharge coefficient. In this study, discharge coefficient prediction performance of multi-layer perceptron neural network (MLPNN) and radial basis neural network (RBNN) were compared with linear and nonlinear particle swarm optimization (PSO) based equations. Performance evaluation of the model was done by using root mean squared error (RMSE), coefficient of determination (R²), mean absolute error (MAE), average absolute deviation (δ) and mean absolute relative error (MARE). Comparison of the results showed that both neural networks and PSO based equations could determine discharge coefficient of modified triangular side weirs with high accuracy. The RBNN with RMSE of 0.037 in test data was found to be better than MLPNN with RMSE of 0.044 and multiple linear and nonlinear PSO based equations (ML-PSO and MNL-PSO) with RMSE of 0.043 and 0.041, respectively. However, due to their simplicity, PSO based equations can be sufficient for use in practical cases.     

基于径向基函数神经网络的发动机磨损预测分析

针对BP神经网络算法的不足,利用径向基函数(RBF)神经网络建立设备的磨损预测模型,对光谱分析数据进行实例仿真,并与BP网络模型进行对比研究.仿真结果表明,该模型预测精度高,训练时间短,大大优于BP神经网络模型.     

BP神经网络修正灰色残差组合模型方法在油液光谱分析中应用的研究

提出了采用神经网络修正灰色残差组合模型对设备的磨损状态进行预测和诊断分析的方法。通过比较GM(1,1)模型、神经网络模型的预测结果,融合GM(GreyModel)模型与神经网络模型并构建组合模型进行油液光谱分析参数预测,可以克服单个模型所存在的不足。结果证明,该组合模型方法在预测中是可行的,预测的误差最小。     

马铃薯晚疫病害的高光谱图像空谱对比研究

为了快速检测马铃薯晚疫病,采用高光谱成像技术对马铃薯晚疫病的空谱信息进行对比研究以得到最佳判别手段。使用高光谱相机采集病害侵染0～6 d的高光谱图像,同时选取第6 d典型晚疫病病害的高光谱数据作为研究对象。采用二阶导数结合主成分分析和二次主成分分析分别从光谱和空间两个方面进行特征提取,之后基于特征波段反射率和主成分图像灰度值建立K最近邻分类算法、BP神经网络、决策树算法3种识别模型对不同时期病害进行识别。实验结果表明:基于二次主成分图像的灰度值结合BP神经网络建立的模型对马铃薯晚疫病的识别具有良好的成效,其识别率达96.6%。利用主成分图像灰度值建立的3种模型既减少了波段的冗余又提高了识别率,为研究和开发实时在线检测仪器提供了参考。     

Prediction of the machined surface quality of ball-end milling of H13 die steel using MLBP method

Abstract

Based on the characteristics of the surface quality prediction system of high-speed milling, the prediction model is used to predict the surface quality of analyzing the advantages of the two methods of using the multilinear and BP neural network model (MLBP) method. This article through the in-depth study of the surface quality, study the surface quality prediction based on the characteristics of multiinput multioutput nonlinear systems, respectively, established a linear regression equation, BP neural network model, and the surface quality of specific conditions to start prediction. The prediction results show that these prediction methods can play a special role as certain conditions. However, owing to the limitations of multiple linear regression and BP neural networks, their generalization ability and robustness cannot meet actual needs. Drawing on the idea of interpolation, and analyzing the advantages and disadvantages of linear regression and BP neural network to solve nonlinear problems, a new prediction method is developed. The main idea are to use interpolation method to insert preprediction under the premise of linear prediction; to process the values and obtain a unified prediction result from linear regression; to combine the experimental results from the pretreatment results; to use these input information as the input content of the BP neural network; to establish a training model based on the BP neural network model self-learning process. This training model predicts the quality of the machined surface. This method is abbreviated as the MLBP method. The experimental results and comparison of model prediction results show that this method can effectively improve the generalization ability and robustness of the prediction model, and further improve the model’s prediction accuracy.     

Prediction of Wing Aerodynamic Performance in Rain Using Neural Net

A new method for prediction of wing aerodynamic performance in rain condition was presented.Three-and four-layer artificial neural networks based on improved algorithm for error Back Propagation(BP)network were respectively built.Detailed approaches to determine the optical parameters for network model were introduced and the specific steps for applying BP network model to predict wing aerodynamic performance in rain were given.On this basis,the established optimal three-and four-layer BP network model was used for this prediction.Results indicate that both of the network models are appropriate for predicting wing aerodynamic performance in rain.The sum of square error level produced by two models is less than 0.2%,and the prediction accuracy by four-layer network model is higher than that of three-layer network.     

基于遗传算法的人工神经网络在航空发动机磨损预测中的应用

提出了一种将遗传算法和BP算法相结合的学习算法来训练BP神经网络，实现网络结构的优化，并用优化后的BP人工神经网络建立了航空发动机的磨损预测模型。将该模型预测结果与BP算法和多元线性回归法的预测结果进行了比较。检验结果表明：基于遗传算法的BP神经网络优于BP算法及多元线性回归法，具有良好的预测效果。