B-P神经网络在作物生育动态模拟中的应用

利用B－P神经网络对作物生育动态进行模拟。在对B－P神经网络的结构和训练算法加以选择后，网络模型具有拟合精度高、收敛速度快和泛化能力强等特点。B－P网络可用于作物生育进程中单输入单输出、单输入多输出、多输入单输出和多输入多输出动态关系的模拟和作物生育动态的预测。     

基于改进的 AlexNet 卷积神经网络的植物叶片识别

针对多类植物叶片识别准确率和计算效率低问题,通过残差连接卷积层,构建了一种基于残差连接的Alexnet卷积神经网络。对卷积层的输入数据进行批归一化,进而加速网络的收敛速度。利用两种不同的全局池化算法既能减少特征图数目又能提高算法识别植物叶片的准确性和计算效率。对于不同种类植物叶片,实验验证残差连接的Alexnet卷积神经网络能够进行高效识别。     

基于无迹卡尔曼滤波神经网络的光伏发电预测

针对光伏发电系统在不同天气状况下发电功率预测精度不高的问题,在分析传统方法的基础上,提出一种无迹卡尔曼滤波神经网络光伏发电预测方法。该方法利用无迹卡尔曼滤波实时更新神经网络模型的权重,以直流电压和电流作为系统的输入,以有功功率和无功功率作为系统的输出,分别建立两个独立的双输入单输出功率预测模型。实验结果表明：所提出的方法对有功功率和无功功率的预测精度分别为97.3%和94.2%,并且对天气具有良好的鲁棒性。     

基于BP神经网络的常规化学成分预测烟气成分和感官得分预测模型研究

为了探索内在化学成分与卷烟烟气指标和感官品质得分之间的关系,建立相应的预测卷烟烟气指标和感官品质得分神经网络模型数学模型。测试了A牌号卷烟不同批次成品卷烟常规化学成分、主流烟气化学成分和感官得分,以常规化学成分作为网络输入,分别建立主流烟气化学成分和感官得分的BP神经网络预测模型。隐含层节点为9,输入函数为Tansig,输出函数为Purelin。训练方法为梯度下降法。选择22个样本作为训练样本,其中19个作为测试样本,3个作为验证样本。训练的目标为允许误差0.000 1,最大迭代次数10 000次。预测结果与烟气常规化学检测和人员实际评吸结果比较,相对标准偏差小于5%,达到了较好的预测结果。该模型对于预测卷烟主流烟气成分的释放量和感官评价具有指导意义。     

毛竹导热系数的神经网络预测模型

为了准确测算一定范围内的毛竹导热系数,同时改进现有的竹材导热系数研究方法,笔者采用激光闪光法精确测量毛竹导热系数值,并以此为基础,建立毛竹导热系数随不同温度和密度变化的神经网络预测模型。由于原始BP算法收敛速度慢,笔者使用Trainlm函数训练神经网络模型,确定了最佳隐层神经元个数,并对该模型的输出预测值进行线性分析及误差分析。实验结果如下：毛竹导热系数神经网络模型具有很高的预测精度,能准确预测一定条件范围内毛竹的导热系数,从而节省了以往常规试验所花费的大量时间和资源。本研究初步揭示了毛竹导热系数随温度、密度等因素的变化关系,为进一步研究毛竹热物理特性提供了理论依据。     

用模糊神经网络提高洪峰预报精度的研究

在大量研究的基础上,提出了基于模糊理论的神经网络改进算法,用来提高对洪峰的预报精度。该方法在网络训练时引入模糊理论来确定网络误差修改的程度。引入的算法增大了大值输出样本和期望输出的误差,使得网络向着提高洪峰拟合精度的方向修改权重。应用表明,改进的模糊BP神经网络能够较好的反映洪水演进机理,提高了神经网络洪水预报模型对洪峰的预报精度,保证了洪峰预报的可靠性。     

基于遗传算法的BP神经网络在小麦蛋白质含量预测中的应用

为了快速、简便、准确地测定小麦蛋白质的含量,本文提出了应用近红外光谱分析技术结合遗传算法(GA)的BP神经网络的建模方法。采用SPXY算法对光谱数据进行了合理划分,并运用连续投影算法(SPA)将预处理过的数据压缩,对光谱数据提取最佳敏感波点作为GA-BP神经网络的输入,建立小麦蛋白质含量的校正模型。模型的预测均方根误差和预测相关系数为1.3379和0.979,并与BP神经网络所建立的校正模型进行了比较。结果表明：GA-BP神经网络所建模型收敛速度快、训练时间短、准确度也较高,能够实现对小麦蛋白质含量快速高效的检测。     

三维谱特征下的汽车尾气评估方法

针对汽车尾气排放的非线性、时变性问题,提出一种三维谱特征下的汽车尾气评估方法。该方法利用频谱分析的原理对汽车尾气进行时频转换,得到尾气的三维谱特征。这些三维谱特征作为输入被提交给径向基神经网络,在K均值聚类算法的驱动下,径向基神经网络完成训练与测试,实现对三维谱特征的分类,从而评估相应的汽车尾气排放水平。数值实验结果表明,提出的汽车尾气评估方法具有较高的准确性。     

基于LM-BP神经网络的耕地土壤养分等级划分模型──以皖南山区为例

研究旨在通过BP神经网络方法,构建起LM-BP网络结构(5-M-1)模型,达到对土壤养分等级划分的目的,为合理的土壤养分管理提供可靠依据。采用Levenberg-Marquardt (LM)训练算法,构建3层网络模型：一个输入层、一个隐含层、一个输出层,利用3层网络作为耕地土壤养分等级划分模型。利用土壤养分各级评价标准作为模型的训练样本和测试样本,以此来对BP神经网络进行训练和测试,并对歙县土壤养分进行综合评价。结果表明：LM-BP网络结构对测试样本输出的预测值和实际参考值是一致的。最终通过灰色关联模型和主成分分析方法对歙县土壤养分的综合评价结果与BP神经网络的模拟结果相对比,发现也是基本一致的。LM-BP网络结构应用于土壤养分等级划分中,得到了很好的预测效果,为智能算法应用于农业领域奠定了良好的基础。     

云制造环境下设计需求与服务匹配模式算法

针对云制造环境下设计需求与设计服务的特性,构建含有属性集、关系集和操作集的设计需求与设计服务数据结构。建立一种云制造环境下的设计需求与设计服务输入、分解、组合和输出匹配模式,研究了该模型的原子匹配、扩展匹配和产品匹配。针对匹配过程中输入、分解、组合和输出量化问题,采用语义概念相似度和循环递归设计结构匹配算法实现设计需求与设计服务智能匹配。最后,通过实验验证,表明该模式与算法的有效性和可行性。     

Fast algorithm for apparent resistivity calculation based on back propagation neural networks

To avoid the complex numerical calculation for the electromagnetic field and determine underground abnormality, a neural network based method is proposed. In consideration of turn off transmitter current, the effect of a linear ramp turn off current on transmitter is corrected. The characteristics of transient expression and the traditional calculation algorithm for apparent resistivity are analyzed, and a predigest structure of network is obtained based on the kernel expression. The three layer back propagation(BP) neural network is trained by using sample data in homogeneous half space, and its number in hidden layer was determined. The method proposed is compared with two traditional calculation methods with simulation experiments. The result demonstrates that BP neural network has a high speed of processing data and is useful in explanation of the transient electromagnetic method.     

Mine transient electromagnetic field multiples phenomenon

In order to accurately calculate the magnetic field parameters of mine transient electromagnetic field based on the former research theory of transient electromagnetic field full-space and half-space combined with transient electromagnetic space applications in mines this article studies the relationship of transient electromagnetic field intensity and half-space transient electromagnetic field and proposes the multiple phenomenon of transient electromagnetic. Research results show that full-space transient electromagnetic field intensity and half-space transient electromagnetic field intensity has multiple phenomenon. They have 2 times relationship in the early stage and have 2.5 times relationship in the late stage. Similarly mine transient electromagnetic field intensity electric field intensity and apparent resistivity calculations also have multiple relationships. Putting forward the multiple phenomenon has important reference value in theory and practice for researching the mine transient electromagnetic field.     

The Multi-objective Fuzzy Optimal Power Flow Model and its Neural Network Algorithm

This paper has presented a multi-objective fuzzy optimal power flow medel.Inthe model , the multiple objectives, such as the minimum generation cost and the minimum powerloss, have been considered simultaneously, A new algorithm based on neural network models is aisopresented,in which the neural networks are employed to express, the membership function of fuzzysets and solve the optimization problems. The validity of model and algorithm is verified with numerical examples.     

Stratification and Bearing Capacity Prediction Method Based on BP Neural Network for Foundation in Huaibei Plain

According to the features of stratification and obvious inhomogeneity in geological soil in Huaibei plain, BP neural network prediction method for stratification and bearing capacity calculation of multiple cross-bedded foundation was proposed. By comparing the results of drill sampling, static cone penetration tests and screw plate tests, plate loading tests, penetration resistance ps value was found as an evaluation index for stratification and bearing capacity prediction of cross-bedded foundation. Moreover, gradient descent algorithm and conjugate gradient algorithm BP neural network models were obtained, and the calculation results of the two algorithms were comparatively analyzed. The results show that penetration resistance value can be taken as an evaluation index for stratification and bearing capacity prediction of cross-bedded foundation in Huaibei plain. Gradient descent algorithm and conjugate gradient algorithm BP neural network models have good results for soil identification and bearing capacity determination, which can meet the accuracy requirements of actual engineering. However, the computational efficiency of gradient descent algorithm is significantly lower than that of conjugate gradient algorithm.     

artificial neural networks based prediction of electromagnetic compatibility problems

It is necessary to predict electromagnetic compatibility (EMC) for electronic equipment and systems. We proposed a fast EMC prediction approach via artificial neural networks (ANN). By choosing relevant electromagnetic interference parameters as the input prediction features, a back propagation (BP) neural network was used to construct the mapping between the input prediction features and the electromagnetic disturbance response of the sensitive system. The EMC fast prediction BP model was trained and tested by sample sets generated using an electromagnetic computational method. We used this method to predict the crosstalk coupling between two wires. The experimental results show the effectiveness of the proposed method.     

A Study Transient on Predictive Calculation Method of on Underground Ventilation Network

The authors developed a computer program of transient predictive calculation method on underground ventilation network. The program approximated a field data set of seasonal cyclic changes of air Temperature and humidity at the inlet to the sine curves, and included sensible heat conduction from rock to air current. The temperature of rock around and airway was calculated by finite difference method. The prediction method can be used to calculate the variation of flow rates, temperatures and humidities of air flow in the airways along underground network.     

A Numerical Method for Transmission Line Equations

Transient analysis of transmission line has recently been received more attention because operating speeds in high-speed digital electronics are increasing. Transmission line equations are hyperbolic partial differential equations, firstly this paper deduces how to change transmission line equations into quasilinear differential equations , thus the transmission line equation numerical result is gotten by computing the differential formation of quasilinear differential equations. The constraint of voltage and current is be considered and lumped equivalent circuit mode at boundary network collaborated at the same time in finding boundary conditions. Finally the paper computes transient response of transmission line with two typical boundary conditions. Numerical result shows that this approach is an effective way. It is explicit algorithm with less CPU consumption which can get time field response directly. The agree-upon effective way does be frequency field method, however it could not get time response unless the numerical inverse laplace transformation (NILT) be introduced. Thus this approach is more effective than FFT algorithm.     

A new pattern recognition method of gas sensor array detection

BP neural network based gas sensor array detection pattern recognition has some disadvantages, such as slow convergence and local minimum problem. A modified immune neural network model which combines BP algorithm and immune algorithm is proposed to enhance global search capability and improve the performance of the neural network model. Orthogonal test is adopted to design the study samples of neural network. This ensures the accuracy of neural network while reducing the number of samples. The simulation results show that the proposed pattern recognition method solves the cross sensitivity of gas sensor effectively, overcomes the disadvantages of traditional BP neural network and improves the learning speed and detection accuracy.