Effect of Completion of Vernalization on Generative Development of Winter Rape (Brassica napus L. var. oleifera) Plants

Germinating seeds and young plants of winter rape var. Górczañski were vernalized for 56–63 days under conditions of 9-hour day, at the temperature 2 and 5 °C and in continuous darkness at the temperature 2 °C. After vernalization the plants grew under conditions enabling to complete vernalization: in a glass-house at the temperature day/night 15/10 °C and in semi natural conditions of open vegetation hall in the period from June till August. After sub-optimal vernalization further growth of the plants at lowered temperature increased its effectiveness (completion of vernalization). Depending on the degree of the vernalization of the plants the completion of their vernalization was both obligatory, i.e. conditioning the acquisition of the ability of generative development, and facultative i.e. accelerating this development. It has been demonstrated that the population of plants of the examined variety is strongly differentiated not only with respect of vernalization requirements in the particular plants, but also what regards the effectiveness of vernalization completion. New observations have been made indicating that the mechanisms controlling the successive phases of generative development, i.e. phase of forming flower buds and the flowering phase are not identical which may be interpreted as indicating that the "flowering factor" is polymorphous.     

基于NGO-CNN-SVM的高标准农田灌溉工程施工成本预测

为提高高标准农田项目施工成本的预测精度,控制施工成本在合理范围,减少投资风险,该研究从单体灌溉工程施工成本预测角度出发,通过随机森林（random forest,RF）筛选出高标准农田灌溉工程施工成本的关键影响因素,结合卷积神经网络（convolutional neural networks,CNN）和支持向量机（support vector machine,SVM）两种模型的优点,通过北方苍鹰优化算法（northern goshawk optimization,NGO）对模型里的惩罚因子和核参数进行寻优,构建基于NGO-CNN-SVM的施工成本预测模型。通过辽宁省2018—2023年高标准农田工程中灌溉工程的施工成本数据,选取样本决定系数R²、平均绝对误差MAE、平均绝对百分比误差MAPE和均方根误差RMSE作为精度指标进行分析,结果表明：基于NGO-CNN-SVM的施工成本预测模型在渠道工程中MAE低于0.615万元,RMSE低于0.512万元,R²达到0.968以上,相对误差小于4.210%;在进水闸工程中MAE低于0.610万元,RMSE低于0.536万元,R²达到0.966以上,相对误差小于4.410%;在桥涵工程中MAE低于0.494万元,RMSE低于0.477万元,R²达到0.970以上,相对误差小于3.548%,并相比较于反向传播神经网络,CNN和CNN-SVM模型,NGO-CNN-SVM模型的预测结果均最优。通过特征选择、模型融合、算法优化以及不同模型对比表明NGO-CNN-SVM模型具有更高的预测准确率和泛化性,可为高标准农田灌溉工程施工成本预测提供理论依据。     

理化复合参数和神经网络结合的冬小麦长势遥感监测

准确、及时地监测区域作物长势状况对农业规划和政策的制定与调整具有重要的意义。遥感技术作为一种收集大面积作物长势信息的有效手段,正日益受到关注。为提高冬小麦长势遥感监测的准确性和全面性,该研究基于田间实测的冬小麦拔节期地上鲜生物量（aboveground fresh biomass,AFB）、叶面积指数（leaf area index,LAI）、叶片叶绿素相对含量（soil and plant analyzer development,SPAD）和叶片氮含量（leaf nitrogen content,LNC）4种生长相关理化参数,利用熵值法获取各参数权重构建冬小麦理化复合参数（physico-chemical composite parameter,PCCP）。利用显著性检验和籽粒产量数据分析复合参数在量化冬小麦长势方面的性能。然后,以Sentinel-2A作为数据源,分析不同遥感指数与LAI、SPAD、AFB、LNC和PCCP的相关性。选取相关性较高的遥感指数作为反向传播（back propagation,BP）人工神经网络（artificial neural networks,ANN）的输入,建立冬小麦长势遥感监测模型,对PCCP进行估计。评价模型精度并用于监测研究区冬小麦长势分布特征。赋权结果表明,作物物理参数的权重大于生化参数,其中LAI的权重最大,为0.387,AFB和SPAD次之,LNC的权重最小,为0.105;PCCP性能评估结果表明,与单一理化参数相比,PCCP值能更好地揭示作物长势状况的差异,其与最终籽粒产量的相关性更好, 决定系数提高0.035～0.468,均方根误差减少46.2～520.0 kg/hm²;在遥感监测过程中,PCCP比单一理化参数有更好的应用潜力,BP-ANN长势遥感监测模型模拟PCCP精度较高,在测试集中决定系数为0.830,均方根误差为0.080;研究区冬小麦总体长势稳定且分布集中,呈现"中部差,南北好"的空间分布特征。因此,构建作物理化复合参数用于量化作物长势是提高长势监测可靠性和准确性的一种有效方式,可为冬小麦田间管理提供科学依据,服务于发展智慧农业和建设农业强国的战略需求。     

物流企业的社会网络特征与企业间信任的构建

第三方物流企业较之其他企业显示出较强的网络特征，企业之间的社会关系网络及其信任构建对企业的生存和发展具有重要意义。本文通过实证研究发现，物流企业信任的形成与企业社会网络的形成过程密切相关，企业组织社会网络的连接对组织信任的构建产生着重要影响。信任加速了企业获取资源的速度和质量，资源获取是企业网际互动的目的和信任的结果。     

Artificial Neural Networks Models for Flow Stress during High Temperature Plastic Deformation of Al-Li Alloy

Using gained experimental data to develop the models of stable flow stresses at high temperature plastic deformation by statistical methods for alloy materials, precision of the models is poor and at the same time the processes of modeling are complicated with great workload. On the basis of the data obtained on Gleeble-1500 Thermal Simulator,the predicting models for the relation between stable flow stress during high temperature plastic deformation and deformation strain, strain rate and temperature for 1420 Al-Li alloy have been developed with BP Artificial Neural Network method. The results show that the model on basis of BPNN is practical and it reflects the real feature of the deforming process. It states that the difference between the real value and the output of the model is in order of 5 percent.     

Multiple Layer BP Neural Network for Fuzzy Calculating

The FCBP(Fuzzy calculating BP) algorithm which is proposed by this paper hasovercome the sensitivity for samples,reduced the number of input layer's samples,lightened the burden of input layer.it is suitable to fuzzy inference and pattern recognition.     

Clustering Routing for Wireless Sensor Networks

In wireless sensor networks that consist of a large number of low-power sensors.Because the sensor's energy is limited,one of the main design is to obtain long system lifetime.The authors firstly analyse LEACH and LEACH-C clustering routing for wireless sensor networks.Aimming at their shortcoming,they present a new routing LEACH-NEW.This routing uses multi ho Pinstead of one hop.At last,they use NS2 to simulate them.Simulation show results that new routing exhibits noticeably longer system lifetime than rouing LEACH and LEACH-C.     

基于混沌算法的工程车辆自动变速神经网络控制

为了克服BP神经网络收敛速度慢和易陷入局部极小点的不足，提出了一种基于混沌算法的工程车辆自动变速神经网络控制方法，并利用ZL50型装载机传动系统换挡控制试验的数据进行了验证性仿真试验。仿真结果表明：该方法对于车辆自动换挡智能控制是可行的，可以根据操作工况实现正确的变速挡位决策。     

自压式树状管网的两级优化设计模型与神经优化设计

建立了自压式树状管网两级优化设计模型，并用人工神经网络法实现树状管网非线性规划模型的快速求解。采用的人工神经网络技术的两级优化设计模型在适用范围、求解速度和获得最优解能力上，均优于单一的非线性规划模型和线性规划模型，是实现树状管网全局优化设计的一条新途径。