Nonlinear Seismic Response Analysis of Long- span CFST Arch Bridge

The non-linear seismic response behavior of concrete filled in steel tube(CFST) arch bridge subjected to synchronous seismic excition and multi-support seismic excitation is studied in this paper.The non-linear seismic response of CFST arch bridge is calculated by time-history analysis method,and the effect of geometric nonlinear to long-span CFST arch bridge is studied.The influence of internal-force and deformence under dead-load,multi-support seismic excitation,etc to nonlinear seismic response behavior of CFST arch bridge is analysed.The result show that the effect of geometric nonlinear to long-span CFST arch bridge is obvious.     

基于BP神经网络的农业电子商务网站评价研究

提出了适合农业电子商务网站的评价指标体系。建立农业电子商务网站的BP神经网络评价模型,通过BP神经网络对数据进行训练、测试,对提出的评价指标体系进行了验证。通过对结果的分析发现,建立的基于BP神经网络的评价模型在农业电子商务网站评价中具有可行性,在网站建设方面具有较强的参考价值。     

人工神经网络在作物基因组选择中的应用

目前, 基因组选择育种主要采用线性模型估计遗传育种值指导作物遗传育种的筛选过程, 但是生物体内的基因以及遗传位点的关系主要是复杂的非线性调控。本研究将人工神经网络技术应用到作物基因组选择育种中, 对现有的作物基因组选择育种模型进行优化, 建立了高效的作物基因组选择预测系统, 并与其他线性回归预测模型进行比较。通过分析小麦的育种数据发现, 基于人工神经网络的遗传育种估计效果优于其他线性回归预测模型, 预测育种值与实际育种值间的相关系数平均值达到0.6636, 相应的岭回归BLUP、贝叶斯线性回归模型和基于系谱信息的贝叶斯回归模型的预测能力分别为0.6422、0.6294和0.6573; 最优的预测效果达到0.8379, 远高于其他2种模型的最优结果。同时, 基于人工神经网络的基因组选择模型的预测效果稳定, 与传统的统计模型相近, 因此, 利用人工神经网络技术建立基因组选择是可行的。     

基于 SPA-RBF神经网络的小麦蛋白质含量无损检测

传统半微量凯氏法测量小麦蛋白质含量繁琐费时,应用近红外光谱分析技术结合SPA-RBF神经网络对小麦蛋白质含量进行快速、无损检测.采用SPXY算法划分校正集和预测集样本,运用连续投影算法(SPA)对一阶微分和SNV预处理后的光谱数据提取敏感波点作为RBF神经网络的输入,建立小麦蛋白质含量的SPA-RBF神经网络校正模型.模型的预测均方根误差和预测相关系数可达到0.26576和0.975,预测效果较好,基本上可以完成粮食储备和食品加工行业对小麦及其制品品质的划分以及育种上的前期世代筛选.研究表明:近红外光谱技术结合SPA-RBF神经网络可实现对小麦蛋白质含量的检测,满足现代农业发展对小麦无损、实时、大量检测的需要.     

基于RBF神经网络的蔬菜价格预报研究

准确预测农产品市场价格对于农户生产决策与政府调控等具有重要意义。针对蔬菜市场价格预报的复杂性,利用RBF神经网络的特性,应用2003-2007年的香菇市场价格数据建立蔬菜价格预报模型,并对RBF神经网络模型的参数选择进行分析。最后应用模型对2008-2009年的香菇市场价格数据进行预报,通过与BP神经网络模型预报结果进行比较,表明RBF神经网络模型具有更高的预报准确度。     

Research on Load Prediction Model of Air Condition System Based on Elman Neural Network

The load of air condition system is influenced by many factors, and they are variable and nonlinear, The relation between them is dynamic,It is impossible to forecaste the load of air condition syestem accurately by traditional method. But Recurrent Neural Network is able to reflect the dynamic lively and directly. Elman is one of the typical RNN. Based on the analysis as above, prediction model of air-condition system based on Elman neural network is established, and some prediction is done. The prediction accuracy of Elman neural network and BP neural network is compared, and the experiments show that the Elman neural network is efficiency and accuracy , so Elman neural network is a new and reliable method for predicting the load of air-condition system.     

Speed Estimation Methods Based on Neural Network

In order to solve the speed estimation problems of speed sensorless vector-controlled induction motor drives, the paper presents two speed estimation schemes based on neural network mode identification theory. The advantages of each scheme are discussed and the simulation results show that the estimated speed can trace the actual speed better (even under the circumstances of load variation or speed step variation). Also, these schemes are not sensitive to the variations of motor parameters and the effect of iron loss. Therefore, the proposed neural network based on speed sensorless vector-controlled induction motor drives have good performance in stady-state and transient-state operation.     

Research and Development of Evaluation system Based on Neural Network and Expert System

As a single system of evaluation, both neural network (NN) and traditional expert system (ES) have many limitations. Developing evaluation system integrating NN with ES is an available way to offset their weakness. With black-box module, a new frame of evaluation system is developed in relative independent method. Then, a way of programming and realizing evaluation system, which is more close to human thinking, is put forward.     

基于BP神经网络的冬季日光温室小气候模拟

为了系统分析日光温室内外气候特征的关系,向日光温室作物环境调控及小气候预报提供支持,根据冬季日光温室内小气候观测试验资料和附近气象站观测资料,利用BP神经网络方法建立3个模型,分别对3种不同天气状况下石家庄地区日光温室冬季小气候特征进行模拟。结果表明,3个模型气温训练值与实测值的均方根误差(RMSE)都在2℃以内,决定系数都在0.95以上;相对湿度训练值的RMSE都在2个百分点以内,决定系数均高于0.95;接受到的太阳辐射的训练值与实测值的RMSE都在16 W/m2以内,决定系数也均超过0.95。利用此模型得到的气温预测值与实测值的RMSE都在2℃以内,决定系数都在0.9以上;相对湿度预测值与实测值的RMSE都在4个百分点以内,晴天和少云-多云状况下决定系数均高于0.9,寡照状况下的决定系数略低,约为0.8;接受到的太阳辐射的预测值与实测值的RMSE都在26 W/m2以内,决定系数均超过0.95。说明所建BP神经网络模型对于不同天气状况下石家庄地区日光温室冬季小气候特征模拟都有较高的精度,可以用于预测。     

Improved Learning Effect Synthetic Evaluation Method Based on Backpropagation Neural Network

Aim at the practicability issue,study effect-evaluating model based on B-P NN was improved on evaluation standards,evaluation model and training swatch.Evaluation standard effectivity was added to set the conversion function of network crytic-layer nodes as'tansig' and that of output-layer nodes as'logsig'.The taining swatch was improved.The simulation results validated the evaluation veracity of the model.     

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。     

Design and Application of Compensatory Fuzzy Neural Network Based on Adaptive Learning Rate Method

To overcome the disadvantages of general networks such as slow convergence speed and being unable to combine with the expert knowledge etc,the authors introduces compensatory fuzzy neural cells,integrate the powerful knowledge expressiveness of fuzzy system and the excellent self-learning of neural network,and present a novel Compensatory Fuzzy Neural Network(CFNN) based on Adaptive Learning Rate Method which changes the learning rate using Adaptive Learning Rate Method in dynamic way.Finally this method is applied to the actual case.The result proves that it not(only) can adjust parameters properly on line,but also can optimize relevant fuzzy reasoning in dynamic way,fasten training rate.     

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。     

Intelligent Control of the Nonlinear Seismic Response of a 3 Story Benchmark Building

Intelligent materials, control devices and intelligent control algorithm research and development in recent years have opened a new world for seismic resistance and disaster reduction in civil engineering. We designed and fabricated a new piezoelectric friction damper. In our research, we regarded the piezoelectric friction damper as the control device. We proposed a fuzzy control algorithm for reducing nonlinear seismic response of a 3 story benchmark building and established the interactive relationships between structural responses and fuzzifier factors, defuzzifier factor. A numerical simulation is carried out to analyze the nonlinear seismic responses of the controlled 3 story benchmark building. The simulation results are compared to those of other control strategies. The results show that the fuzzy control can reduce the nonlinear seismic response of 3 story benchmark building and minimize the structural damage caused by strong earthquakes.     

Craft Orbit Selection by Knowledge Based Neural Network

There are more than one measure devices during the craft launching proceeding, reliable craft orbit measurement selection is important for launching monitor and safety control. This paper proposes a novel orbit selection method by knowledge based neural network, which combines the human knowledge and orbit samples based training together. The false spur orbit data are deleted according the data continuity rule at first, then the difference between orbit data is computed, and at last a neural network is trained to test reliability of each data and select the orbit with high precision among all orbit data. Simulations and experiments show the efficiency and reliability of our method.     

Malfunction Diagnosis of Three-phase Full-bridge Controlled Rectifier Based on BP Neural Network

The diagnosis of the power electronic circuit is very intricate. One of the main reasons is that the structure of the circuit will change if the power device is not working .The thyristor is the easiest to be mangled. So diagnosing the malfunction is the most important about the diagnosis of the power electronic circuit. The paper puts forward a malfunction diagnosis of the thyristors of three-phase full-bridge controlled rectifier with BP neural network. After analyzing the output waveforms of malfunctioning circuit and training a BP neural network with the sampling data of malfunctioning waveforms, a well training BP neural network is constructed and used to diagnose the malfunction. The simulation and experiment demonstrate that this method is valid.     

Fault Diagnosis in Hydraulic Turbine Governor Based on BP Artificial Neural Network

The governing system of hydraulic turbine generator plays an important role in power system. It is significant to find out the faults of governing system and remove them quickly. This paper sets up a new fault diagnosis model of the hydraulic turbine generator governing system with the advanced ANN (artificial neural net). This 17-in-13-out model consists of three layers. It is proved that this model can find the fault accurately.     

Evaluation of Academic Degrees and Graduate Education Based on Neural Network

With the development of the academic degrees and graduate education, evaluation is the important measure for guaranteeing the quality in the area. With increasing complication of the target of the evaluation of academic degrees and graduate education , it is necessary to introduce nonlinear method of the evaluation, which has great significance for the validity of the result of the evaluation. Neural networks have been developed greatly in recent years,they have the advantages of nonlinear mapping,parallelity ,adaption, etc. Therefore , they are good tools of nonlinear modeling. On the basis of setting up the model of the evaluation based on neural network ,this paper presets the practical value of the method.based them.