神经网络在个人信用组合预测中的应用

该文运用组合预测的思想,提出了通过感知器、BP、Elman和LVQ等不同的具有代表性的神经网络模型,将多元线性回归和logistic回归两单一方法进行组合,并分别应用于某商业银行的个人信用评估,其结果表明:感知器、BP、Elman和LVQ神经网络组合预测方法精确度不尽相同,但总体上能够获得比多元线性回归和logistic回归更高的预测精度,尤其在避免纳伪错误方面更具优势。     

Support vector machine forecasting method improved by chaotic particle swarm optimization and its application

By adopting the chaotic searching to improve the global searching performance of the particle swarm optimization (PSO), and using the improved PSO to optimize the key parameters of the support vector machine (SVM) forecasting model, an improved SVM model named CPSO-SVM model was proposed. The new model was applied to predicting the short term load, and the improved effect of the new model was proved. The simulation results of the South China Power Market’s actual data show that the new method can effectively improve the forecast accuracy by 2.23% and 3.87%, respectively, compared with the PSO-SVM and SVM methods. Compared with that of the PSO-SVM and SVM methods, the time cost of the new model is only increased by 3.15 and 4.61 s, respectively, which indicates that the CPSO-SVM model gains significant improved effects. Foundation item: Project(70572090) supported by the National Natural Science Foundation of China     

江西省农业旱情预测模型的建立与应用

根据农业用地的不同性质分别建立旱地缺墒模型,灌溉水田、水浇地、菜地与望天田缺水度模型,并据此建立江西省农业旱情预测模型,对江西省农业旱情进行预测.为科学抗旱和减少旱灾损失提供依据和指导.     

Compressibility of fine-grained soils subjected to closed-system freezing and thaw consolidation

In order to investigate the effects of freezing and thawing on the compressibility of fine-grained soils, freezing and thawing tests and subsequent compression tests with fine-grained soils in an oedometer were carried out. During the freezing, a part of the soils is loosened and another part is over-consolidated under the freezing pressure ?E. The compression curves after the freezing and thaw consolidation are neither different from the normal consolidation curve nor from the rebound curve of an unfrozen soil, until the consolidation pressure ?z = ?E is arrived. Based on the experimental results, a theoretical model has been developed to predict the frost heaves, the thaw-settlements and the compressive deformations of fine-grained soils after the thaw consolidation. The theoretical results are very close to the experimental results.     

牡丹江长江屯站2009年1月冰坝特征及其成因分析

对牡丹江长江屯站2009年1月5~7日形成的冰坝的概况、河道特性、冰坝特征及成因进行分析,以期为冰坝预测及凌汛分析等相关研究提供参考。     

多步自适应组合预测及其应用

提出一种多步自适应组合预测方法.预测由多个并行不同的多步自适应预测模型组成,最终预测结果,由多个预测模型预测值的线性加权组合决定.本法适用于随机时变动态系统过程的多步预测问题,在某省粮食产量趋势预测中,应用此法获得了良好的效果.     

方形气固流化床从鼓泡到湍动流型转变的实验研究

在368mm×368 mm方形气固床中对FCC颗粒进行流态化实验,研究了从鼓泡到湍动的流型转变行为及相关问题.实验测试了多个床层截面的压差波动,由波动标准差随表观气速变化的最大值获得了流型转变速度Uc.结果表明,方形床中的流态化平均行为在床层截面纵横两个方向一致,沿床层轴向呈现不均匀性,底部存在颗粒密相区;不同床层截面转变速度Uc不同,由床层上部向下扩展,Uc呈线性增加关系,说明流型转变至上而下进行;静床高度对Uc影响显著,静床高度增加,床层轴向各截面Uc相应增加;以上结果表明了目前仅与气固物性参数相关联的Uc预测模型有待改进.     

2种不同类型的沉降样本对数据处理影响的研究

利用小波模型、神经网络模型及小波神经网络模型,分别以累积沉降样本和间隔沉降样本作为训练样本对沉降进行了分析预测,证明了在大多数情况下采用间隔沉降样本进行沉降分析预测的效果较好．     

封装板式冰蓄冷系统蓄能模糊建模与分析

针对冰蓄冷系统蓄能的非线性特性,将自适应神经网络应用于封装板式圆罐型蓄冰装置的蓄能初始化和释冷出口温度实时运行的模糊建模,进行了冰蓄冷系统蓄冷量的模糊建模,确定了实验影响因素载冷剂进口温度、载冷剂流速、蓄冷时间的隶属度函数和模糊推理规则.运用减法聚类法和网格法对模型进行初始化训练与运行对比,使蓄冷系统能够跟踪负荷情况.通过调控影响因素的参数,可以更合理地初始化设定蓄冷阶段的蓄冷量.利用该建模程序进行实时释冷出口温度模糊建模策略验证,模型运行平稳.冰蓄冷装置蓄能模糊控制性能的优化保证了蓄冷量与负荷相匹配,实时输出释冷出口温度,进而达到冰蓄冷空调系统优化及经济运行的目标.     

Effect of Curing Regime on Bonding Strength of EVA Modified Mortar to Tile

Ethylene-Vinyl Acetate (EVA) redispersible powder and latex were used to modify mortar. Three kinds of curing regimes: standard curing, high temperature curing and freeze-thaw circle curing were adopted to cure the bonded samples. Bonding strength of EVA modified mortar was tested at 28 days. The development of bonding strengths under all three curing regimes were discussed and compared. The experimental results show that bonding strength increases with the increase of EVA content in mortar. The curing regi...