模糊认知图在股票市场预测中的应用研究

复杂系统中存在着大量的过程依赖、自组织,并且一直是进化的,用传统的方法对其建模十分困难。模糊认知图作为一种模糊逻辑和神经网络相结合的产物,为复杂系统建模提供了一种有效工具。文中根据模糊认知图的特点,提出了用遗传学习算法建立系统的模糊认知图方法,为复杂系统分析及预测提供了一种解决方案。最后,以股票市场的数据为例进行了分析和预测模拟,结果表明,该方法是有效的。     

基于分段线性内映射的混沌二值序列设计

混沌扩频序列具有良好的自相关特性,适合作为地址码用于DS-CDMA系统.文中对基于分段线性内映射的二值序列进行了设计,得到了自相关函数为符号交替、指数衰减的最优二值序列,该序列比高斯白序列在系统容量上有约15.5%的提高.     

基于卡诺图的均布式绝对位置编码

提出了一种基于卡诺图的均布式绝对位置编码，介绍了该绝对编码的生成方法及在绝对位置角度传感器中的应用。基于卡诺图的均布式绝对位置编码是一种单码道绝对位置编码，克服了传统位置编码随精度提高而码道增多、工艺上不易实现的缺点，可缩减码盘的直径，为绝对位置角度传感器的高精度、小型化开辟了一条新的途径。     

新都桂湖水系演变及特点研究

鉴于历史地图自身信息的模糊性,采用历史地图解译法对桂湖水系相关的历史地图进行解译绘制,通过解译图纸能较为清楚展示桂湖水系的演变过程,进而相对客观地总结其水系的演变特点。从城市水系与园林水源、水系周边建筑营建、水系空间形态划分3个方面,按照隋唐、宋代、明清、近代、现代的时间段对桂湖水系的演变过程进行梳理,并从新都城市水系与桂湖园林水系的关系、水系周边建筑功能及附属空间属性的变化、水系形态的艺术划分3方面归纳总结水系演变特点: 1）新都城市水系与桂湖园林水系在形态结构联系上呈现出完整、完善、破坏、重建4个阶段,桂湖园林水系与新都城市水系在水系体系构成上经历融合、维持、撤离、融入4个阶段的变化。2）水系周边建筑功能经纪念性萌芽、公共性增强、纪念性强化、纪念性精炼的变化,其建筑附属空间布局经历游赏性空间错列分布、公共性空间沿岸排布、纪念性空间中心贯穿、纪念性空间核心主导的4个阶段,使得桂湖从以游玩聚会为主的驿站园林变为以纪念为主的公共园林。3）桂湖水系的形态结构划分呈一池三岛“粗”分、五岛两堤“概”分、五岛两堤“密”分与五岛两堤“旷”分的演变特点。     

基于BP神经网络和3D加工图的Ti2041合金的热变形行为研究

通过热压缩实验研究了Ti2041合金的流动行为。利用BP神经网络建立的合金本构模型,具有较高的精度,其相关系数达到0.99613,平均相对误差为4.498%,预测值偏差在10%以内的数据点达92.98%。在实验数据的基础上,研究了应变速率敏感因子、功率耗散和失稳参数。建立了加工图,通过加工图的预测和显微组织观察,失稳区主要为局部流动（650~775℃/0.056~1s-1）和机械失稳（825~900℃/0.056~1s-1）,稳定区的变形机制主要为动态再结晶。结果表明：合适的变形参数为：变形温度760~825℃/825~900℃,应变速率0.001~0.01s-1/0.0032~0.056s-1。     

Ceramic wear maps

Ceramic wear maps have been developed to elucidate the complex interactions of the operating parameters, environments, and wear mechanisms. This paper summarizes these interactions for four ceramics, alumina, yttria-doped zirconia, silicon carbide and silicon nitride. Wear maps of these ceramics are systematically constructed using measured data under dry sliding, water, and paraffin lubricated conditions. For each material, different wear level regions acid wear transition zones are identified as a function of operating conditions and lubrication conditions. Wear mechanism studies performed within each wear region give rise to the wear mechanism maps. These maps facilitate material comparison and selection. The knowledge of wear, wear transitions, and wear mechanisms for a material pair enables realistic wear model development. One outcome of this approach is the recognition that a single wear model for a material pair cannot cover all operating conditions and environments.

As wear maps are constructed today, they are material pair specific. Within a material pair, there are microstructural dependence and surface properties influence. These parameters can change substantially for a given chemical composition of the material. How to incorporate these factors into the wear map research remains an issue. The search for a universal parameter such as the “asperity temperature” in Ashby's wear map continues in spite of mounting evidence that this may not be practical or feasible. But the hope remains that some parameters can be identified to normalize a large number of materials, operating conditions, and environments for tribological applications. Systematic wear maps are the first steps in this direction.     

Comparison of self-organizing maps classification approach with cluster and principal components analysis for large environmental data sets

Three classification techniques (loading and score projections based on principal components analysis (PCA), cluster analysis (CA) and self-organizing maps (SOM)) were applied to a large environmental data set of chemical indicators of river water quality. The study was carried out by using long-term water quality monitoring data. The advantages of SOM algorithm and its classification and visualization ability for large environmental data sets are stressed. The results obtained allowed detecting natural clusters of monitoring locations with similar water quality type and identifying important discriminant variables responsible for the clustering. SOM clustering allows simultaneous observation of both spatial and temporal changes in water quality. The chemometric approach revealed different patterns of monitoring sites conditionally named "tributary", "urban", "rural" or "background". This objective separation could lead to an optimization of river monitoring nets and to a better tracing natural and anthropogenic changes along the river stream.     

Mapping of background air pollution at a fine spatial scale across the European Union

Background

There is a need to understand much more about the geographic variation of air pollutants. This requires the ability to extrapolate from monitoring stations to unsampled locations. The aim was to assess methods to develop accurate and high resolution maps of background air pollution across the EU.

Methods

We compared the validity of ordinary kriging, universal kriging and regression mapping in developing EU-wide maps of air pollution on a 1 × 1 km resolution. Predictions were made for the year 2001 for nitrogen dioxide (NO₂), fine particles < 10 µm (PM₁₀), ozone (O₃), sulphur dioxide (SO₂) and carbon monoxide (CO) using routine monitoring data in Airbase. Predictor variables from EU-wide databases were land use, road traffic, population density, meteorology, altitude, topography and distance to sea. Models were developed for the global, rural and urban scale separately. The best method to model concentrations was selected on the basis of predefined performance measures (R², Root Mean Square Error (RMSE)).

Results

For NO₂, PM₁₀ and O₃ universal kriging performed better than regression mapping and ordinary kriging. Validation of the final universal kriging estimates with results from all validation sites gave R²-values and RMSE-values of 0.61 and 6.73 µg/m³ for NO₂; 0.45 and 5.19 µg/m³ for PM₁₀; and 0.70 and 7.69 µg/m³ for O₃. For SO₂ and CO none of the three methods was able to provide a satisfactory prediction.

Conclusion

Reasonable prediction models were developed for NO₂, PM₁₀ and O₃ on an EU-wide scale. Our study illustrates that it is possible to develop detailed maps of background air pollution using EU-wide databases.     

Fretting corrosion of tin-plated contacts

The susceptibility of tin-plated contacts to fretting corrosion is a major limitation for its use in electrical connectors. The present paper evaluates the influence of a variety of factors, such as, fretting amplitude (track length), frequency, temperature, humidity, normal load and current load on the fretting corrosion behaviour of tin-plated contacts. This paper also addresses the development of fretting corrosion maps and lubrication as a preventive strategy to increase the life-time of tin-plated contacts. The fretting corrosion tests were carried out using a fretting apparatus in which a hemispherical rider and flat contacts (tin-plated copper alloy) were mated in sphere plane geometry and subjected to fretting under gross-slip conditions. The variation in contact resistance as a function of fretting cycles and the time to reach a threshold value (100 mΩ) of contact resistance enables a better understanding of the influence of various factors on the fretting corrosion behaviour of tin-plated contacts. Based on the change in surface profile and nature of changes in the contact zone assessed by laser scanning microscope (LSM) and surface analytical techniques, the mechanism of fretting corrosion of tin-plated contacts and fretting corrosion maps are proposed. Lubrication increases the life-time of tin-plated contacts by several folds and proved to be a useful preventive strategy.     

Prediction of the fretting fatigue resistance of various surface-modification layers on 1045 steel: the role of fretting maps

In this work, fretting maps of various surface modifications were established based on the friction logs of fretting experiments. The fretting fatigue resistance of the coatings was analyzed according to the features of the fretting maps of the coatings. The results showed clearly that fretting maps of materials are effective tools to predict the fretting fatigue properties of substrates and surface-modification coatings. It was also demonstrated that the fretting fatigue resistance of a 1045 steel substrate could be improved to different extents through surface modification. The fretting fatigue resistance of solid lubricating coatings was the best and the tendency for initiation and propagation of cracks in the substrate material could also be restrained by depositing hard coatings.