基于模糊小波网络的伺服系统参数辨识研究

伺服系统大多是非线性系统,难以对其建立准确的控制模型,其位置、和速度检测信号易受干扰,而小波网络具有多分辨率特性和任意逼近能力。利用其非线性映射能力对系统的输入输出关系进行模拟,将小波网络和模糊规则结合对系统的位置和速度进行辨识,动态调整网络的权值W和模糊规则,将非线性映射的问题转化为求解系统最优解,从而产生一种新的系统辨识方法,并以永磁伺服系统为例,设计了辨识的结构模型和策略,实验表明该算法可以达到较高的系统控制要求。     

����IPSO-BPģ�͵Ĵ�Ӷ�Դ�������Ԥ���뷴��

???????????????????IPSO??????????????????????м??????????????????????????????????????????????????????????????????????????????BP?????????γ?IPSO_BP??????????????????μ????????????????????????IPSO_BP???????????????Ч??????????????????????????????     

Statistical Downscaling of FGOALS-s2 Projected Precipitation in Eastern China

A statistical regression downscaling method was used to project future changes in precipitation over eastern China based on Phase 5 of the Coupled Model Intercomparison Project （CMIPS） the Representative Concentration Pathway （RCP） scenarios simulated by the second spectral version of the Flexible Global Ocean- Atmosphere-Land System （FGOALS-s2） model. Our val- idation results show that the downscaled time series agree well with the present observed precipitation in terms of both the annual mean and the seasonal cycle. The regres- sion models built from the historical data are then used to generate future projections. The results show that the en- hanced land-sea thermal contrast strengthens both the subtropical anticyclone over the western Pacific and the east Asian summer monsoon flow under both RCPs. However, the trend of precipitation in response to warming over the 21 st century are different across eastern Chi- na under different RCPs. The area to the north of 32°N is likely to experience an increase in annual mean precipitation, while for the area between 23°N and 32°N mean precipitation is projected to decrease slightly over this century under RCP8.5. The change difference between scenarios mainly exists in the middle and late century. The land-sea thermal contrast and the associated east Asian summer monsoon flow are stronger, such that precipitation increases more, at higher latitudes under RCP8.5 compared to under RCP4.5. For the region south of 32°N, rainfall is projected to increase slightly under RCP4.5 but decrease under RCP8.5 in the late century. At the high resolution of 5 km, our statistically downscaled results for projected precipitation can be used to force hydrological models to project hydrological processes, which will be of great benefit to regional water planning and management.     

Verifying Fossil-Fuel Carbon Dioxide Emissions Forecasted by an Artificial Neural Network with the GEOS-Chem Model

In this study, the authors developed an en- semble of Elman neural networks to forecast the spatial and temporal distribution of fossil-fuel emissions （ff） in 2009. The authors built and trained 29 Elman neural net- works based on the monthly average grid emission data （1979-2008） from different geographical regions. A three-dimensional global chemical transport model, God- dard Earth Observing System （GEOS）-Chem, was applied to verify the effectiveness of the networks. The results showed that the networks captured the annual increasing trend and interannual variation of ff well. The difference between the simulations with the original and predicted ff ranged from -1 ppmv to 1 ppmv globally. Meanwhile, the authors evaluated the observed and simulated north-south gradient of the atmospheric CO2 concentrations near the surface. The two simulated gradients appeared to have a similar changing pattern to the observations, with a slightly higher background CO2 concentration, - 1 ppmv. The results indicate that the Elman neural network is a useful tool for better understanding the spatial and tem- poral distribution of the atmospheric C02 concentration and ft.     

华北地区夏季降水模拟研究:区域气候模式性能评估

利用高分辨率区域气候模式Reg CM3对华北地区1991—2002年夏季气候进行了数值模拟,对照中国台站的实测资料,对模拟的华北地区夏季降水、温度进行了较为全面的比较,以检验模式的模拟性能。对平均场的模拟结果检验认为,该区域气候模式对华北地区夏季降水的空间分布模拟存在一定的误差,河套地区及黄河以南地区降水量接近实况,沿着太行山脉及东部沿海地区降水量明显偏多。模式对温度的模拟误差较小,较好地再现了气温的空间分布特征,但山西及以北地区模拟的温度略偏低。模式能够较好地模拟出华北地区夏季降水和气温的年际变化,成功再现了该区域降水和气温的异常变化。模式能够成功模拟出该区域降水和气温日变化特征,特别是对于逐年夏季的降水日变化过程的峰值和谷值均有成功表现,对于典型年份华北地区较强降水过程中降水发生的时间、落区、强度等也有再现能力,不足的是模拟的降水量比观测偏大。对于模式误差是否与地形或模式积云对流参数化方案等有关,需要进一步探讨。     

基于遗传小波神经网络的海底声学底质识别分类

分割海底声纳探测图像,提取单元特征向量进行主成份分析,选取均值、标准差、对比度、相关系数、能量及同质性作为训练特征向量,构建小波神经网络。利用遗传算法优化小波神经网络的初始权值及小波参数,对砂、礁石、泥3种底质类型分别进行训练,并得到3种底质的测试精度都在90%以上,优于单独利用小波神经网络进行训练时的测试精度,克服了小波神经网络训练时易陷入局部极小的固有缺陷,表明基于遗传算法的小波神经网络可有效用于海底底质声纳图像的识别和分类。     

基于ROMS模式利用集合最优插值同化沿轨海表面高度异常数据的研究

The ensemble optimal interpolation （EnOI） is applied to the regional ocean modeling system （ROMS） with the ability to assimilate the along-track sea level anomaly （TSLA）. This system is tested with an eddy-resolving system of the South China Sea （SCS）. Background errors are derived from a running seasonal ensemble to account for the seasonal variability within the SCS. A fifth-order localization function with a 250 km localization radius is chosen to reduce the negative effects of sampling errors. The data assimilation system is tested from January 2004 to December 2006. The results show that the root mean square deviation （RMSD） of the sea level anomaly decreased from 10.57 to 6.70 cm, which represents a 36.6% reduction of error. The data assimilation reduces error for temperature within the upper 800 m and for salinity within the upper 200 m, although error degrades slightly at deeper depths. Surface currents are in better agreement with trajectories of surface drifters after data assimilation. The variance of sea level improves significantly in terms of both the amplitude and position of the strong and weak variance regions after assimilating TSLA. Results with AGE error （AGE） perform better than no AGE error （NoAGE） when considering the improvements of the temperature and the salinity. Furthermore, reasons for the extremely strong variability in the northern SCS in high resolution models are investigated. The results demonstrate that the strong variability of sea level in the high resolution model is caused by an extremely strong Kuroshio intrusion. Therefore, it is demonstrated that it is necessary to assimilate the TSLA in order to better simulate the SCS with high resolution models.     

基于特征区域统计的多光谱遥感影像海岛瞬时岸线提取(英文)

本研究采用IKONOS遥感图像,选取波谱特征区,通过区域像元统计并计算各波段权重系数,将影像进行波谱归一化处理,使归一化的影像岛陆与海水特征更明显。在此基础上,采用最大类间方差法确定最佳分割阈值,对归一化的影像进行二值化,从而提取海岛岸线。该方法采用特征曲线法进行水陆分离,得到的二值图像保持了原图的有效边缘,采用二值形态学提取的海岸线连续可靠、信噪比高。结果表明,该方法简单、快速,能有效提取海岸线,具有实用价值。     

公交车辆全线运行状态的监督站牌及查询系统

针对出行者对公交车辆运行信息的需求,基于GPS技术设计了一个动态显示公交车辆位置信息的监督站牌系统,并提供公交位置信息的网络查询服务,方便出行者了解公交车辆的实时运营信息,以及对公交车辆的实时监督.系统以LabVIEW为软件开发平台对数据进行分析与处理,利用ASP.NET进行Web网页开发并与数据库交互,实现公交系统的智能运营和智能服务.通过实际验证,该方案具有可行性、实用性.     

山东暴雨天气学预报指标的统计特征分析

采用山东省2000—2011年逐日、逐时降水资料和NCEP最终分析资料,研究了山东省暴雨天气学指标物理量的时空分布,获得了不同季节、区域和范围的暴雨预报指标特征。研究表明:山东暴雨有明显的夜间增强趋势。业务中常用的暴雨指标物理量均有不同程度的季节性变化特征,一方面表现在指标物理量的阈值有明显的季节性差异,例如暴雨的850 hPa比湿指标在4、5月仅为10 g·kg~(-1),而7月则可达14 g·kg~(-1);另一方面不同季节的水汽、动力和热力不稳定等因子对暴雨贡献也不尽相同,通常盛夏季节暴雨的水汽因子较高,而动力因子偏低,而且对流不稳定性较强,但斜压性减弱,其他季节的暴雨则相反。山东暴雨指标物理量的区域性差异没有季节性差异明显,同时各因子的区域差异也并不一致,具体来说鲁南暴雨需要更强的水汽,同时热力不稳定性因子也较高,K指数比其他区域约高0.5℃,而半岛地区暴雨动力因子更强。同时,大范围暴雨和区域暴雨需要更好的水汽条件、更强的动力条件,但对流不稳定条件较低,而局地暴雨则与此相反。