基于ANFIS的黄河灵口流域水文预报模型

运用ANFIS在环境水文要素与出口断面流量之间建立了洪水预报模型,模型输入为归一化的平均降雨强度、雨强距离指数、植被指数,输出为流域出口断面的洪峰流量,采用混合学习算法进行参数率定。在黄河灵口流域的应用结果表明:模型验证误差不超过15%,符合较高精度等级洪水预报的要求。     

云模型在中长期降水预测中的应用

中长期降水预测对灌区水资源管理、种植结构调整及水生生态系统的健康发展具有重要意义。将定性概念与定量概念之间的不确定性转换模型引入到中长期降水预测中,以更好地反映降水时程分配中的随机不确定性和模糊不确定性。基于云模型的降水预测法通过挖掘已有观测数据的内在联系,形成预测规则,并据此进行中长期预测。最后,运用云模型对河南省渠村引黄灌区2004—2013年的降水量进行了预测。结果表明:云模型预测的年降水量平均值与实测值整体拟合较好,预测精度优于灰色预测等方法。     

人工神经网络在径流长期预报中的应用

介绍了人工神经网络（Artificial Neural Network-ANN）模型,并阐述了BP模型算法。通过Matlab6．5中的Neural Network Toolbox编写程序,根据塔里木河源流叶尔羌河卡群控制水文站历年的气象资料和水文资料,对径流量进行了预报,并对模型进行了验证和分析,结果表明：1968～1997年间预报合格的有25年,合格率为83％;1998～2002年的合格率为100％,从而说明神经网络在水文预报方面具有良好的适用性。     

GSM短消息业务在水情自动测报系统中的应用

介绍了目前水情自动测报系统通用的几种通信组网方式及其特点,重点阐述利用GSM短消息业务来实现水情自动测报系统遥测站与中心站之间的数据传输方案,并详细分析了采用这种方式的优点,以及利用GSM短消息业务在澜沧江流域水情自动测报系统的实际应用情况。     

Genetic Algorithms for Multi-objective Optimization: Application to a Multi-reservoir System in the Chi River Basin, Thailand

The multi-objective genetic algorithm is applied to determine the optimal operation of a multi-reservoir system in the Chi River Basin, Thailand. Two competing objective functions are considered; dam release and dam storage. The predicted values for the release and storage needed are mostly lower than in current established management practice.     

新安江模型在瓦塘江流域短期洪水预报中应用

为满足泵站科学调度运行的要求和对库区瓦塘江泵站防汛淹没损失的考核,贵港航运枢纽分公司以集团公司水调自动化系统数据库为基础数据来源,以新安江模型建立了瓦塘江流域短期洪水预报系统。通过对瓦塘江流域洪水预报进行实例检验,及对模拟结果的评价指标进行分析,研究结果表明该系统能取到较高精度,为瓦塘江泵站的48 h实时调度提供科学依据。     

中国洪水预报系统在东江流域的应用

中国洪水预报系统是基于预报模型计算机化的技术,2007年在广东省水情系统推产应用,惠州分局于2006年开始将该项技术应用到东江流域的洪水预报中,并取得了良好的应用效果。     

Optimization of Hydropower Reservoir Using Evolutionary Algorithms Coupled with Chaos

Over the past decade, several conventional optimization techniques had been developed for the optimization of complex water resources system. To overcome some of the drawbacks of conventional techniques, soft computing techniques were developed based on the principles of natural evolution. The major difference between the conventional optimization techniques and soft computing is that in the former case, the optimal solution is derived where as in the soft computing techniques, it is searched from a randomly generated population of possible solutions. The results of the evolutionary algorithm mainly depend on the randomly generated initial population that is arrived based on the probabilistic theory. Recent research findings proved that most of the water resources variables exhibit chaotic behavior, which is a projection depends upon the initial condition. In the present study, the chaos algorithm is coupled with evolutionary optimization algorithms such as genetic algorithm (GA) and differential evolution (DE) algorithm for generating the initial population and applied for maximizing the hydropower production from a reservoir. The results are then compared with conventional genetic algorithm and differential evolution algorithm. The results show that the chaotic differential evolution (CDE) algorithm performs better than other techniques in terms of total annual power production. This study also shows that the chaos algorithm has enriched the search of general optimization algorithm and thus may be used for optimizing complex non-linear water resources systems.     

Long-Term Simulation of PCB Export from the Fox River to Green Bay

A mass balance approach was used to model long-term PCB transport in the Fox River (Wisconsin) from Lake Winnebago to Green Bay. The objectives of this research were to (1) extend the modeling approach for the Fox River to permit realistic long-term simulations of contaminant transport and fate, (2) forecast long-term PCB export from the Fox River to Green Bay, and (3) develop a rational approach for evaluating sediment remediation alternatives. Field data collected as part of the Green Bay Mass Balance Study during 1988-90 and additional data collected by the Wisconsin Department of Natural Resources and the U.S. Geological Survey during 1992-93 were used to develop the model. A 10-year hindcast was conducted to confirm long-term model predictions. A series of 25-year forecasts were then conducted to explore the potential effects of hydrograph structure, extremely high flows, and sediment remediation on long-term PCB export from the Fox River to Green Bay. PCB export from the Fox River is forecast to decrease, and most (75%) of the PCB reservoir in Fox River sediment is expected to remain in place. However, extremely high flows in future years are forecast to cause significant PCB resuspension and export. Model forecasts suggest that long-term PCB export is only mildly sensitive to changes in hydrograph structure. Sediment remediation is forecast to reduce but not eliminate PCB export.     

Field Studies of the Kinematic Structure of River Flows with Different Water Volumes

Studies of the kinematics and dynamics of averaged flows in rivers with substantially differing water volumes are presented.__________Translated from Gidrotekhnicheskoe Stroitel’stvo, No. 4, April 2005, pp. 26 – 28.     

MATLAB遗传算法工具箱(GAOT)在水资源优化计算中的应用

阐述了遗传算法的基本原理,对MATLAB遗传算法工具箱（GAOT）的参数使用进行了详细介绍,探讨了MATLAB遗传算法工具箱（GAOT）在水资源非线性规划和多目标规划时的应用,并用简单实例证明了这种应用具有良好的通用性、可行性和简便性,可以得到较满意的优化计算结果。     

用中国洪水预报系统率定丰良河洪水参数

利用“中国洪水预报系统”平台,使用三水源新安江模型,对丰良河的棠荆水文站小流域洪水进行参数率定,并对率定结果进行分析,采用合理的方法,对参数进行人工调试,确定适合该小流域洪水特征的参数,增加模型洪水计算的拟合度,得到较好的洪水预报方案。     

灰色系统在瑞丽江长期水文预报中的应用

根据瑞丽江防汛抗旱、水资源管理等工作的实际需要,选取流域内有代表性的戛中、等戛水文站为实例,采用灰序列关联分析技术对年径流量和年最大洪峰流量两要素进行预测,并与自回归模型AR(P)的预测结果进行对比,证明灰序列关联分析法预测精度优于自回归模型AR(p)。     

不同预报模型在东江中小流域的适应性探讨

以东江一级支流秋香江为为例,探讨了降雨径流相关、单位线、蓄满产流及滞后演算等方法在东江中小流域洪水预报中的适应性,并根据模型检验结果对不同模型方法进行了比较分析。     

棱锥体结构对弯道水流的改善与布置参数优化研究

河道的弯道段设置相应的护岸工程,可规避复杂横向水流对河岸稳定性产生的影响.文章通过模型试验,探讨了在河流弯道段设置棱锥体对改善流态的作用.结果显示,在弯道设置三棱锥体可提高水面均匀度和水面横比降,显著改善弯道流态,具有一定的工程应用价值,增加椎体的设置数量对改善水面流态更为有利.     

自适应BP神经网络对黄河下游洪水位的预报

利用黄河下游多水文站的多年水位资料,用自适应BP神经网络对艾山水文站的水位进行预测,同时与逐步回归分析以及普通BP神经网络得到的结果对比,结果表明：①自适应BP神经网络的预报精度高于普通BP神经网络、逐步回归法,尤其对最高洪水水位的预报精度有较大的提高;②普通BP神经网络存在易陷入死循环、收敛速度慢、对神经元个数依赖大等缺点,可以利用学习率自适应调整和动量法改进BP神经网络;③建议在补充、完善资料的基础上,将神经网络与时间序列相结合,加强黄河下游洪水水位预报的研究和实验,进一步提高预报精度。     

遗传算法在暴雨强度公式优化问题中的应用及Matlab实现

介绍了遗传算法在实现暴雨强度公式优化问题中的应用,给出了在Matlab语言环境下实现编码、译码、选择、重组和变异各算子的编程方法,通过比较来说明遗传算法在寻求最优解的优越性。