基于贝叶斯理论和遗传算法的管网漏损探测定位

针对舰艇消防供水管网结构复杂、管网中用户的用水量与漏损损耗量难以区分等特点,通过将管网中的漏损点等效为具有用水量的虚拟节点,提出了一种基于贝叶斯理论与遗传算法相结合的管网漏损探测定位模型。通过对所有单个虚拟节点模拟管网漏损量,将其剩余压力平方和作为目标函数,通过遗传算法寻找能使目标函数取得最小值确定管网的漏损情况。利用遗传算法搜索在不同漏损管段个数下能使得贝叶斯概率取得最小值的最优管段组合,从而实现漏损定位。仿真结果表明,通过结合贝叶斯理论与遗传算法进行漏损探测与定位具有探测速度快、定位结果准确的优点,可用于解决多点漏损管网的漏损探测和定位问题。     

用水压图调节流量法对城市供热网络的模拟

结合邯郸市城市集中供热管网的具体实例,以管网主干线各节点压力的实测值为基础,找到一种以"水压图调节流量"法模拟现状管网的实际运行状态的新方法,获得各热力站的实际流量值,为准确模拟现状管网的水力特征和网络的规划发展奠定了基础。     

给水管网水力模型的建立及应用

某市供水管网水力模型以管网地理信息系统、客户营销系统、数据采集与监控系统为基础,整合三大系统的数据,采用计算机模拟的方式来表现供水管网各管段及泵站的流量、压力、流速、流向、水力坡度变化,分析和评价管网布设的合理程度及运行规律,优化管网设计,完善供水调度方案．该模型的建立及应用能够为决策者提供参考依据,使供水企业逐渐告别粗放型的管网运行管理模式,令供水管网处于良性运行状态．     

ZStack传感器网络定位系统设计

在无线传感器网络定位系统中,由于元器件品控和外界环境等因素的差异,以往测出的衰减模型参数的经验值并不能适应当下的定位环境,以至定位精度很低,实验过程不具重复性。根据待定位节点临近的参考节点多次互发报文,经过最小二乘法拟合出衰减模型参数。算法对所有参考节点根据RSSI值进行排序,选取RSSI值最小的3个节点用三边定位算法计算待定位节点坐标。最后,设计了一个基于ZStack协议栈的定位原型系统。算法经过进一步简化,大幅度减小了由于衰减模型参数不准确对定位精度的影响,为今后深入研究室内定位打下基础。     

基于遗传算法的供水管网需求乘数因子校核

水力模型已广泛应用于给水管网设计、分析与运行中。在所有水力模型中,需水量是导致模型输出最不确定的参数之一。因用水情况不确定,使得管网中的节点需水量变得异常复杂。在大多数实际管网中,用于校核节点需水量的监测设备数量有限,且小于未知量个数,使得节点需水量校核作为欠定问题,令节点需水量校准产生较大误差,并且传统遗传算法校核节点需水量的方法是假定所有节点的需求乘数因子一致,这也导致校核后的模型无法接近真实运行情况,因此提出在欠定条件下用遗传算法解决需求乘数因子的校核问题。通过对一个实际案例多次运行并取平均值作为结果进行验证,结果表明,遗传算法的校核结果不仅能够与被测位置的实际值相拟合,而且可以得到非测量位置的管道流量和节点水头,其中校核后的节点水头和管道流量误差较小,平均误差分别为1.78%、4.05%。该方法相比于传统校核方法具有更高精度,且更能反映出管网真实运行情况,同时还避免了传统校核方法中因遗传算法产生局部最优解而导致误差偏大的问题,对于大型管网模型校核也具有一定参考价值。     

移动热源问题的移动加权最小二乘无网格法

针对具有奇异性的高斯移动热源问题,基于无网格法和移动网格法的思想提出了移动加权最小二乘无网格法,节点能够在求解域中自适应地向解梯度较大的区域移动,从而更好地表征热源的温度分布.数值算例验证了算法的有效性.     

基于信标节点间RSSI的改进三维定位算法的研究

节点定位是无线传感器网络的重要支撑技术之一,目前主要有两种定位算法,基于距离的定位算法和非基于距离的定位算法.考虑到两种算法在三维空间的优缺点,提出了一种基于RSSI测距的修正算法,并优选信标节点,最后通过最小二乘法进行定位.仿真结果表明：本算法比传统的RSSI算法精度更高.     

基于混合优化的RBF神经网络集成的降水预报模型

针对传统的单个RBF神经网络集成中个体的隐节点个数和初始参数难以客观确定的不足,为了提高泛化能力,提出一种以高斯核函数的混合优化的RBF神经网络的方法,首先引入正交最小二乘法动态客观的获取数据中心的个数、数据中心及权值;然后通过计算隐层中心点间最小距离作为扩展常数;最后使用剃度法调节权值、中心及扩展常数使网络参数和结构达到最优.该方法结合了正交最小二乘法和剃度算法的优点,通过从结构和算法两方面的调整提升了单个的传统的RBF网络的性能.并将上述优化混合的RBF神经网络与主成分分析方法相结合建立模型.本文以广西5月逐日降水事先初选的众多预报因子进行主成分分析算法提取有效的几个综合因子,然后使用混合算法优化的径向基网络建立降水预测模型.结果表明,该模型具有较好的收敛效果和泛化能力,在预报性能上明显优于同期的T213降水预报,具有一定的普遍适用性.     

基于RSSI测距模型优化算法研究

RSSI定位方法已成为近年来研究热点,基于测距的RSSI定位算法本身具有一定缺陷,无线信号在传播过程中由于受到环境中各种高斯白噪声的干扰,致使获取的RSSI值会在某一中心值上下波动,极大影响了定位的实效性、准确性。为提高室内环境的定位精度,提出一种基于RSSI的高斯—卡尔曼滤波优化。先用极大似然估计得出RSSI测距模型的修正参数,然后使用最小二乘法（LSM）初步估计所求定点的坐标,最后利用高斯 卡尔曼滤波对计算出来的定位节点坐标和参数进行优化,利用Matlab实验仿真结果表明,算法具有定位误差小、精度高的明显特点。     

解微分方程的改进算法在微机距离保护中的应用研究

对解微分方程算法做了改进,通过数字仿真计算验证了改进后算法的优良估计性能,并且把它与递推最小二乘法、全周傅立叶算法作了比较,并根据各算法的估计性能特点,提出了一种具有反时限特性的微机距离保护算法的实现方案。     

Seismic reliability and rehabilitation decision of water distribution system

in order to evaluate the seismic reliability of water distribution system and make rehabilitation decisions correspondingly, it is necessary to assess pipelines damage states and conduct functional analysis based on pipe leak- age model. When an earthquake occurred, the water distribution system kept serving with leakage. By adding a virtual node at the centre of the pipeline with leakage, an efficient approach to pressure-driven analysis was developed for simulating a variety of low relative scenarios, and a hydraulic leakage model was also built to perform hydraulic analy- sis of the water supply network with seismic damage. Then the mean-first-order-second-moment method was used to analyse the seismic serviceability of the water distribution system. According to the assessment analysis, pipes that were destroyed or in heavy leakage were isolated and repaired emergently, which improved the water supply capability of the network and would constitute the basis for enhancing seismic reliability of the system. The proposed approach to seismic reliability and rehabilitation decision analysis on water distribution system is demonstrated effective through a case study.     

Leak Detection in Water Distribution Systems Using Bayesian Theory and Fisher’s Law

A leak detection method based on Bayesian theory and Fisher’s law was developed for water distribution systems. A hydraulic model was associated with the parameters of leaks (location, extent). The randomness of parameter values was quantified by probability density function and updated by Bayesian theory. Values of the parameters were estimated based on Fisher’s law. The amount of leaks was estimated by back propagation neural network. Based on flow characteristics in water distribution systems, the location of leaks can be estimated. The effectiveness of the proposed method was illustrated by simulated leak data of node pressure head and flow rate of pipelines in a test pipe network, and the leaks were spotted accurately and renovated on time.     

Optimal operation of water supply systems with tanks based on genetic algorithm

INTRODUCTION With increased urbanization and consumer de-mand, most water distribution systems and efficient scheduling of pump operation have become increas-ingly complex. Several optimization methods are used to find optimal pump schedules. Because of the complex water distribution systems, simple calcula-tions are no longer possible. The main methods used at present are linear programming (Crawley and Dandy, 1993), dynamic programming (Yeh et al., 1992; Nitivattananon et al., 1996), …     

基于蚁群粒子群混合算法的多目标优化在供水管网优化设计中的应用

在城市供水系统中,管网的铺设费用占很大比重。如何最大限度降低建设成本而又保证供水的可靠性,是供水管网设计的重点和难点。基于供水管网的固有特性,结合蚁群、粒子群算法的优点,将蚁群粒子群混合算法应用到供水管网设计的多目标优化中。将蚁群中的信息素、启发因子、信息素挥发度参数映射到粒子群算法中粒子的位置坐标,通过粒子迭代寻找最优位置,并将蚁群算法通过特定信息素更新方式并限制迭代次数来进行优化,再将粒子最优位置反馈到优化后的蚁群算法中,寻找最优解。通过此算法,优化了供水管网中管径的选择,在保证供水管网可靠性的前提下,尽量缩减建设费用,为决策者提供更加经济实用的决策参考。     

Calibration of pipe roughness coefficient based on manning formula and genetic algorithm

This paper presents a method to calibrate pipe roughness coefficient (i.e., Manning n-factor) with genetic algorithm (GA) under multiple loading conditions. Due to the old pipe age as well as deleting valves and blends in the skeleton of distribution network, most of the pipes in hydraulic model of practical water distribution system (WDS) are rough. The commonly used Hazen-Williams C-factor is therefore replaced by Manning n-factor in calibrating WDS hydraulic model. Adjustment to GA is designed, and the program efficiency is improved. A case study shows that the adjustment can save 60% of the total runtime. About 90% of the relative differences between simulated and observed pressures at monitoring locations are lower than 3%, which suggests that the proposed adjustment to the calibration is efficient and effective.     

Two-dimensional pipe leakage through a line crack in water distribution systems

In water distribution systems, water leakage from cracked water pipes is a major concern for water providers. Generally, the relationship between the leakage rate and the water pressure can be modeled by a power function developed from the orifice equation. This paper presents an approximate solution for the computation of the steady-state leakage rate through a longitudinal line crack of a water distribution pipe considering the surrounding soil properties. The derived solution agrees well with results of numerical simulations. Compared with the traditional models, the new solution allows assessment of all the parameters that related with leakage including the pressure head inside the pipe, hydraulic conductivity, crack size and its position, and pipe size and its depth.     

Optimization of the Open Degree of Key Valves Based on Relative Entropy and Pipeline Leakage

Based on information entropy theory, the definition of relative entropy, and the relative entropy minimum principle, this study establishes a multi-objective optimization model for a key valve opening of an urban water distribution network(WDN). Each node pressure is taken as the main research object to reduce pipeline leakage. Moreover, genetic algorithm is applied in the proposed model to solve the key valve opening of the actual WDN in a city in southern China. Using the proposed model, the relevant decision variables of a WDN can be optimized to provide a new manner of network dispatching.     

基于EPANET的电厂工业水管网优化设计

以某电厂工业水管网为例,运用EPANET软件进行水力计算,通过对管段内流速的控制,精确控制管径以及节点压力,达到管网优化设计的效果,软件操作简便,计算快速准确,满足工程设计的要求。     

神经网络在供热管网泄漏故障诊断中的应用(英文)

为了研究供热管网泄漏检测策略,利用图论理论构建了一个基于空间管网的泄漏工况水力计算数学模型,得出节点泄漏和管段泄漏工况下管网各点的压力变化情况.然后,采用人工神经网络方法建立了一个基于BP神经网络的供热管网泄漏诊断系统.该诊断系统可根据管网中压力监测点的压力变化定位泄漏管段,实现对泄漏点位置的初步估计.最后,通过实例验证了该方法的有效性.实验结果表明,这种诊断系统对泄漏管段的预测准确率达到100%.