基于微粒群算法的工程项目质量、费用和工期综合优化

进度、费用和质量称为工程项目的三大控制目标,三者之间相互依存、相互影响。工程项目控制的理想状态是同时实现合理的工期、较低的费用和较高的质量。微粒群算法(PSO)是新近出现的一种仿生算法,具有简单容易实现,而且随机搜索的优点,使得搜索不易陷于局部最优。将该算法引入工程项目优化领域,研究工程项目的质量、费用和工期的综合优化问题。系统介绍微粒群算法原理、流程以及算法的改进发展,研究工程项目质量、费用和工期的优化,并建立质量、费用和工期的多目标综合优化模型,介绍应用微粒群算法编码解决工程项目多目标优化的方法步骤。最后,通过一个应用实例,计算表明微粒群算法可以准确快速地解决工程项目多目标优化问题。     

基于机器学习理论的SWMM参数自动率定方法

SWMM作为一种模拟降雨情况的软件,由于其模型参数在经验范围内选取的不确定性,随着模型不断地向前运行演绎,误差会持续累积,最终影响模型的模拟结果,而传统的参数率定方法则具有效率低、准确度差等缺点。为此,利用MATLAB软件调用SWMM的水力演算程序来完成两者的数据交互与集成,结合多元逐步回归法筛选出敏感性高的参数作为率定对象,进而通过数值实验的方式以敏感性分析结果为依据使用Bayes-MH机器学习算法实现SWMM参数的自动率定。对于不同的实测降雨场景,自动率定的结果均能够顺利输出,参数匹配度达95%以上,表明了该方法具备优秀的稳定性、自适应性与全范围寻参能力。     

基于SWMM模型参数率定的研究

通过实测青岛市的降雨,以建模完成的SWMM模型为背景,进行了参数率定。采用初步率定完成的SWMM模型,通过扰动分析法对水文水质进行了局部灵敏度分析。结果表明,对于SWMM模型模拟的青岛市降雨,水文上不透水区曼宁系数对峰值流量模型的灵敏度最大,其次为透水区洼地蓄水深度;水质方面以COD的累积为判断标准,对COD峰值浓度最敏感的是道路最大累积量,其次是道路速率常数。     

基于代理模型辅助PSO算法的排水管网优化设计

近年来城市暴雨洪涝灾害日益严重,设计良好的排水管网则是缓解城市洪涝最为经济有效的方式之一。但目前排水管网一般采用经验方法进行设计,不仅设计成本较高,而且管网排水能力有限。基于此,利用程序将SWMM模型嵌入粒子群算法寻优过程,以管道溢流量最小为目标,并以经济成本和水力特性为约束条件建立优化模型;同时,为了克服粒子群算法最优解波动较大和计算效率较低问题,通过耦合Kriging模型,提出了一种基于在线代理模型辅助粒子群算法的排水管网优化设计方法。以西安市某排水分区为例进行验证,并与常规的设计方法进行对比,结果表明,所提出的方法可在满足约束条件下实现洪涝缓解效果的最大化,相比于规划设计方法,管道溢流量降低了33.35%。此外,与标准粒子群算法优化结果相比,平均计算时间减少了27.56%,且优化效果更为显著。     

基于微粒群算法和BP网络的结构损伤识别

提出了基于BP网络的结构损伤识别方法,同时引入了微粒群算法对BP网络权值和阀值进行优化,建立了完整模型和损伤模型,进行了仿真,经检测样本证明,微粒群算法优化后的BP网络能很好的识别出结构损伤的位置和程度,是一种快速、有效的结构损伤识别方法。     

基坑支护设计优化研究

基坑支护设计优化一项重要而又复杂的问题,通过将支持向量机与微粒群算法结合,提出了基坑支护设计优化的新方法,并详细叙述了其实施过程;该方法用支持向量机表示支护设计参数与基坑安全系数之间的复杂非线性映射关系,提高了优化过程中基坑稳定性评价的效率,用微粒群算法作为优化工具,优化过程实施比较简单,并且具有很好的全局优化能力,最后,通过一个工程实例说明了该方法的有效性.     

大型基础设施周转材料施工方案多目标优化研究

基于离散事件仿真理论和多目标优化理论,结合实际工程案例,建立了离散仿真模型和多目标优化模型,利用智能优化算法对可行的周转材料施工方案进行了“工期-成本”优化。将周转材料的施工过程进行了逻辑抽象,对其施工过程分解并离散化,从而建立离散仿真模型,实现施工方案的参数化,并自动生成所有可行的周转方案,以选用粒子群算法进行多目标优化。在案例研究中,分析了863341种施工方案,利用粒子群算法对各种方案进行工期-成本优化,将其结果和传统方案进行比对,证明了优化方案的优越性。将离散事件仿真理论和多目标优化理论引入到大型基础设施周转材料施工方案的优化中,为其管理决策提供了新的方法依据。     

基于微粒群算法的污水管网优化设计

针对遗传算法存在的问题，提出一种利用微粒群算法（PSO）优化污水管网的模型，并阐述了应用微粒群算法进行污水管网优化设计的原理、特点。在南京市某地区的污水系统设计中采用了该算法，取得了良好的社会效益和经济效益。     

基于改进粒子群算法的海洋钻机系统布局优化

为提高海洋钻机的工作效率和平台的空间利用率,应用改进的粒子群算法对海洋钻机系统进行布局优化研究。针对多目标、多约束的钻机系统布局优化问题,建立钻机系统布局优化数学模型,应用多目标粒子群算法直接求解,得出相应的最优解集。利用线性加权法将多目标转变为单目标进行求解分析,针对单目标粒子群算法的缺点,基于约束条件、惯性权重以及遗传算法的选择和杂交对粒子群算法进行改进,完成不同改进算法的测试实验。结果表明,在应用粒子群算法求解布局问题时将约束条件作为目标函数、单独引入遗传算法的杂交思想求解速度和精度更好。提出的基于杂交的动态惯性权重粒子群算法的布局优化问题求解性能更优,得到的优化方案符合海洋钻井作业要求且占用甲板面积较小。     

基于微粒群算法的工程项目资源均衡优化

将微粒群算法运用到工程项目管理的资源均衡优化问题,定义了以活动的实际开始时间作为微粒坐标的微粒群;建立了资源方差与活动实际开始时间直接联系的评价函数;通过微粒群在飞行中位置的进化过程来搜索对应于最优方案的活动实际开始时间。最后通过算例的计算分析,用微粒群算法得到的资源强度比初始方案降低了75.2%,比遗传算法的结果降低了26.97%,验证了该方法在工程项目管理的资源均衡优化中的可行性及有效性,同时还获得了若干个次优方案,对于工程项目管理中的资源均衡优化具有实际应用价值。     

A high resolution application of a stormwater management model (SWMM) using genetic parameter optimization

Low Impact Development (LID) tools and green infrastructure approaches have been developed and applied to mitigate the urbanization impacts on increasing runoff and pollutant washoff. The present work is the first part of a larger effort to simulate LID scenarios for a large scale urban catchment through up-scaling of high-resolution study catchments using the Stormwater Management Model (SWMM). In this study we present the setup, calibration, validation, and the results of a parameter sensitivity analysis of a high-resolution SWMM model for a highly urbanized small catchment located in Southern Finland. The homogenous subcatchments and associated narrow parameter boundaries, which are allowed by the high spatial resolution, result in insensitivity of SWMM to the fraction of impervious cover. The model optimization, using only the two identified key parameters “depression storage” and “Manning's roughness n for conduit flow”, yielded good performance statistics for both calibration and validation of the model.     

The nexus of inhabitants and impervious surfaces at city scale — wastewater and stormwater travel time distributions and an approach to calibrate diurnal variations

ABSTRACT

We present an approach to calibrate dry weather flow patterns of people in eight subnetworks of Dresden, Germany. The monitored data was pre-processed, and SWMM model runs were performed. Congruence of modelled results and observed data was evaluated with the Nash-Sutcliffe Efficiency (NSE). New diurnal variation patterns of dry weather flow were quantified based on the presented calibration approach. Most of the modelled hydrographs exceeded an NSE of 0.9 just after the second SWMM model run, which is a sign of model adequacy. Travel time distributions (TTDs) of upstream wastewater from connected people and stormwater from impervious surfaces of the monitored locations were determined, and a dynamic index ?_iA-PE(k) was proposed, determined and its adequacy was assessed. In general, TTDs confirmed a lower population density and a less meshed urban drainage network in the outer parts of Dresden. The functional information within ?_iA-PE(k) considers development characteristics among the subnetworks and within a subnetwork of interest. The presented index is useful to evaluate prospective strategies of developments and the implementation of green and blue infrastructures in residential areas.     

基于改进差分进化算法的设计反应谱高稳定性标定方法研究

设计反应谱是抗震设计的重要依据,由设计谱的特征参数表征。利用差分进化算法标定设计反应谱,可给出拐点周期、特征周期、平台值和衰减指数等特征参数。但标准的差分进化算法易造成优化结果的早熟或停滞,在设计反应谱的标定中导致标定结果不稳定。为实现设计谱标定结果的最优化,该文从PEER数据库中选取60条不同类型的地震加速度反应谱,比较多种改进的差分进化算法的稳定性和适用性,以期为设计反应谱的标定提供优质的方法。通过对比分析多种方法给出的特征参数和评价指标,论证了方法的精确性和稳定性。分析结果表明,GLDE算法在标定设计反应谱的工程问题中能有效地避免标定结果不稳定的现象,获得比其他方法更精确的特征参数,因此推荐GLDE算法标定设计反应谱和研究设计谱的特征参数。     

Leveraging the analysis of parametric uncertainty for building energy model calibration

Calibrated energy models are used for measurement and verification of building retrofit projects, predictions of savings from energy conservation measures, and commissioning building systems (both prior to occupancy and during real-time model based performance monitoring, controls and diagnostics). This paper presents a systematic and automated way to calibrate a building energy model. Efficient parameter sampling is used to analyze more than two thousand model parameters and identify which of these are critical (most important) for model tuning. The parameters that most affect the building’s energy end-use are selected and automatically refined to calibrate the model by applying an analytic meta-model based optimization. Real-time data from an office building, including weather and energy meter data in 2010, was used for the model calibration, while 2011 data was used for the model verification. The modeling process, calibration and verification results, as well as implementation issues encountered throughout the model calibration process from a user’s perspective are discussed. The total facility and plug electricity consumption predictions from the calibrated model match the actual measured monthly data within ±5%. The calibrated model gives 2.80% of Coefficient of Variation of Root Mean Squared Error (CV (RMSE)) and ?2.31% of Normalized Mean Bias Error (NMBE) for the whole building monthly electricity use, which is acceptable based on the ASHRAE Guideline 14–2002. In this work we use EnergyPlus as a modeling tool, while the method can be used with other modeling tools equally as well.     

城市雨洪模型参数不确定性分析及应用

针对分布式城市雨洪模型的研究现状,分析讨论了城市雨洪模型及其模拟结果的不确定性问题,并以深圳市某独立排水片区为例,采用GLUE方法分析SWMM模型参数的不确定性。首先构建排水区的SWMM模型,针对敏感性参数随机生成多个参数方案,通过MATLAB编程调用SWMM动态链接库多次进行参数率定,以Nash-Sutcliffe效率系数(NS)大于0.8为阈值进行最佳参数方案的筛选,得到置信度为90%的排水区径流量区间。研究结果表明,GLUE方法能够分析出模型敏感性参数的不确定性,此种模型不确定性研究方法可为实际工程提供更加科学的预测。     

基于 PSO-PP 的边坡稳定性评价

边坡的稳定性评价是一个复杂的不确定系统问题。结合投影寻踪算法、粒子群优化算法和逻辑斯谛曲线函数,建立了边坡稳定性评价的粒子群优化投影寻踪模型 (PSO-PP) 。该模型一方面利用粒子群算法 (PSO) 优化投影指标函数及逻辑斯谛曲线函数参数,确保了模型参数的准确性;另一方面利用逻辑斯谛曲线函数建立投影值与经验等级之间的非线性关系。模型的测试结果显示了良好的精度。将该模型应用到雅砻江锦屏一级水电站左岸边坡的稳定性分析中,实例分析结果与实际状态吻合较好,表明该模型在边坡稳定性评价中的可行性和有效性。     

排水管道泥沙淤积深度估算方法研究

运用C#编程语言实现了SWMM模型参数的自动提取,通过创建BP-人工神经网络实现了节点水深值与模型参数值之间的非线性拟合,基于模型参数率定的思路提出了一种排水管道泥沙淤积深度的估算方法,并且以G市某雨水排水系统为例,采用4场降雨数据对模型进行了校核与验证。结果表明,通过两场降雨数据的验证,对于管径为1.2~1.8 m的管道,淤积深度预测值与实测值之间的绝对误差均在4 cm以内;模拟结果和实测数据的水深峰现时间偏差均低于实测数据历时的5%,峰值的数值偏差均在3%以内;场次3和场次4两场降雨4个监测点的水深预测值与实测值的平均相对误差分别为3.35%、2.98%,2.75%、2.51%,7.39%、6.77%,5.53%、8.15%,说明该方法能够对排水管道淤积情况进行有效预测。     

镇江市主城区排水管网计算机建模方法

为了预防道路积水等城市型水灾害，基于暴雨雨水管理模型（SWMM）平台建立了镇江市主城区排水管网计算机模拟模型。结合建模实践，对排水管网计算机实用建模方法进行了探讨，可分为汇水子区域划分、参数获取、模拟情境设计、灵敏度分析及模型预校准等步骤，为后续的模型微观校准提供了有利条件。该方法对现阶段建模数据不完备地区的排水管网建模具有借鉴意义。     

Calibration of urban stormwater drainage models using hydrograph modelling

Use of mathematical models requires the estimation of model parameters, which is usually known as the calibration of the model. In general, parameter optimization is preferred in model calibration to the trial-and-error visual comparison of observed and modelled output responses, due to subjectivity and the time-consuming nature of the latter approach. An optimization procedure, called two-stage inner/outer optimization, is described in this paper, which can be used to estimate the model parameters of any urban stormwater drainage catchment modelled with any urban drainage computer modelling software. However, the ILSAX computer software was used in this study. The method is designed to provide the ‘best’ set of model parameters that consider several storm events simultaneously. Impervious area parameters are obtained from frequent ‘small’ storm events, while the pervious area parameters are obtained from less-frequent ‘large’ events. The Giralang catchment in Canberra (Australia) was used to demonstrate the method. Several ‘small’ and ‘large’ storm events of the catchment were considered in parameter optimization. Few other storm events, which were not used in model calibration, were used to validate the model parameters obtained from calibration. Results from both calibration and validation showed that the ‘best’ set of model parameters obtained for the catchment was able to produce hydrographs similar to the observed hydrographs. Pervious and impervious area parameters obtained from calibration agreed well with the information gathered from other sources such as aerial photographs and published literature.     

Calibration of the descent local search algorithm parameters using orthogonal arrays

Solving optimization problems using heuristic algorithms requires the selection of its parameters. Traditionally, these parameters are selected by a trial and error process that cannot guarantee the quality of the results obtained because not all the potential combinations of parameters are checked. To fill this gap, this paper proposes the application of Taguchi's orthogonal arrays to calibrate the parameters of a heuristic optimization algorithm (the descent local search algorithm). This process is based on the study of the combinations of discrete values of the heuristic tool parameters and it enables optimization of the heuristic tool performance with a reduced computational effort. To check its efficiency, this methodology is applied to a technical challenge never studied before: the optimization of the tensioning process of cable‐stayed bridges. The statistical improvement of the heuristic tool performance is studied by the optimization of the tensioning process of a real cable‐stayed bridge. Results show that the proposed calibration technique provided robust values of the objective function (with lower minimum and mean values, and lower standard deviation) with reduced computational cost.