PSO和SVM混合算法确定太湖入湖河流水质主要影响因子

以影响太湖入湖河流水质的24个因子值为研究对象,将PSO算法与SVM算法相结合。PSO算法用于优化SVM算法的参数c和g,以利于快速、高效地确定c和g的全局最优值;SVM算法基于最优的c和g,分别以24,21,18,15,12,9和6个因子作为特征向量预测水质的污染程度。结果表明,当特征向量为9个影响因子时预测率最高。其参数c=18.56,g=1.35,对应的预测率为：全局预测率92.59%,重度污染水质预测率88.89%,轻度污染水质预测率94.45%。因此,通过PSO和SVM混合算法,可以确定影响太湖入湖河流水质的主要因子,利用这些主要因子对水质进行预测预警,不但可以节省时间,而且可以得到精确的结果。     

基于PSO-SVM算法的环境监测数据异常检测和缺失补全

针对环境监测数据异常和数据缺失问题,提出了基于支持向量机的粒子群优化数据异常检测和缺失补全算法。利用粒子群优化算法选取较优的支持向量机训练参数组合,以此建立非线性的支持向量机模型,并利用结果模型对测得的真实数据拟合预测。以宁夏回族自治区某污水处理厂的污染物测量数据作为实验数据,结果表明,利用该算法预测数据的准确率可达97.977%,检测异常数据准确度高,缺失数据补全正确。     

Optimal Expansion Strategy for a Sewer System under Uncertainty

Because of fast urban sprawl, land use competition, and the gap in available funds and needed funds, municipal decision makers and planners are looking for more cost-effective and sustainable ways to improve their sewer infrastructure systems. The dominant approaches have turned to planning the sanitary sewer systems within a regional context, while the decentralized and on-site/cluster wastewater systems have not overcome the application barriers. But regionalization policy confers uncertainties and risks upon cities while planning for future events. Following the philosophy of smart growth, this paper presents several optimal expansion schemes for a fast-growing city in the US/Mexico borderlands—the city of Pharr in Texas under uncertainty. The waste stream generated in Pharr is divided into three distinct sewer sheds within the city limit, including south region, central region, and north region. The options available include routing the wastewater to a neighboring municipality (i.e., McAllen) for treatment and reuse, expanding the existing wastewater treatment plant (WWTP) in the south sewer shed, and constructing a new WWTP in the north sewer shed. Traditional deterministic least-cost optimization applied in the first stage can provide a cost-effective and technology-based decision without respect to associated uncertainties system wide. As the model is primarily driven by the fees charged for wastewater transfer, sensitivity analysis was emphasized by the inclusion of varying flat-rate fees for adjustable transfer schemes before contracting process that may support the assessment of fiscal benefits to all parties involved. Yet uncertainties might arise from wastewater generation, wastewater reuse, and cost increase in constructing and operating the new wastewater treatment plant simultaneously. When dealing with multiple sources of uncertainty, the grey mixed integer programming (GIP) model, formulated in the second stage, can further allow all sources of uncertainties to propagate throughout the optimization context, simultaneously leading to determine a wealth of optimal decisions within a reasonable range. Both models ran for three 5-year periods beginning in 2005 and ending in 2020. The dynamic outputs of this analysis reflect the systematic concerns about integrative uncertainties within this decision analysis, which enable decision makers and stakeholders to make all-inclusive decisions for sanitary sewer system expansion in an economically growing region.     

基于两级拓扑优化的振动台扩展台面设计与试验验证

根据拓扑优化基本原理,利用OptiStruct进行振动台扩展台面的结构最优化设计,通过两级拓扑优化完成结构的拓扑寻优。首先利用整体级拓扑优化,找到结构的整体最佳构造。然后利用局部级拓扑优化,对局部结构进行拓扑寻优,最终完成产品的结构设计。试验结果与仿真结果对比表明,误差在5%以内,表明方法的有效性和实用性。     

The Role of Translocation in Recovery of Woodland Caribou Populations

Abstract: Maintenance of viable populations of many endangered species will require conservation action in perpetuity. Efforts to conserve these species are more likely to be successful if their reliance on conservation actions is assessed at the population level. Woodland caribou (Rangifer tarandus caribou) were extirpated recently from Banff National Park, Canada, and translocations of caribou to Banff and neighboring Jasper National Park are being considered. We used population viability analysis to assess the relative need for and benefits from translocation of individuals among caribou populations. We measured stochastic growth rates and the probability of quasi extinction of four populations of woodland caribou with and without translocation. We used two vital rates in our analysis: mean adult female survival and mean number of calves per breeding‐age female as estimates of mean fecundity. We isolated process variance for each vital rate. Our results suggested the Tonquin caribou population in Jasper is likely to remain viable without translocation, but that translocation is probably insufficient to prevent eventual extirpation of the two other populations in Jasper. Simulated reintroductions of caribou into Banff resulted in a 53–98% probability of >8 females remaining after 20 years, which suggests translocation may be an effective recovery tool for some caribou populations.     

APPLICATION OF ENHANCED ANNEALING TO GROUND WATER REMEDIATION DESIGN1

ABSTRACT: A methodology for ground water remediation design has been developed that interfaces ground water simulation models with an enhanced annealing optimizer. The ground water flow and transport simulators provide the ability to consider site‐specific contamination and geohydrologic conditions directly in the assessment of alternative remediation system designs. The optimizer facilitates analysis of tradeoffs between technical, environmental, regulatory, and financial risks for alternative design and operation scenarios. A ground water management model using an optimization method referred to as “enhanced annealing” (simulated annealing enhanced to include “directional search” and “memory” mechanisms) has been developed and successfully applied to an actual restoration problem. The demonstration site is the contaminated unconfined aquifer referred to as N‐Springs located at Han‐ford, Washington. Results of the demonstration show the potential for improving groundwater restoration system performance while reducing overall system cost.     

A COMPARISON OF STREAMFLOW GENERATION MODELS FOR RESERVOIR CAPACITY-YIELD ANALYSIS1

ABSTRACT: An analysis of four streamflow generation schemes for the use in the estimation of the required conservation storage for a single reservoir is presented. The comparison of the generating schemes should aid in the selection of an appropriate model type for the reservoir sizing problem. The streamflow generation models are compared using two criteria. The first comparison is between the statistics of the generated streamflow sequences and the corresponding statistics from the historical record. The second evaluation compares the median reservoir size determined by each model with the required storage based on the historical flow sequence. The results of a comparative analysis for monthly streamflow data for the Rzav River in Yugoslavia are presented and discussed. The results indicate that both evaluation criteria are required to discriminate between the various options.     

COMPARISON OF RESERVOIR LINEAR OPERATION RULES USING LINEAR AND DYNAMIC PROGRAMMING1

ABSTRACT: Mathematical optimization techniques are used to study the operation and design of a single, multi-purpose reservoir system. Optimal monthly release policies are derived for Hoover Reservoir, located in Central Ohio, using chance-constrained linear programming and dynamic programming-regression methodologies. Important characteristics of the former approach are derived, discussed, and graphically illustrated using Hoover Reservoir as a case example. Simulation procedures are used to examine and compare the overall performance of the optimal monthly reservoir release policies derived under the two approaches. Results indicate that, for the mean detention time and the corresponding safe yield target water supply release under existing design of Hoover Reservoir, the dynamic programming policies produce lower average annual losses (as defined by a two-sided quadratic loss function) while achieving at least as high reliability levels when compared to policies derived under the chance-constrained linear programming method. In making this comparison, the reservoir release policies, although not identical, are assumed to be linear. This restricted form of the release policy is necessary to make the chance-constrained programming method mathematically tractable.     

MODELS FOR WATER AND POWER SCHEDULING FOR THE CALIFORNIA STATE WATER PROJECT1

ABSTRACT: A large-scale simulation/optimization model provides schedules for operation of water and power for the California State Water Project (SWP). The SWP consists of a series of reservoirs linked by rivers, pumping plants, canals, tunnels, and generating plants and is operated by the California Department of Water Resources. The Department provides water to municipal and agricultural users, and manages its electrical loads and resources. The model, therefore, performs hydraulic and electrical computations leading to optimal operation of the entire system. It consists of hydraulic network programming components to meet the storage objectives at all the reservoirs, a linear programming component to determine the schedules at pumping and generating plants, an electrical network programming component to balance electrical loads and resources, and a number of other simulation components. It operates on yearly, weekly, and daily bases. It is primarily used for real-time operation of the SWP and can provide hourly detail schedules which are implemented by the SWP staff via a computerized system.