基于XGBoost算法的WRF-Chem模式优化模拟

采用人工智能算法XGBoost结合大气化学模式WRF-Chem,利用北京地区大气污染物的模拟结果及站点监测数据,构建XGBoost统计预报算法模型,并对两种大气污染物（PM_2.5和O₃）进行优化模拟,同时分析其特征贡献要素.结果表明,该统计预报模型能够很好地优化大气化学模式模拟的大气污染物浓度,降低模拟误差,对于北京地区站点模拟浓度优化呈现出城区>近郊>远郊的优化特点,且算法模型对O₃浓度优化程度更高,优化后相关系数提高达128%.此外,通过特征要素的贡献量分析表明,CO是影响O₃优化的重要特征变量,城郊区特征贡献得分均高达1000以上,Q2（近地面2m比湿）是影响PM_2.5优化的重要气象特征变量,城郊区特征贡献得分分别为950和824.     

几何射线追踪法算法改进

本文主要研究电波传播模拟中重要的方法射线追踪法的算法改进问题。讨论在射线发射阶段的优化算法,通过设计一种新的数据结构来达到动态追踪的目的。最终在保证精度的前提下减少追踪射线的条数,减少追踪时间,实现算法优化。     

基于改进蝴蝶算法和社会力模型的多出口疏散模型研究*

为提高多出口场景下行人疏散效率和精度,基于蝴蝶算法和社会力模型,提出一种新的应急疏散仿真路径规划方法。在原有社会力模型中,考虑距离出口远近及行人所处位置拥挤度对运动过程中期望速度的影响,引入速度调节因子,描述行人在疏散中的期望速度变化;针对蝴蝶算法中后期收敛速度慢和易陷入局部最优的缺陷,提出自适应感知概率参数以增强局部搜索和全局搜索之间的平衡;在每轮迭代结束时引入迭代局部搜索策略,扰动局部最优解获得中间状态,并重新搜索上述中间状态得到全局最优解。研究结果表明:提出的应急疏散仿真路径规划方法在多出口环境下能够更有效地利用出口资源,提高疏散效率。     

环冷机组TSP无组织排放溯源及影响因素分析

本文以中心虚点源法为基础,通过虚设源强与误差分析相结合的方式,对某烧结厂环冷机组面源TSP（总悬浮颗粒物）无组织排放的源强进行了反推计算,得到该面源在监测期间TSP排放量范围在12300 ～ 20790mg/s,最小总误差只有9.3％.其中16 ～30μm粒径段颗粒物占的比例最大达28％.并对这种系统误差浮动产生的原因进行了分析,发现选取较大风速条件进行模拟时可以减小系统误差.同时采用spss软件对源排放量与实际工况进行了多元线性回归分析,发现环冷机的颗粒物无组织排放与其核心生产原料混匀矿相关性最大,推测该环冷机组粉尘无组织排放量大的根本原因是机组的超负荷使用.     

Modeling Hydraulic and Thermal Electricity Production Based on Genetic Algorithm-Time Series (GATS)

Abstract

This study deals with the estimation of electricity production from hydraulic and thermal sources using the Genetic Algorithm (GA) with time series (TS) approach. Two forms of the mathematical models are developed, of which one is exponential and the second is polynomial. The power form of the Genetic Algorithm-Time Series (GATS) model is used for the thermal electricity production. The polynomial form of the GATS is used for the electricity production from the hydraulic sources. The GATS weighting parameters are obtained by minimizing the Sum of Squared Error (SSE) between observed and estimated electricity production from both sources. Therefore, the fitness function adapted is the minimization of the SSE for use in the GA process. The application of the GATS model is correspondingly presented. Some future scenarios are made to increase the electricity production from hydraulic sources. Variations of the electricity production from thermal and hydraulic energy sources are analyzed. Future prospects of electricity production are dealt with in terms of policy changes. The GATS models are used for making scenarios for future electricity planning policy. Results also show if current trend continues, the thermal electricity production amounts to 75% of the total electricity production, which is undesirable for environmental concerns. Results also shows that if new policy is to move from the thermal to hydraulic electricity production, the hydraulic sources will meet the demand until 2020.     

基于差异进化支持向量机的坑外土体沉降预测

就用支持向量机(SVM)预测基坑外土体沉降而言,通过差异进化(DE)算法构造适合的决策函数十分重要。在确定坑外土体沉降函数的基本形式下,进行参数反演。后将得到的解析式作为SVM的决策函数,再进行核函数转换,从而使SVM的曲线拟合更加快速,预测更加准确。对大连地铁湾家车站基坑坑外土体的沉降数据的分析及预测的结果表明,使用SVM-DE算法在计算数据量、计算消耗时间和预测精度方面优于2种方法单独使用。     

基于ANN耦合遗传算法的爆破方案选择方法

为预防露天矿爆破引起的事故,基于安全和经济方面的考虑,对露天矿爆破方案进行优化选择,提出将人工神经网络(ANN)模型与遗传算法(GA)相耦合,从而进行爆破方案优化。研究露天矿爆破可能引起的2种主要危害形式:超爆和飞石,进而确定超爆深度和飞石距离为爆破方案的被优化目标参数。另一方面,炮眼深、间距、装药深度、阻塞深度、单位炸药消耗量和钻孔率对超爆深度和飞石距离的影响是复杂的、非线性的,因而将其作为爆破方案的影响参数。分别用影响参数和目标参数作为ANN的输入值和输出值加以训练,训练后的ANN数据作为GA的适应度函数进行方案优化。结果表明:可找到符合工程实例数据的爆破方案集合,借助Pareto图,可得到相关参数的值最小(超瀑深度为0.6999m,飞石距离为27.3386m)的最优爆破方案。     

A FUZZY SETS MODEL FOR MEASURING THE EFFECTIVENESS OF PUBLIC PARTICIPATION IN WATER RESOURCES PLANNING1

Mathematical modeling of complex water resources System problems, particularly water pollution control, is aided by fizzy set theory. Public participation in large scale federally funded water resources and pollution control projects is now a federal requirement and practice of various planning agencies. However, no systems based model for quantifying and measuring the effectiveness of public participation is known to exist. In this paper, we report a fuzzy set based model developed for doing this in areawide water resources planning The model is essentially cascade in nature and employs the concepts of fuzzy pessimistic and optimistic aggregations to cluster and analyze the evaluations of the basic factors. Sample computations of the model are provided.     

Cost effective environmental control technology for utilities

On September 24, 1998, new regulations announced by the US EPA require 22 eastern states plus the District of Columbia to develop state implementation plans to reduce ground-level ozone through the reduction of nitrogen oxide (NOx) emissions (Cooper, 1998). This plan calls for a 28% NOx cut in the summer time (1.2 million tons) by 2007. This calls for utilities to develop new, efficient, and robust post-combustion NOx control technologies. A new environmental control technology called low temperature oxidation (LTO) system, which can reduce NOx emissions below measurable levels (i.e. 2 ppm using process analyzers) at low temperature (125-325 °F), was awarded the best available control technology and the lowest available emission reduction technology by the US EPA in April 1998. Ozone is employed to oxidize nitric oxide (NO) to dinitrogen pentoxide (N₂O₅) at a low temperature in an oxidizer, which is then easily absorbed by water in a scrubber. Bench scale and pilot plant tests have shown that the LTO process can almost completely remove the NOx emissions (i.e. NOx emissions are below levels measurable using process analyzers). This proved that the LTO system is an attractive process to meet the stricter NOx regulations. There are multiple benefits of the LTO system besides removal of NOx emissions, includes reduction of SOx and CO emissions, and no secondary air emissions (NH₃, N₂O). In order to obtain minimum NOx emissions, extra ozone needs to be supplied. The cost of the process also increases nonlinearly as emissions decrease. This poses a challenging multiobjective optimization problem where emissions like NOx and SOx need to be minimized, while minimizing the system cost as well as extra ozone. This problem is addressed using a new and efficient multiobjective optimization framework. This framework will provide designs that are cost effective as well as environmentally friendly.     

Decision Tree Algorithm for Detection of Spatial Processes in Landscape Transformation

The conversion of landscapes by human activities results in widespread changes in landscape spatial structure. Regardless of the type of land conversion, there appears to be a limited number of common spatial configurations that result from such land transformation processes. Some of these configurations are considered optimal or more desirable than others. Based on pattern geometry, we define ten processes responsible for pattern change: aggregation, attrition, creation, deformation, dissection, enlargement, fragmentation, perforation, shift, and shrinkage. A novelty in this contribution is the inclusion of transformation processes causing expansion of the land cover of interest. Consequently, we propose a decision tree algorithm that enables detection of these processes, based on three parameters that have to be determined before and after the transformation of the landscape: area, perimeter length, and number of patches of the focal landscape class. As an example, the decision tree algorithm is applied to determine the transformation processes of three divergent land cover change scenarios: deciduous woodland degradation in Cadiz Township (Wisconsin, USA) 1831–1950, canopy gap formation in a terra firme rain forest at the Tiputini Biodiversity Station (Amazonian Ecuador) 1997–1998, and forest regrowth in Petersham Township (Massachusetts, USA) 1830–1985. The examples signal the importance of the temporal resolution of the data, since long-term pattern conversions can be subdivided in stadia in which particular pattern components are altered by specific transformation processes.