Optimizing mixture properties of biodiesel production using genetic algorithm-based evolutionary support vector machine

Nowadays, biodiesel is used as one of the alternative renewable energy due to the increasing energy demand. However, optimum production of biodiesel still requires a huge number of expensive and time-consuming laboratory tests. To address the problem, this research develops a novel Genetic Algorithm-based Evolutionary Support Vector Machine (GA-ESIM). The GA-ESIM is an Artificial Intelligence (AI)-based tool that combines K-means Chaotic Genetic Algorithm (KCGA) and Evolutionary Support Vector Machine Inference Model (ESIM). The ESIM is utilized as a supervised learning technique to establish a highly accurate prediction model between the input--output of biodiesel mixture properties; and the KCGA is used to perform the simulation to obtain the optimum mixture properties based on the prediction model. A real biodiesel experimental data is provided to validate the GA-ESIM performance. Our simulation results demonstrate that the GA-ESIM establishes a prediction model with better accuracy than other AI-based tool and thus obtains the mixture properties with the biodiesel yield of 99.9%, higher than the best experimental data record, 97.4%.     

军用集成电路质量控制方法分析与探讨

集成电路是军用电子设备最重要的器件之一,集成电路的质量直接影响到军用装备的质量。从集成电路的选择、二次筛选和破坏性物理分析(DPA)这几个方面探讨了军用集成电路的质量控制方法。实践证明通过质量控制筛选得到的集成电路整批使用可靠性都有明显的提高。     

Ecosystem services assessments in local municipal decision making in South Africa: justification for the use of a business-based approach

The ecosystem services (ES) concept is being increasingly incorporated into environmental policy formulation and management approaches. The Corporate Ecosystem Services Review (ESR) is a framework used to assess the dependence and impact that a business has on ES. The success of the corporate experience of ES assessment provides an opportunity for adaption for local authority decision making. In this paper, the ESR tool was adapted to the South African setting at a local government level, and tested at two sites in the Msunduzi Municipality, KwaZulu-Natal. In testing the tool and gathering feedback from key stakeholders, it was found that there are both opportunities and challenges to this approach. Overall, however, it provides an opportunity for the systematic inclusion of ES assessment into existing regulatory frameworks for land-use planning and Integrated Environmental Management, whether in a strategic application, at a broader spatial (municipal) scale or in a specific locale within the municipality.     

A spatially explicit backcasting approach for sustainable land-use planning

General backcasting as a decision support and planning method starts from desired future states and simulates developments backwards until reaching the present state. Development pathways that reveal steps to be taken to reach a certain future state, and milestones that serve as interim goals, are created during the process. Backcasting has hitherto only been applied in workshops or as a theoretical framework and no spatially explicit backcasting model has previously been established. This paper presents the development of a spatially explicit backcasting model. The proposed model first creates a future scenario utilizing an agent-based model and then simulates backwards. It is implemented using the programming language Python. The model has been applied to a case study for sustainable land-use planning in Salzburg, Austria. The results of the model run show a successful backcasting of land-use classes from a future state back to the present, in 10 year time steps.     

化学事故危害后果评估与应急救援的辅助决策系统设计

根据重大城市的化学事故后果评估与应急救援的实际需要出发,提出了研制辅助决策系统任务需求和设计构想,阐述了该系统的系统结构、系统实现的流程和系统功能,并做了可行性分析。系统的模块包括：化学品基础信息模块、化学事故类型划分模块、地理信息系统模块、化学源周围道路交通模块、实时的天气预报模块、数学模型模块、危害后果评估模块、救援方案生成模块、人员疏散撤离方案生成模块、人机交互模块。系统与地理信息系统（G IS）、卫星导航系统（GPS）、遥感成像技术结合后能够实现精确定位、快速评估。将物联网技术与系统结合,还可实现对大型固定化学源远程时时监控,确保在事故发生后第一时间掌握信息,为后果评估和应急救援赢得时间,将化学突发事故的危害降到最低。该系统在信息化条件下,较好地为决策者进行化学事故后果评估,为应急救援决策提供了依据,可大幅度提高应急救援效能。     

氧化沟工艺处理火车站废水的运行与调试

以信阳市火车北站污水处理工程为例．介绍了以一体化氧化沟工艺为主的处理工艺及其主要构筑物如：泵井、平流沉砂池、氧化沟以及接触消毒池的结构特点和设计水力负荷条件等。针对火车站废水特有的含油污量高、可生化性差的特点．指出了其运行与调试过程中应注意的问题。     

近20年来中国典型区域PM2.5时空演变过程

近20年来PM_(2.5)污染严重制约了中国可持续发展.长时间序列历史监测数据的缺失阻碍了相关研究.为此,本文以四大典型区域2013~2016年的PM_(2.5)浓度监测值和2000~2016年MODIS AOD数据、边界层高度、温度等气象数据作为基础数据,将反向人工神经网络和支持向量回归机两种算法相结合,构建组合模拟模型,并利用地理空间分析技术实现近20年来PM_(2.5)浓度历史变化过程的情景再现.研究结果表明,组合模型具有较低的误差和更高的泛化能力;时空分析结果表明,2000~2010年京津冀和东三省PM_(2.5)浓度持续增长,珠三角PM_(2.5)浓度缓慢下降,3个研究区PM_(2.5)污染范围呈扩大趋势,长三角PM_(2.5)浓度值及污染范围基本保持稳定.2012年4个研究区PM_(2.5)浓度值降低且污染范围缩小,但2013~2016年PM_(2.5)浓度略微上升后又下降,高污染范围缩小,这与国家采取PM_(2.5)区域联防等治理措施有关.     

加速能源转型与产业结构调整的环境健康协同效益评估：以京津冀鲁地区为例

京津冀鲁地区是我国温室气体减排与大气污染治理的重心,随着末端控制措施减排空间的缩紧,通过能源转型和产业结构优化等源头治理方式实现减污降碳协同增效的需求日益迫切.基于开发的REACH综合评估模型,通过情景模拟分析,评估了京津冀鲁地区进一步加强末端控制的减排潜力,以及加速能源转型与产业结构调整的环境和健康协同效益.结果表明,未来在京津冀鲁地区快速推行最佳可行的末端控制技术,2035年能够带来约3.3μg·m^-3的PM_2.5浓度削减,但仅依靠此措施不足以实现区域PM_2.5浓度控制目标;加速能源转型和产业结构调整是京津冀鲁地区实现空气质量达标的必要条件,2035年,能源经济系统的加快转型对大气PM_2.5污染改善的贡献可达6.3μg·m^-3;相比于当前的政策力度,4省市虽然需要额外付出相当于地区GDP 0.9%～2.5%的社会经济成本以实现PM_2.5浓度控制目标,但加速转型带来的环境健康协同效益能够部分或全部覆盖该成本.     

大气环境质量评价的标度指数法

提出用标度表示大气污染物分指数和大气环境质量综合指数新概念。依据大气污染物浓度等比赋值,其危害程度等差分级原则,导出了标度分指数和综合指数的计算公式。标度分指数表达形式简单、规范,对任何污染程度都以统一基准衡量;标度综合指数既能反映多种污染物并存对环境的综合影响,又适当突出严重污染物对环境的危害。通过对实例的应用、分析和比较,证实了该评价方法的有效性、可比性和通用性,且这些性质不受污染物种类和数目多少的限制。     

山区土壤重金属空间插值性能的改进

山区土壤重金属监测中,密集均匀的布点采样困难大,成本高。根据稀疏非均匀样本数据准确预测山区土壤重金属空间分布,对可视化描述检测元素的分布及趋势具有重要意义。基于云南省楚雄市南部山区表层土壤中重金属锰、钒的采样数据,对集成径向基函数神经网络(IRBFANNs)和传统插值方法:反距离(IDW)、普通克里格(OK)、径向基函数神经网络(RBFANNs),进行了不同等级采样密度下的插值性能比较。结果表明,样本点数量减少时,传统预测方法的插值精度都有所下降,而IRBFANNs算法在样本点较少情况下能够保持最好的插值精确度和稳定性,有效改进了空间插值性能。