基于人工神经网络理论的船舶动力装置安全综合评价模型

为提高船舶动力装置安全综合评价水平，依据人工神经网络的基本原理，分析了BP神经网络模型的基本原理和优化策略，将其应用于船舶动力装置的安全评价之中。提出了基于神经网络理论的船舶动力装置综合安全评价模型及实现方法，并以实例论证了此方法的可行性。     

基于BP网络的建筑安装施工现场安全综合评价的研究

针对目前我国建筑安装施工现场安全评价技术的不成熟和欠科学性的现状 ,笔者分析和综合了目前安全评价技术 ,结合建筑业特点 ,提出了基于BP神经网络的建筑安装施工现场安全评价方法 ,并对该评价模型的原理、方法及算法进行了研究。首先 ,结合建筑安装施工现场安全生产的特点建立评价指标体系 ,随后 ,运用层次分析法确定指标及准则层的权重 ,并运用模糊综合评价法生成评价样本集 ,最后 ,利用样本集训练BP网络 ,待误差满足要求后 ,即可运用训练成功的BP神经网络进行安全评价。     

液化气运输过程中的危险分析

应用各种爆炸后果估计模型对液化气运输过程中的爆炸后果进行了评估，并用ETA分析方法对存在的危险进行了分析，指出了控制措施。     

区域性洪涝灾害的灾情评估

以区域孕灾环境、致灾因子和承灾能力三方面的资料为基础,探讨了如何运用地理信息系统和评估模型进行洪涝灾害灾情评估的思路和方法.经实例验证,综合灾害经济损失总量、区域调节承受能力和灾后社会或部门追加投入总量的洪涝灾度评估方法,可对区域实际遭受洪涝灾害的破坏程度和影响深度做出科学、客观、合理的评估.     

土壤镉污染调查研究

本文阐述了重金属镉对植物和人体危害的机理，描述了土壤镉的主要来源，并开展了城郊及矿山周围土壤镉污染现状调查。调查结果提醒人们提高土壤质量意识，重视土壤镉污染并进行土壤修复，保护生态环境、实现农业的可持续发展。     

Environmental assessment of supercritical water oxidation of sewage sludge

Environmental aspects of using supercritical water oxidation (SCWO) to treat sewage sludge were studied using a life cycle assessment (LCA) methodology. The system studied is the first commercial scale SCWO plant for sewage sludge in the world, treating sludge from the municipal wastewater treatment facility in Harlingen, TX, USA. The environmental impacts were evaluated using three specific environmental attributes: global warming potential (GWP), photo-oxidant creation potential (POCP) and resource depletion; as well as two single point indicators: EPS2000 and EcoIndicator99. The LCA results show that for the described process, gas-fired preheating of the sludge is the major contributor to environmental impacts, and emissions from generating electricity for pumping and for oxygen production are also important. Overall, SCWO processing of undigested sewage sludge is an environmentally attractive technology, particularly when heat is recovered from the process. Energy-conserving measures and recovery of excess oxygen from the SCWO process should be considered for improving the sustainability potential.     

TEMPORAL CHANGES IN THE YADKIN RIVER FLOW VERSUS SUSPENDED SEDIMENT CONCENTRATION RELATIONSHIP1

ABSTRACT: Dynamic linear models (DLM) and seasonal trend decomposition (STL) using local regression, or LOESS, were used to analyze the 50‐year time series of suspended sediment concentrations for the Yadkin River, measured at the U.S. Geological Survey station at Yadkin College, North Carolina. A DLM with constant trend, seasonality, and a log₁₀ streamflow regressor provided the best model to predict monthly mean log₁₀ suspended sediment concentrations, based on the forecast log likelihood. Using DLM, there was evidence (odds approximately 69:1) that the log₁₀ streamflow versus log₁₀ suspended sediment concentration relationship has changed, with an approximate 20 percent increase in the log₁₀ streamflow coefficient over the period 1981 to 1996. However, sediment concentrations in the Yadkin River have decreased during the decade of the 1990s, which has been accompanied by a concomitant increase in streamflow variability. Although STL has been shown to be a versatile trend analysis technique, DLM is shown to be more suitable for discovery and inference of structural changes (trends) in the model coefficient describing the relationship between flow and sediment concentration.     

黄河积石峡水电站库区泥石流危险度评价

在选取一次(可能)最大冲出物方量、泥石流发生频率、流域面积、主沟长度、流域相对高差、流域切割密度、泥沙补给段长度比7个因子为泥石流沟谷危险度划分的主要因子的基础上,对评价因子隶属度的确定作了分析和阐述,并运用模糊综合评判法对黄河上游积石峡水电站库区16条泥石流沟进行了危险度划分.