A flexible intelligent algorithm for identification of optimum mix of demographic variables for integrated HSEE-ISO systems: The case of a gas transmission refinery

This study proposes a flexible intelligent algorithm for assessment and optimization of demographic features on integrated health, safety, and environment and ergonomics (HSEE)-ISO systems among operators of a gas transmission refinery. To achieve the objectives of this study, standard questionnaires with respect to HSEE and ISO standards are completed by 80 operators. Demographic features include age, education, gender, weight, stature, marital status, and work type. The average results for each category of HSEE are used as inputs and effectiveness of ISO systems (ISO 18000, ISO 14000, and ISO 9000) are used as output for the intelligent algorithm. Artificial Neural Networks (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) in addition to conventional regression are used in this paper. Result shows the applicability and superiority of the flexible intelligent algorithm over conventional methods through mean absolute percentage error (MAPE). Computational results show that the proposed ANN performs better than ANFIS and conventional regressions based on its relative error. Finally, the optimum mix of demographic variables from viewpoint of HSEE and ISO are identified. This is the first study that proposes a flexible intelligent algorithm for assessment of optimum mix of demographic features for HSEE and ISO systems in a complex system such as a gas transmission refinery.     

摩托车齿轮类零件的工艺规程自动生成系统的研制

此文介绍了摩托车齿轮类零件的工艺规程自动生成系统。该系统直接从CAD系统中获取零件的有关信息,根据此文所建立的特征体素描述方法,自动生成零件的特征编码,采用零件自动识别的方法实现CAD/CAPP的信息集成,利用工艺知识库,通过工艺决策模型的分级推理,实现齿轮类零件的工艺过程设计的自动化。     

基于模糊神经网络的A2/O工艺出水氨氮在线预测模型

采用厌氧/缺氧/好氧污水处理系统(A2/O)对人工合成污水进行处理,并利用人工神经网络(ANN)模型和自适应模糊人工神经网络(ANFIS)模型对A2/O处理污水的过程进行仿真模拟.在MATLAB环境下,选取可在线监测的水力停留时间(HRT)、进水pH值(pH)、好氧池溶解氧(DO)和混合液回流比(r)作为输入参量,系统出水氨氮浓度(NH4+eff)为输出量,建立在线预测模型.结合自适应模糊C均值聚类算法,确定ANFIS模型的模糊规则数及最优运行参数,对实验数据进行仿真预测.结果表明,与ANN模型相比,ANFIS模型的仿真输出值与实际值的拟合程度更高,相对误差在6.45%之内,平均绝对百分比误差(MAPE)为2.8%,均方根误差(RMSE)为0.1209,相关系数(R)达0.9956.模型训练过程中所得到的三维曲面图,可直观的反映各因素与出水氨氮浓度之间的非线性函数关系,为A2/O系统的高效稳定运行提供指导.     

基于SAVEE方法的海岛空间价值评价——以南沙群岛为例

对SAVEE评价方法的理论基础、分析步骤、应用条件和优缺点进行了系统归纳和总结,构建了SAVEE评价分析模型。以南沙群岛的空间价值评价为例开展实证研究,尝试将SAVEE方法应用于海岛空间价值评价。结果表明:SAVEE评价法计算简便,可操作性强,能够量化体现每个因子价值,评价结果清晰易懂。SAVEE为空间价值评价方法提供了新的选择,具有极大的应用前景。     

基于自适应网络模糊推理方法在河道洪水预报中的应用

对于易受洪灾的地区而言,快速而准确的洪水预报非常重要,能够为洪水预警消息的发布提供更长的先导时间,从而为可能受灾地区的人们提供更充足的时间以采取相应的防洪措施或安全转移。 常用的预报模型包括基于物理性模型和基于系统技术模型。尽管物理性模型能对洪水形成的物理过程提供很好的解释, 水文学家并不愿意使用它们,因为模型中参数的率定是比较复杂的。因此,一种基于纯数据集的黑箱技术已被广泛采纳。常用的黑箱模型包括线性模型(LR)、自回归移动平均模型(ARMA)和人工神经网络模型（ANN）等。 在当前的研究中,一个相对新颖的黑箱模型--基于自适应网络的模糊推理系统（ANFIS）被用来对长江某河段的洪水进行预报。与此同时,一个线性回归模型（LR）用来作为ANFIS模型的对照。在构建ANFIS中,混合学习算法 (即误差反衍（BP）耦合最小二乘法（LSE）) 用来训练模型的参数。此外,为避免出现过度训练现象,原始数据集基于统计特征值划分成3个子集：训练集、测试集和校正集。当对ANFIS模型训练时,测试集用来帮助控制训练代数。结果表明,ANFIS的预报效果优于LR模型。分析认为ANFIS能够提供预报精度是因为其采用了局部拟合技术,通常它会优于LR模型所采用的全局拟合技术。最后,对本研究而言,最适合的ANFIS模型是输入量为梯形的成员度函数。     

滇池流域TN、TP入湖负荷预报预警系统

以流域模型HSPF和贝叶斯递归回归树算法(BRRT)为计算模块,建立了滇池流域27条主要入湖河流和33个散流区的TN、TP入湖负荷预报预警系统.同时,构建了考虑历史排放规律和预测负荷计算预警指数(EWI)评价预警等级的两套预警体系.结果表明:BRRT替代模型在流域内以农业面源为主的柴河子流域校准和验证的可决系数R2均大于0.8,模拟结果相对可靠;根据预警时间选取预警体系;适用于6月份之前的预警体系一(EWS-1),利用现状排放量和历史排放量的关系计算预警指数.适用于6月份之后的预警体系二(EWS-2),主要考虑现状排放量、历史平均排放量、排放限值和预测排放量之间的关系计算3个预警指数,最终以最严格的作为综合预警指数EWI评价预警等级;根据柴河子流域"十二五"规划的TN和TP排放限值为130.2 t·a-1、6.8 t·a-1,应用此系统对2011年2、4、9和11月做出预警检验,各月份预警结果基本处于红色和黑色预警,该系统可为流域提供预警支持.     

Mechanisms and impacts of an incentive-based conservation program with evidence from a randomized control trial

Conservation science needs more high-quality impact evaluations, especially ones that explore mechanisms of success or failure. Randomized control trials (RCTs) provide particularly robust evidence of the effectiveness of interventions (although they have been criticized as reductionist and unable to provide insights into mechanisms), but there have been few such experiments investigating conservation at the landscape scale. We explored the impact of Watershared, an incentive-based conservation program in the Bolivian Andes, with one of the few RCTs of landscape-scale conservation in existence. There is strong interest in such incentive-based conservation approaches as some argue they can avoid negative social impacts sometimes associated with protected areas. We focused on social and environmental outcomes based on responses from a household survey in 129 communities randomly allocated to control or treatment (conducted both at the baseline in 2010 and repeated in 2015–2016). We controlled for incomplete program uptake by combining standard RCT analysis with matching methods and investigated mechanisms by exploring intermediate and ultimate outcomes according to the underlying theory of change. Previous analyses, focused on single biophysical outcomes, showed that over its first 5 years Watershared did not slow deforestation or improve water quality at the landscape scale. We found that Watershared influenced some outcomes measured using the survey, but the effects were complex, and some were unexpected. We thus demonstrated how RCTs can provide insights into the pathways of impact, as well as whether an intervention has impact. This paper, one of the first registered reports in conservation science, demonstrates how preregistration can help make complex research designs more transparent, avoid cherry picking, and reduce publication bias.     

Hierarchical spatial point process analysis for a plant community with high biodiversity

A complex multivariate spatial point pattern of a plant community with high biodiversity is modelled using a hierarchical multivariate point process model. In the model, interactions between plants with different post-fire regeneration strategies are of key interest. We consider initially a maximum likelihood approach to inference where problems arise due to unknown interaction radii for the plants. We next demonstrate that a Bayesian approach provides a flexible framework for incorporating prior information concerning the interaction radii. From an ecological perspective, we are able both to confirm existing knowledge on species’ interactions and to generate new biological questions and hypotheses on species’ interactions.

External drift kriging of NOx concentrations with dispersion model output in a reduced air quality monitoring network

In the mid nineteen eighties the Dutch NO_x air quality monitoring network was reduced from 73 to 32 rural and city background stations, leading to higher spatial uncertainties. In this study, several other sources of information are being used to help reduce uncertainties in parameter estimation and spatial mapping. For parameter estimation, we used Bayesian inference. For mapping, we used kriging with external drift (KED) including secondary information from a dispersion model. The methods were applied to atmospheric NO_x concentrations on rural and urban scales. We compared Bayesian estimation with restricted maximum likelihood estimation and KED with universal kriging. As a reference we also included ordinary least squares (OLS). Comparison of several parameter estimation and spatial interpolation methods was done by cross-validation. Bayesian analysis resulted in an error reduction of 10 to 20% as compared to restricted maximum likelihood, whereas KED resulted in an error reduction of 50% as compared to universal kriging. Where observations were sparse, the predictions were substantially improved by inclusion of the dispersion model output and by using available prior information. No major improvement was observed as compared to OLS, the cause presumably being that much good information is contained in the dispersion model output, so that no additional spatial residual random field is required to explain the data. In all, we conclude that reduction in the monitoring network could be compensated by modern geostatistical methods, and that a traditional simple statistical model is of an almost equal quality.

Univariate Bayesian nonparametric binary regression with application in environmental management

In environmental management, we often have to deal with binary response variables whose outcome dictates the course of action. This paper introduces a nonparametric Bayesian binary regression model with a single predictor variable that is more flexible than the commonly used logistic or probit models. Due to the Bayesian feature, the model can be easily used to combine observed data with our knowledge of the subject to produce site-specific results. By using three examples, this paper shows the potential application of the model in the environmental management, and its advantages in terms of flexibility in model specification, robustness to outliers, and realistic interpretation of data.