PLS-based EWMA fault detection strategy for process monitoring

Fault detection (FD) and diagnosis in industrial processes is essential to ensure process safety and maintain product quality. Partial least squares (PLS) has been used successfully in process monitoring because it can effectively deal with highly correlated process variables. However, the conventional PLS-based detection metrics, such as the Hotelling's T² and the Q statistics are ill suited to detect small faults because they only use information from the most recent observations. Other univariate statistical monitoring methods, such as the exponentially weighted moving average (EWMA) control scheme, has shown better abilities to detect small faults. However, EWMA can only be used to monitor single variables. Therefore, the main objective of this paper is to combine the advantages of the univariate EWMA and PLS methods to enhance their performances and widen their applicability in practice. The performance of the proposed PLS-based EWMA FD method was compared with that of the conventional PLS FD method through two simulated examples, one using synthetic data and the other using simulated distillation column data. The simulation results clearly show the effectiveness of the proposed method over the conventional PLS, especially in the presence of faults with small magnitudes.     

中国“四化”建设对水足迹强度的影响分析

采用2000—2016年中国30省市（不包括香港、澳门、台湾、西藏四省区）的数据,构建四化指标体系,计算四化发展指数,进行地区四化水平评价,通过OLS和GMM回归模型考察四化发展对水足迹强度的影响,同时设置四化之间的交互项来识别四化指标之间的相互作用。主要结论如下：首先,从四化水平的地域发展差异上来看,中国四化水平总体上呈现出东部优于中部、中部优于西部的格局,水足迹强度的分布与之类似,说明四化水平发展与水足迹强度之间可能存在相关关系;其次,计量模型显示四化水平的提升对于水足迹强度的改善有积极影响,但每一化对于水足迹强度改善的影响大小不一;第三,以交互项衡量的四化相互作用对于水足迹强度的影响作用为正,表明四化发展对水足迹强度的改善效果逐渐趋于收敛。因此,优先提升落后地区的四化水平,以四化水平的提升推动水足迹强度的降低,能够有效降低我国总体水足迹强度水平。     

A Variance Estimator for Constrained Estimates of Change in Relative Categorical Frequencies

Consistent estimators of change and state becomes an issue when sample data come from a mix of permanent and temporary observation units. A joint maximum likelihood estimator of state and change creates estimates of state that depend on antecedent viz. posterior survey results and may differ from estimates of state derived from a single-date analysis of the sample data. A constrained estimator of change in relative categorical frequencies that eliminates this potential inconsistency is proposed and a model based estimator of their sampling variance is developed. The performance of the constrained estimator is quantified against six criteria and a joint maximum likelihood estimator in simulated sampling from 15 populations with three combinations of permanent and temporary samples, four to six categorical class attributes, and constant size between sampling dates. Bias of the constrained estimators was negligible but larger than for joint maximum likelihood estimators. Mean absolute deviations and variances of constrained estimators were generally at par with the joint estimators. Constrained estimators of root mean square errors and achieved coverage of nominal confidence intervals of constrained estimators were occasionally better. A generalized variance function for the constrained estimates of change is provided as a computational shortcut.     

Investigation of the Influence of Seagrass on Fisheries Catch Level Using Isotonic Regression

The relationship between seagrass area and the commercial catch of some economically important South Australian fish species is not known in any quantitative sense. However, there is evidence in the literature to suggest that seagrass decline will detrimentally impact on species abundance and composition, and consequently that the presence or absence of seagrass will compromise the commercial and recreational fishery. In this paper we describe the construction of models based on order restricted (isotonic) regression and discuss the role of seagrass area, in terms of its influence on the level of commercial catch through modifying the effect of fishing 'effort'.     

Modeling the spatial pattern of farmland using GIS and multiple logistic regression: a case study of Maotiao River Basin, Guizhou Province, China

Land use change is an important topic in the field of global environmental change and sustainable development. Land use change modeling has attracted substantial attention because it helps researchers understand the mechanisms of land use change and assists regulatory bodies in formulating relevant policies. Maotiao River Basin is located in the province of Guizhou, China, which has a developed agricultural industry in the karst mountain areas. This paper selected biophysical and social–economic factors as independent variables, and constructed a multiple logistic regression of farmland spatial distribution probability by random sampling. Then, by using GIS technology and integrating the 2000 data, this study predicted the farmland spatial pattern. When the predicted map was compared with the actual farmland map for 2000, we noted that 71% of the simulation is in accordance with the 2000 farmland pattern. The result satisfactorily proves the reasonability and applicability of our model.     

Using environmental stressor information to predict the ecological status of Maryland non-tidal streams as measured by biological indicators

In Maryland, U.S., an interim framework has recentlybeen developed for using biologically based thresholds, or `biocriteria', to assess the health of nontidal streams statewide at watershed scales. The evaluation of impairment is based on indices of biological integrity from the Maryland Biological Stream Survey (MBSS). We applied logistic regression to quantify how the biotic integrity of streams at a local scale is affected by cumulative effects resulting from catchment land uses, point sources, and nearby transmission line rights-of-way. Indicators for land use were developed from the remote sensing National Land Cover Data and applied at different scales. We determined that the risk of local impairment in nontidal streams rapidly increases with increased urban land use in the catchment area. The average likelihood of failing biocriteria doubled with every 10% points increment in urban land, thus an increase in urban land use from 0 to 20% quadruples the risk of impairment. For the basins evaluated in this study, catchments with more than 40–50% urban land use had greater than 80% probability of failing biocriteria, on average. Inclusion of rights-of-way and point sources in the model did not significantly improve the fit for this data set, most likely because of their low numbers. The overall results indicate that our predictive modeling approach can help pinpoint stream ecosystems experiencing or vulnerable to degradation.     

环境科学研究中两变量非线性相关时的线性回归方程

以环境科学研究两变量非线性相关的问题为对象，讨论建立线性回归方程的方法。有绝对误差均方和最小的最小二乘法、相对误差最小的新回归法。以简易的方法，建立相关性好、误差小的回归方程。介绍了两变量各种非线性相关时的线性回归方程在环境科学研究中的应用。     

利用多次回归拟合水的饱和蒸气压与温度的关系表达式

在使用于湿球测定锅炉烟气含湿量的过程中,需要查找水的饱和蒸气压,非常不方便.利用D-196和<化工原理>上册中取得部分数据,用多次线性回归的方法,拟合出水在0～200℃范围内的饱和蒸气压与温度的关系表达式;并对该表达式的误差进行了分析,误差均值为0.2‰,最大值也只有0.8‰,完全可以满足环境监测中数据处理的精度要求.     

方头柱塞冷挤镦工艺及模具设计

分析了硬铝合金方头柱塞件的冷挤镦工艺 ,设计了方头柱塞冷挤镦件图 ,计算及选用了毛坯形状及尺寸 ,验算了许可变形程度 ,选择了冷成形用的设备 ,拟制了冷挤镦工艺前的毛坯处理并设计了方头柱塞冷挤镦模具结构。     

常压塔塔顶腐蚀关键参量相关性分析与预测

预测常压塔顶回流罐切水的关键离子浓度可以为常压塔顶系统工艺防腐提供技术指导。收集了某炼厂2014-2016年常压装置的生产实时工艺参数、原料及产品采样数据、水质分析化验参数,采用线性插值方法对不同时间尺度的数据进行补全。通过线性相关性分析获得了影响常压塔顶回流罐切水总铁离子浓度、pH的主要因素,并基于深度学习、支持向量机回归、粒子群优化方法建立了腐蚀关键参量预测模型。结果表明,pH值和总铁离子浓度的相关因素大部分重叠,与原料性质及产品馏出温度较强相关;建立的回归模型预测精度高,在训练集和预测集上,总铁离子浓度预测值与测量值最大偏差分别为4. 4%和9. 8%,pH值预测值与测量值最大偏差分别为0. 9%和1. 1%。