基于二值逻辑的复合绝缘子状态判别策略研究

复合绝缘子是架空输电线路上广泛使用的设备,它的老化会给电力系统的正常运行带来威胁。电力相关工作人员需要一种能够对复合绝缘子的运行状态进行判别的方法,帮助他们确定复合绝缘子是否满足运行要求,而对复合绝缘子的定性表征就成为一种优选的表征策略。将运行后的复合绝缘子分成"满足运行要求"和"不满足运行要求",使用二值逻辑回归模型,选取合适的特征量,建立了复合绝缘子状态表征体系。     

The role of situation awareness in accidents of large-scale technological systems

In the last two decades, several serious accidents at large-scale technological systems that have had grave consequences, such as that at Bhopal, have primarily been attributed to human error. However, further investigations have revealed that humans are not the primary cause of these accidents, but have inherited the problems and difficulties of working with complex systems created by engineers. The operators have to comprehend malfunctions in real time, respond quickly, and make rapid decisions to return operational units to normal conditions, but under these circumstances, the mental workload of operators rises sharply, and a mental workload that is too high increases the rate of error. Therefore, cognivitive human features such as situation awareness (SA)—one of the most important prerequisite for decision-making—should be considered and analyzed appropriately. This paper applys the SA Error Taxonomy methodology to analyze the role of SA in three different accidents: (1) A runaway chemical reaction at Institute, West Virginia killing two employees, injuring eight people, and requiring the evacuation of more than 40,000 residents adjacent to the facility, (2) The ignition of a vapor cloud at Bellwood, Illinois that killed one person, injured two employees, and caused significant business interruption, and (3) An explosion at Ontario, California injuring four workers and caused extensive damage to the facility. In addition, the paper presents certain requirements for cognitive operator support system development and operator training under abnormal situations to promote operators’ SA in the process industry.     

回采工作面瓦斯涌出量遗传投影寻踪回归预测

为快速、准确预测回采工作面瓦斯涌出量,基于投影降维思想,建立一种遗传算法(GA)投影寻踪回归预测方法。选取煤层瓦斯原始含量、埋藏深度、煤层厚度、煤层倾角、工作面长度、推进速度、采出率、临近层瓦斯含量、临近层厚度、临近层层间距、岩层岩性、开采深度作为评价因子,对某矿15个学习样本进行训练,建立GA投影寻踪回归预测模型。利用该矿3个实测样本对模型进行检验,并与主成分分析和BP神经网络方法结果进行对比。研究表明:利用GA投影寻踪回归预测回采工作面瓦斯涌出量,平均误差为3.43%,最大误差为5.7%,精度优于其他2种方法。     

岩溶塌陷倾向性等级的KPCA-SVM预测模型

为了快速、有效地预测岩溶塌陷倾向性等级,在统计分析大量观测实例的基础上,选取岩性系数、岩体结构系数、地下水系数、覆盖层系数、地形地貌系数和环境条件系数作为特征指标。利用核主成分分析(KPCA)方法在高维空间提取岩溶塌陷影响因子的主成分,将获取的主成分作为支持向量机(SVM)的特征向量,建立基于KPCA的岩溶塌陷倾向性等级的SVM预测模型。将12组观测数据作为学习样本对模型进行训练。采用回代估计法进行回检,误判率为0。利用训练好的模型对2组待判样本进行预测。结果表明:经KPCA后指标个数减少,相关性降低,SVM运算的复杂度降低。用该模型所得预测结果的准确率为100%。     

Modelling and Prediction of Diesel Engine Performance using Relevance Vector Machine

Diesel engines are being increasingly adopted by many car manufacturers today, yet no exact mathematical diesel engine model exists due to its highly nonlinear nature. In the current literature, black-box identification has been widely used for diesel engine modelling and many artificial neural network (ANN) based models have been developed. However, ANN has many drawbacks such as multiple local minima, user burden on selection of optimal network structure, large training data size, and over-fitting risk. To overcome these drawbacks, this article proposes to apply an emerging machine learning technique, relevance vector machine (RVM), to model and predict the diesel engine performance. The property of global optimal solution of RVM allows the model to be trained using only a few experimental data sets. In this study, the inputs of the model are engine speed, load, and cooling water temperature, while the output parameters are the brake-specific fuel consumption and the amount of exhaust emissions like nitrogen oxides and carbon dioxide. Experimental results show that the model accuracy is satisfactory even the training data is scarce. Moreover, the model accuracy is compared with that using typical ANN. Evaluation results also show that RVM is superior to typical ANN approach.     

基于地理加权回归模型评估土地利用对地表水质的影响

针对传统线性回归模型大多忽视空间数据局部变化特征这一缺陷,引入地理加权回归模型(GWR)用于评估土地利用对地表水质的影响,分析了不同子流域内两者关系出现空间变化的规律并阐释了原因.同时,对比了GWR模型与普通最小二乘模型(OLS)的校正R2、Akaike信息准则(AICc)及残差的空间自相关指数(Moran's I),验证了GWR模型在预测精度和处理空间自相关过程中是否优于OLS模型.结果表明,同一土地利用类型对水质的影响随空间位置的改变而发生方向或大小的变化.以温瑞塘河流域总氮(TN)与农用地的关系为例,从GWR模型局部回归系数的方向分析,两者关系表现为农村正、城区负的现象,从大小分析,旧城区TN与农用地回归系数的绝对值高于其它区域;在溶解氧(DO)与人口密度所构建的GWR模型中,两者关系在整个研究区域内均表现为负值,与OLS结果吻合,从回归系数的大小分析,人口密度对DO的作用在郊区及农村更为显著.针对此类关系出现空间变化的原因分析表明,相邻子流域土地利用百分比的改变及水体主要污染源的不同,是导致土地利用对水质作用发生变化的根本因素.最后,对比所构建的80个GWR与OLS模型校正R2、AICc指标,验证了GWR作为一种局部统计模型,其预测精度优于OLS等传统全局模型且更能反映实际空间特征.     

Stepwise multiple regression method of greenhouse gas emission modeling in the energy sector in Poland

The energy sector in Poland is the source of 81% of greenhouse gas (GHG) emissions. Poland, among other European Union countries, occupies a leading position with regard to coal consumption. Polish energy sector actively participates in efforts to reduce GHG emissions to the atmosphere, through a gradual decrease of the share of coal in the fuel mix and development of renewable energy sources. All evidence which completes the knowledge about issues related to GHG emissions is a valuable source of information. The article presents the results of modeling of GHG emissions which are generated by the energy sector in Poland. For a better understanding of the quantitative relationship between total consumption of primary energy and greenhouse gas emission, multiple stepwise regression model was applied. The modeling results of CO₂ emissions demonstrate a high relationship (0.97) with the hard coal consumption variable. Adjustment coefficient of the model to actual data is high and equal to 95%. The backward step regression model, in the case of CH₄ emission, indicated the presence of hard coal (0.66), peat and fuel wood (0.34), solid waste fuels, as well as other sources (− 0.64) as the most important variables. The adjusted coefficient is suitable and equals R² = 0.90. For N₂O emission modeling the obtained coefficient of determination is low and equal to 43%. A significant variable influencing the amount of N₂O emission is the peat and wood fuel consumption.     

Stepwise multiple regression method of greenhouse gas emission modeling in the energy sector in Poland

The energy sector in Poland is the source of 81% of greenhouse gas (GHG) emissions. Poland, among other European Union countries, occupies a leading position with regard to coal consumption. Polish energy sector actively participates in efforts to reduce GHG emissions to the atmosphere, through a gradual decrease of the share of coal in the fuel mix and development of renewable energy sources. All evidence which completes the knowledge about issues related to GHG emissions is a valuable source of information. The article presents the results of modeling of GHG emissions which are generated by the energy sector in Poland. For a better understanding of the quantitative relationship between total consumption of primary energy and greenhouse gas emission, multiple stepwise regression model was applied. The modeling results of CO₂ emissions demonstrate a high relationship (0.97) with the hard coal consumption variable. Adjustment coefficient of the model to actual data is high and equal to 95%. The backward step regression model, in the case of CH₄ emission, indicated the presence of hard coal (0.66), peat and fuel wood (0.34), solid waste fuels, as well as other sources (-0.64) as the most important variables. The adjusted coefficient is suitable and equals R² = 0.90. For N₂O emission modeling the obtained coefficient of determination is low and equal to 43%. A significant variable influencing the amount of N₂O emission is the peat and wood fuel consumption.     

Prediction of effluent concentration in a wastewater treatment plant using machine learning models

Of growing amount of food waste, the integrated food waste and waste water treatment was regarded as one of the efficient modeling method. However, the load of food waste to the conventional waste treatment process might lead to the high concentration of total nitrogen(T-N) impact on the effluent water quality. The objective of this study is to establish two machine learning models—artificial neural networks(ANNs) and support vector machines(SVMs), in order to predict 1-day interval T-N concentration of effluent from a wastewater treatment plant in Ulsan, Korea. Daily water quality data and meteorological data were used and the performance of both models was evaluated in terms of the coefficient of determination(R~2), Nash–Sutcliff efficiency(NSE), relative efficiency criteria(d rel). Additionally, Latin-Hypercube one-factor-at-a-time(LH-OAT) and a pattern search algorithm were applied to sensitivity analysis and model parameter optimization, respectively. Results showed that both models could be effectively applied to the 1-day interval prediction of T-N concentration of effluent. SVM model showed a higher prediction accuracy in the training stage and similar result in the validation stage.However, the sensitivity analysis demonstrated that the ANN model was a superior model for 1-day interval T-N concentration prediction in terms of the cause-and-effect relationship between T-N concentration and modeling input values to integrated food waste and waste water treatment. This study suggested the efficient and robust nonlinear time-series modeling method for an early prediction of the water quality of integrated food waste and waste water treatment process.     

水资源环境承载能力监测预警平台设计探讨

建立水资源环境承载力监测预警平台与机制,是实现我国环境管理战略由以环境污染控制为目标导向,向以环境质量改善为目标导向彻底转变的重要支撑手段。以水资源环境承载力领域的相关研究进展为基础,提出水资源环境承载力监控预警平台的设计框架,平台设计的逻辑结构、核心功能以及相对应的水资源环境承载力评估技术,并对该平台建设的困难、问题及未来的发展趋势进行了分析,以期为水资源环境承载能力监测预警机制建设提供有益的参考。