安钢90 m2烧结机尾除尘工艺设计特点

介绍了安钢90 m2烧结机尾除尘工艺设计中的设备选型、系统配置、管网阻力平衡的特点及应注意的几个问题.     

网络攻击检测中的机器学习方法综述

在详细介绍网络攻击检测机器学习原理的基础上,对现有的各种方法进行了评述,并结合网络攻击检测系统的应用需求,阐述了网络攻击检测系统机器学习技术的发展方向。     

基于机器学习和情景分析的我国焦化行业企业用地污染预测

针对焦化行业企业用地缺乏时序连续监测数据而无法预测其污染趋势的问题,从企业特征、企业管理水平、污染物特征和自然地理要素等4个方面选取13个影响企业用地污染的指标,识别焦化行业企业用地污染主控因子,在此基础上构建基于机器学习的焦化行业企业用地污染预测模型,并在不同情境下,对2025年和2030年焦化行业企业用地污染状况进行预测.结果表明,生产经营活动时间、建厂时间、企业环境监管记录、土壤黏粒和年均风速是焦化行业企业用地污染的主控因子;相对于支持向量机模型、BP神经网络模型和决策树模型,逻辑斯蒂模型预测价值高、性能指标稳健,其预测精度受试者工作曲线面积为0.91,模型准确率和召回率分别为84%和88%.在乐观情境下,2025年和2030年焦化行业高概率污染地块数量分别为1599块和1695块;在悲观情境下,2025年和2030年焦化行业高概率污染地块数量分别为1671块和1715块.研究结果可为焦化行业企业用地的修复治理和生态环境的宏观决策提供科学依据.     

基于应力分解法的整机加速因子预计方法研究

提出了计算整机加速因子的新方法.将整机的失效率通过定量分析方法按照部件、失效模式和应力的顺序逐级下分,从而得到各敏感应力的失效率,再通过加速模型计算各失效模式在加速应力下的失效率.最终可以得到整机在加速应力下的失效率,进而计算出整机加速因子.以典型电子产品为例,预计了弹上计算机在温度、湿度、振动综合环境应力下的加速因子为153.5.     

融合时空特征的PCA-PSO-SVM臭氧(O3)预测方法研究

针对目前臭氧预测方法未能考虑臭氧污染的区域性和在时间周期内的强自相关性的问题,提出一种融合时空特征的PCA-PSO-SVM臭氧组合预测模型.利用小波分析和系统聚类提取臭氧时间序列波动特征和站点空间分布相似性特征,并通过主成分分析和粒子群算法优化的支持向量机组合模型（PCA-PSO-SVM）对臭氧日最大8h平均浓度进行预测,以2016~2018年杭州市大气污染物观测数据和气象数据进行实验验证.结果表明：融合时空特征的PCA-PSO-SVM模型预测精度有较大提升,与未融合时空特征的PCA-PSO-SVM模型相比,精度提升19%.气象因素中温度对臭氧预测效果影响最大,在气象预报数据存在一定误差的情况下,提出的模型仍得到较高精度的预测效果,具备较好的鲁棒性.     

基于pso-SVM的废水厌氧处理过程软测量模型

由于厌氧消化过程的复杂性和厌氧菌的敏感性,保持厌氧消化体系的稳定和高效性是比较困难的.本文在实验室采用IC反应器构建了一套厌氧废水处理系统处理人工合成废水,基于支持向量机(SVM)提出了一种预测废水厌氧处理系统出水挥发性脂肪酸(VFA)浓度和COD去除率的软测量模型.为了提高模型的精确性和鲁棒性,加入pso算法(粒子群算法)优化SVM模型,并引入了分类策略对元数据集进行有效分类.仿真结果表明,基于pso-SVM模型的软测量模型对厌氧废水处理系统出水VFA浓度和COD去除率具有较好的预测能力,模型预测系统COD去除率及出水总VFA浓度测试样本数据相关系数分别为65.86%、85.25%;加入分类策略后,元数据集分成两类,模型预测系统COD去除率测试样本数据相关系数分别为92.34%、83.41%;模型预测系统出水总VFA浓度测试样本数据相关系数分别为99.14%、99.59%,系统预测精度明显提高.引入分类策略对元数据集进行有效分类,基于pso-SVM的软测量模型可为监控、优化和理解厌氧消化过程提供指导.     

Development of a method for comprehensive water quality forecasting and its application in Miyun reservoir of Beijing, China

Water quality forecasting is an essential part of water resource management. Spatiotemporal variations of water quality and their inherent constraints make it very complex. This study explored a data-based method for short-term water quality forecasting. Prediction of water quality indicators including dissolved oxygen, chemical oxygen demand by KMnO₄ and ammonia nitrogen using support vector machine was taken as inputs of the particle swarm algorithm based optimal wavelet neural network to forecast the whole status index of water quality. Gubeikou monitoring section of Miyun reservoir in Beijing, China was taken as the study case to examine effectiveness of this approach. The experiment results also revealed that the proposed model has advantages of stability and time reduction in comparison with other data-driven models including traditional BP neural network model, wavelet neural network model and Gradient Boosting Decision Tree model. It can be used as an effective approach to perform short-term comprehensive water quality prediction.     

Reuse of sugarcane bagasse ash (SCBA) to produce ceramic materials

Sugarcane bagasse ash (SCBA) is a residue resulting from the burning of bagasse in boilers in the sugarcane/alcohol industry. SCBA has a very high silica concentration and contains aluminum, iron, alkalis and alkaline earth oxides in smaller amounts. In this work, the properties of sintered ceramic bodies were evaluated based on the concentration of SCBA, which replaced non-plastic material. The ash was mixed (up to 60 wt%) with a clayed raw material that is used to produce roof tiles. Prismatic probes were pressed and sintered at different temperatures (up to 1200 °C). Technological tests of ceramic probes showed that the addition of ash has little influence on the ceramic properties up to 1000 °C. X-ray diffraction and thermal analysis data showed that, above this temperature the ash participates in the sintering process and in the formation of new important phases. The results reported show that the reuse of SCBA in the ceramic industry is feasible.     

Impact Resistance of Materials for Guards on Cutting Machine Tools—Requirements in Future European Safety Standards

Guards on machine tools are meant to protect operators from injuries caused by tools, workpieces, and fragments hurled out of the machine’s working zone. This article presents the impact resistance requirements, which guards according to European safety standards for machine tools must satisfy. Based upon these standards the impact resistance of different guard materials was determined using cylindrical steel projectiles. Polycarbonate proves to be a suitable material for vision panels because of its high energy absorption capacity. The impact resistance of 8-mm thick polycarbonate is roughly equal to that of a 3-mm thick steel sheet Fe P01. The limited ageing stability, however, makes it necessary to protect poycarbonate against cooling lubricants by means of additional panes on both sides.