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.     

基于机器学习和非参数估计的PM2.5风险评估

为开展区域风险评估,融合手机信令、气象和地理信息等多源数据,引入随机森林机器学习、非参数估计分位数图示法和非监督学习K-mean等方法,构建了区域PM_2.5风险评估及特征识别评价框架,在南京市区以0.3km分辨率网格为基础单元开展了案例研究.结果表明,该技术既可有效模拟PM_2.5浓度时空分布,十折交叉验证R²达到0.76,证明了准确度较高,并基于此识别出4种主要污染特征;也可有效捕捉短期人口流动导致的风险,在污染浓度不变的情况下短期人口流动会导致风险增加0.30~0.97倍.综合PM_2.5浓度和人口分布,识别出4种主要暴露风险模式,其中,研究区域6.5%的面积为高风险地区,23.0%的面积为低风险地区.“十四五”期间应加快现代科学技术在环境保护领域的应用,实施网格化和差异化的风险控制政策,维护人群健康.     

大气环境分类的SVM联合决策方法

目的实现城市大气环境的精准快速归类预测。方法基于支持向量机(SVM)构建多分类问题的联合决策算法,将大量城市环境因素数据的主成分聚类结果作为输入,通过机器学习训练,组建大气环境的SVM联合决策模型。结果该模型根据大气环境因素将数据集91个城市划分为9类,其中河内与海防环境相似度最高,巴东与格尔木差异最大。9个SVM二分类器组建的联合决策模型通过逐点预测在主成分数据空间形成了分区预测云图。结论SVM联合决策模型可实现城市环境的快速分类辨识,分类预测结果精度高于95%。     

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.     

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.     

Evaluation and Optimization of Handle Design Parameters of a Grass Trimming Machine

The grass trimming machine is a widely used agricultural machine for cutting grass by the roadside and in other areas in Malaysia. Hand-arm vibration (HAV) syndrome is very common among workers operating power tools and performing similar work for extended periods. Grass trimming involves the use of a motorized cutter spinning at high speed, resulting in high levels of HAV among its operators. The existing D-shape handle causes HAV-related stress and operational load in operators. This research proposes a new design of a handle of the grass trimming machine. When this new design was compared with the old one, it was found that the new handle resulted in 18% lower HAV. To find the lowest HAV, 3 critical parameters of the new handle (length, angle and material of the cap of the handle) were optimized using the Taguchi quality tool. Appropriately selected parameters of the new handle significantly reduced the occurrence of HAV among grass trimmers.