Estimation of daily sunshine duration using support vector machines

Although sunshine duration (SD) is one of the most frequently measured meteorological parameters, there is a lack of measurements in some parts of the world. Hence, it should be estimated accurately for areas where no reliable measurement is possible. The main objective of this study is to evaluate the potential of support vector machine (SVM) approach for estimating daily SD. For this purpose, three different kernels of SVM, such as linear, polynomial, and radial basis function (RBF), were used. Different combinations of five related meteorological parameters, namely cloud cover, maximum temperature (T_max), minimum temperature (T_min), relative humidity (RH), and wind speed (WS), and one astronomic parameter, day length, were considered as the inputs of the models, and the output was obtained as daily SD. Simulated values of the models were compared with ground measured values, and concluded that the usage of the SVM-RBF estimator with combination of all input attributes produced the best results. The coefficient of determination, root mean square error, and mean absolute error were found to be 0.8435, 1.5105 h, and 1.0771 h, respectively, for the pooled four-year daily data set of 14 stations in Turkey. It was also deduced that accuracy increased as the number of attributes increased and the major contribution to this came from RH as compared with T_max, T_min, and WS. This study has shown that the SVM methodology can be a good alternative for conventional and artificial neural network methods for estimating daily SD.     

雾霾天气预测中支持向量机的应用分析

支持向量机在对非线性复杂问题进行处理的过程中,展现出来的优势特征非常突出,本文针对雾霾天气预测中支持向量机的应用做出了进一步探究,对支持向量机的概念、支持向量机的基本思想、建立雾霾预测模型、预测试验给出了详细的分析。     

Understanding crashes involving roadway objects with SHRP 2 naturalistic driving study data

Introduction: Crashes involving roadway objects and animals can cause severe injuries and property damages and are a major concern for the traveling public, state transportation agencies, and the automotive industry. This project involved an in-depth investigation of such crashes based on the second Strategic Highway Research Program (SHRP 2) Naturalistic Driving Study (NDS) data including detailed information and videos about 2,689 events. Methods: The research team conducted a variety of logistic regression analyses, complemented by Support Vector Machine (SVM) analyses and detailed case studies. Results: The logistic regression results indicated that driver behavior/errors, involvement of secondary tasks, roadway characteristics, lighting condition, and pavement surface condition are among the factors that contributed significantly to the occurrence and/or increased severity outcomes of crashes involving roadway objects and animals. Among these factors, improper turning movements (odds ratio = 88), avoiding animal or other vehicle (odds ratio = 38), and reaching/moving object in vehicle (odds ratio = 29) particularly increased the odds of crash occurrence. Factors such as open country roadways, sign/signal violation, unfamiliar with roadway, fatigue/drowsiness, and speeding significantly increased the severity outcomes when such crashes occurred. The sensitivity analysis of the three SVM classifiers confirmed that driver behavior/errors, critical speed, struck object type, and reaction time were major factors affecting the occurrence and severity outcomes of events involving roadway objects and animals. Practical Applications: The study provides insights on risk factors influencing safety events involving roadway objects, including their occurrence and the severity outcomes. The findings allow researchers and traffic engineers to better understand the causes of such crashes and therefore develop more effective roadway- and vehicle- based countermeasures.     

中国工业化、城市化进程中的能源需求预测与分析

为了取得可靠的能源需求预测,本文引入工业化、城市化等重要因素,利用支持向量回归机在时间序列预测中的优势,确定了输入向量集合和输出向量集合,建立基于支持向量回归机能源需求预测模型.将我国1985-2009年能源需求相关数据进行模拟与仿真,并对中国2010-2020年能源需求量进行预测,并模拟解释变量不同增长率下能源需求的演变并给出政策选择.研究结果表明,中国高速的经济增长以及工业化和城市化的发展对能源需求影响很大,到2020年能源需求将达到45.3亿t标准煤,而且经济增长速度越快对能源需求就越大.变量模拟得出的结论是产业结构也是能源需求重要影响因素之一,工业结构的调整,即便是微调,也会对能源需求有很大的抑制作用;中国城市化进程以及城市化发展阶段所表现出的工业化特征,推动了能源需求快速增长,城市化率越高对能源需求越大,且对能源需求是刚性的,城市化也是能源需求重要影响因素之一.     

基于支持向量机的飞行安全隐患危险性评价

提出了基于支持向量机的飞行安全隐患危险性评价方法,建立了支持向量机模型。并以飞行安全隐患危险性评价的基本要素为输入节点,以评价结果作为输出节点,对空军某部的飞行安全状况进行了评价。结果表明:对于飞行安全隐患危险性评价问题,支持向量机方法较传统神经网络方法精度更高,速度更快,实际应用中也更易于实现。     

基于GWO-VMD算法的齿轮故障自适应特征提取

目的 齿轮产生故障时,利用其声发射信号进行自适应特征提取后诊断。方法 利用变分模态分解方法（VMD）对齿轮发生故障时的声发射信号进行分解。在现实状况中,采集声发射原信号噪声干扰大,导致特征提取准确度低,并且模态分解时参数需要人为调试设定。鉴于此,引入灰狼优化算法（GWO）,对模态分解个数k和二次惩罚因子α自适应选择最优参数后,对信号分解得到本征模态函数（IMF）。通过相关系数选出最佳IMF作为特征分量,计算其峭度和样本熵。结果 计算了各分量的相关系数,选取与原始信号最为相近的分量,分别计算其峭度和样本熵。分解后,齿轮故障声发射信号峭度高于正常的情况,而样本熵则偶然性表现为正常情况下的值大于故障条件下的值。结论 采用支持向量机对特征向量集进行分类识别,对比改进后的试验结果,GWO-VMD结合峭度–样本熵的方法能够有效地提取故障特征,判断齿轮状态是否健康。     

基于优化算法的弹药贮存寿命预测方法

目的 实现对缺失及不足的制导弹药贮存失效数据预测及补充的能力。方法 首先通过4种不同的预测算法（GA-BP、PSO-BP、GA-SVM、PSO-SVM）,对自然贮存条件下弹药贮存失效数据进行预测,其次根据最小二乘拟合法,实现弹药贮存寿命评估模型的构建,再通过寿命评估模型,计算出不同方法下对应的贮存寿命。结果 通过不同模型的构建,4种预测方法与无优化条件下均能实现弹药贮存失效数据的预测,并且在规定可靠度,GA-BP和PSO-BP预测精度比另外2种方法更低。结论 GA-SVM与PSO-SVM更适合弹药贮存失效数据的预测,且效果更好。     

基于矢栅混合数据模型的土地适宜性评价研究

土地适宜性评价一般为单独基于栅格数据模型或者单独基于矢量数据模型。单一的数据类型在进行土地适宜性评价时对信息的表达难免存在不足。结合面向对象的思想,以土地评价的对象个体为评价单元,利用矢量数据的评价单元边界来分割各类因子作用分值数据,并将评价单元对象内数据统计分析后的结果通过栅格图斑标号对象的联接,入库作为评价单元该因子的作用分值,再根据确定的各因子权重,计算因子的综合评价分值来建立矢量栅格混合数据模型。在此基础上实现了算法,并以浙江省标准农田建设为例,在标准农田立地条件评价中进行了试验。试验结果表明,提出的矢栅混合数据模型能够较为全面地反映地块的各方面要素信息,保证了土地适宜性评价的准确性,并为土地适宜性评价的数据混合提供了一种新的思路。     

基于生理指标的建筑工人攀登作业疲劳实验研究

为研究攀登作业建筑工人生理疲劳状态的评测指标,提出1种基于生理指标的建筑工人攀登作业疲劳测度实验方法。首先,设计实验测量建筑工人的心率、皮肤温度、舒张压、收缩压4项生理指标,结合Brog’s RPE主观疲劳程度量表研究建筑工人生理疲劳的变化;其次,提取上述4项指标的平均值和标准差作为生理指标特征值,利用静息状态下生理指标特征值和疲劳状态下生理指标特征值进行方差分析、球形检验、T检验筛选出与疲劳相关的特征值;最后,利用支持向量机构建疲劳检测模型。研究结果表明：上述8项生理指标特征值与攀登作业工人疲劳具有显著相关性,疲劳检测模型的准确率为96.875%,研究结果可对攀登作业人员疲劳评估和疲劳预警具有实践性意义。     

PCA-SVR在煤层瓦斯含量预测中的应用

针对煤层瓦斯含量与其影响因素之间存在着复杂的非线性关系,建立了基于主成分分析和支持向量回归机的煤层瓦斯含量预测模型。该模型有效地解决了小样本、非线性预测的问题,并发挥了主成分分析法消除输入变量间相关性的优点,减少了输入变量个数,提高了预测精度和收敛速度。通过实证分析,该模型的预测精度高,能够直接用于煤矿现场预测煤层瓦斯含量。