基于Multi-class SVM的车辆换道行为识别模型研究

自动安全换道是车辆实现无人驾驶的关键,为精确识别行驶车辆换道状态,保证行车安全,设计了一种基于多分类支持向量机(Multi-class Support Vector Machine,Multiclass SVM)的车辆换道识别模型。从NGSIM数据集中选取美国101公路车辆轨迹数据进行分类处理,并将车辆换道过程划分为车辆跟驰阶段、车辆换道准备阶段和车辆换道执行阶段。采用网格搜索结合粒子群优化算法(Grid Search-PSO)对SVM模型中惩罚参数C和核参数g进行寻优标定,利用多分类支持向量机换道识别模型对样本数据进行训练和测试,模型测试精度达97.68%。研究表明,模型能够很好地识别车辆在换道过程中的行为状态,为车辆换道阶段的研究提供支持。     

矿井突水水源识别的RS-LSSVM模型

为了对矿井突水水源进行准确、高效的判别,综合考虑水化学特征,选取Ca~(2+),Mg~(2+),K~++Na~+,HCO-3,SO2-4,Cl~-和总硬度7个指标的质量浓度(mg/L)作为矿井突水水源的最初判别指标。利用粗糙集(RS)理论的属性约简来筛选水化学特征指标,用以作为水源识别的核心判别指标,建立基于RS的矿井突水水源识别的最小二乘支持向量机(LSSVM)模型。选用约简处理后的13组煤矿数据对模型进行训练,再用训练好的模型对另外12组突水数据进行水源判别,并与未进行属性约简的LSSVM模型及Fisher判别分析法、随机森林方法进行对比。结果表明,利用属性约简方法可以很好地排除原始数据中的冗余信息干扰,因而能有效判别矿井突水水源,使矿井突水水源模型的误判率降低至0;而且指标约简过程可以降低LSSVM运算的复杂度,也能够提高判别效率。     

基于灰色支持向量机组合模型的我国火电NOx排放量预测

区域火电NO_x排放量的预测属于小样本、贫信息的灰色系统. 由于NO_x排放量受多个因素的叠加性影响,单一预测模型难以准确反映NO_x排放量的复杂变化,易产生较大的预测误差. 基于此,利用灰色预测理论和支持向量机预测理论,建立了火电NO_x排放量组合优化预测模型. 采用国家权威部门发布的火电NO_x排放量数据,综合考虑影响我国火电NO_x排放量的主要因素,对我国2008—2010年以及2020年的火电NO_x排放量进行了预测,预测结果与官方公布的实际值基本一致; 同时,预测的时间大大缩短.      

基于基团贡献法的有机化合物好氧生物降解预测模型研究

从MITI-Ⅰ试验中筛选出587种不同类型有机化合物的可用数据,通过对这些物质的结构进行拆分,随机选择其中50种化合物作为验证集,另外537种作为训练集,利用多元线性回归(MLR)和支持向量机(SVM)2种计算方法分别建立模型。结果表明,芳香酸、醛、芳香碘和叔胺等功能基团对有机化合物的好氧生物降解性影响较大;MLR模型总体预测正确率为81.43%,验证集正确率为82%,SVM模型总体预测正确率为87.90%,验证集正确率为86%。所建立的2种定量结构与生物降解性关系(QSBR)模型有效,可用于化学品的好氧生物降解性评价。     

安全带整体静负荷试验机的研制及应用

安全带是有效地预防高处作业人员因意外坠落而受到身体伤害的必要防护装备。本文根据GB6095—2009《安全带》、GB／T6096—2009《安全带测试方法》标准中安全带整体静态负荷试验的要求,对安全带整体静负荷试验机的研制与应用开展一些调研和探讨,希望对从事安全带检验的机构和安全带生产的企业中的科研、检验人员提供一些感性的认知和帮助。     

多类支持向量机在煤矿安全评价中的应用研究

针对矿井子系统诸多、环境复杂、影响因素多变和在现实条件下难以获得大量煤矿样本的情况,提出将对非线性、小样本问题有较高处理能力的支持向量机理论引入到机制评价中,并在归纳了支持向量分类机从一对多到一对一再到决策树模式的多渠道多层次分类原理基础上,建立了基于多分类支持向量机原理的煤矿安全多层次评价模型,同时通过提取影响煤矿安全因素的特征参数,引人类权重因子和样本权重因子,较好地解决了训练样本类别数量不平衡、数据干扰导致的错分问题,实现了对煤矿安全较高准确率和较高效率的评价.     

Integrated leakage detection and localization model for gas pipelines based on the acoustic wave method

With the development of natural gas transportation systems, major accidents can result from internal gas leaks in pipelines that transport high-pressure gases. Leaks in pipelines that carry natural gas result in enormous financial loss to the industry and affect public health. Hence, leak detection and localization is a major concern for researchers studying pipeline systems. To ensure the safety and improve the efficiency of pipeline emergency repair, a high-pressure and long-distance circular pipe leakage simulation platform is designed and established by similarity analysis with a field transmission pipeline, and an integrated leakage detection and localization model for gas pipelines is proposed. Given that the spread velocity of acoustic waves in pipelines is related to the properties of the medium, such as pressure, density, specific heat, and so on, this paper proposes a modified acoustic velocity and location formula. An improved wavelet double-threshold de-noising optimization method is also proposed to address the original acoustic wave signal collected by the test platform. Finally, the least squares support vector machine (LS-SVM) method is applied to determine the leakage degree and operation condition. Experimental results show that the integrated model can enhance the accuracy and precision of pipeline leakage detection and localization.     

煤与瓦斯突出预测的QGA-LSSVM模型

为快速、有效地对煤与瓦斯突出类型作出预测,运用灰色关联和因子分析模型对所选主要的判别指标进行分析提取,利用量子遗传算法(QGA)对最小二乘支持向量机(LSSVM)的参数作寻优处理,最终建立QGA-LSSVM煤与瓦斯突出预测模型。选取从砚石台矿区历史实测的数据,以96∶20的比例对该模型进行训练与测试,并将预测结果与其他预测模型的预测效果进行了比较。研究结果表明:对判别指标进行灰色关联分析可以有效去除对煤与瓦斯突出影响作用小的指标;用因子分析进行公共因子提取,可以有效减少数据信息冗余;利用QGA优化的LSSVM模型能使结果避免陷入局部最优解,用该模型可以有效预测煤与瓦斯突出类型,误判率为0。     

An analytical investigation on energy efficiency of high-speed dry-cutting CNC hobbing machines

Abstract

Energy efficiency analysis has been recognised as an effective measure for the energy prediction, energy assessment and energy benchmarking in the machining system. However, study on energy efficiency of CNC hobbing machines, especially high-speed, dry-cutting CNC hobbing machines (HSDC-CHM), is still scarce. The energy consumption by HSDC-CHM is generally considered larger, and energy efficiency lower, than wet-cutting CNC hobbing machines (WC-CHM). Therefore, this paper summarises the investigation of energy efficiency of HSDC-CHM and establishes energy efficiency models of CNC hobbing machines. Energy efficiency of HSDC-CHM and WC-CHM are compared and analysed based on energy efficiency models established. Through the theory analysis, results show that, in the production line, although HSDC-CHM possess larger transient energy consumption, its energy efficiency is higher than energy efficiency of WC-CHM. Moreover, it is difficult to obtain quantitative energy efficiency of two types of hobbing machines due to massive relevant hard-to-acquire parameters using energy efficiency models; for this reason, experiments are performed to compare and analyse energy efficiency of HSDC-CHM and WC-CHM. The experiments results indicate that energy efficiency of HSDC-CHM is excellent and far higher than WC-CHM. The study results have a positive significance for the development and application of HSDC-CHM.     

2种基于模式识别的环状燃气管网泄漏检测方法

为了将模式识别技术应用于环状燃气管网泄漏检测并找到合适的特征提取方法,以天津城建大学实验室环状燃气管网泄漏为例,将实验的28种工况作为测试样本,与之对应的模拟工况作为训练样本,采用提取压力图像特征向量法和节点压力矩阵法分别进行环状燃气管网的泄漏检测,采用支持向量机分类器将2种方法获得的特征向量进行训练与分类检验,进而将其分类准确率进行对比分析。研究结果表明:该2种方法均可用于环状燃气管网泄漏检测,提取压力图像特征向量法因有效地降低了特征向量的维度和数据波动的干扰,其结果更优。结合SCADA和GIS系统,可将该法应用于实际水、气、油管网泄漏检测和定位,有助于降低成本,提高检测效果。