基于HMM-SVR的船舶动力设备故障模式识别与状态预测研究

船舶动力设备因故障监测信号样本少、变化缓慢且数据特征呈非线性,使得设备故障模式的准确识别和状态预测比较难。鉴于此,文章研究了基于隐马尔科夫模型的故障模式识别方法,利用该模型将微弱变化的信号特征转换为变化较大的对数似然概率对故障模式实现有效识别。在此基础上进一步提出基于HMM-SVR的设备状态预测模型,将遗传算法用于支持向量回归模型参数寻优,并结合隐马尔科夫模型,实现对设备状态的预测。对船用柴油机进行仿真,结果表明上述模型具有较高的识别率,能准确预测船舶动力设备的当前状态。     

Situation analysis forecasting: the case of European maritime clusters

Within the literature concerned with aspects of competitiveness, innovation and strategic management of industrial clusters, the body regarding forecasting of strategic management is still nascent. This work aspires to render a contribution within the domain of strategic management forecasting, through the indicative case of European maritime clusters. For this end, a two-tier model is formulated. A quantitative strengths, weaknesses, opportunities, and threats (SWOT) methodology that derives from the fusion of a quondam situation analysis and crosstabs’ theory is generated. This leads to the utilization of the crosstab’s conditional probabilities as transition probabilities; the latter are called to compile the transition matrix of a Markov chain. Through this methodology, and the successive Markov chain’s transition matrices, strategic forecasts are extracted for a devised European maritime cluster case. This work relinquishes a novel application with respect to strategic management forecasting, that provides a dichotomy of practical interpretations and scenarios for quantitative situation analysis. Thus, it may enable effective real-time decision-making for strategic management and/or policy drafting. The situation analysis forecasting model may find applicability in a plethora of practical and theoretical cases, wherein forecasting may be desirable. It may as well pertain to an intrinsic methodology for situation analysis forecasting of maritime clusters.     

基于支持向量机的多传感器船舶火灾探测技术

针对船舶火灾探测误报率高的情况,为提高火灾探测系统的可靠性,提出一种基于支持向量机的多传感器火灾信息融合方法。经过仿真试验证明,通过多传感器探测数据的有效融合,可以大幅提高火灾探测系统的火灾识别率。     

Short-term forecasting of high-speed rail demand: A hybrid approach combining ensemble empirical mode decomposition and gray support vector machine with real-world applications in China

Short-term forecasting of high-speed rail (HSR) passenger flow provides daily ridership estimates that account for day-to-day demand variations in the near future (e.g., next week, next month). It is one of the most critical tasks in high-speed passenger rail planning, operational decision-making and dynamic operation adjustment. An accurate short-term HSR demand prediction provides a basis for effective rail revenue management. In this paper, a hybrid short-term demand forecasting approach is developed by combining the ensemble empirical mode decomposition (EEMD) and grey support vector machine (GSVM) models. There are three steps in this hybrid forecasting approach: (i) decompose short-term passenger flow data with noises into a number of intrinsic mode functions (IMFs) and a trend term; (ii) predict each IMF using GSVM calibrated by the particle swarm optimization (PSO); (iii) reconstruct the refined IMF components to produce the final predicted daily HSR passenger flow, where the PSO is also applied to achieve the optimal refactoring combination. This innovative hybrid approach is demonstrated with three typical origin–destination pairs along the Wuhan-Guangzhou HSR in China. Mean absolute percentage errors of the EEMD-GSVM predictions using testing sets are 6.7%, 5.1% and 6.5%, respectively, which are much lower than those of two existing forecasting approaches (support vector machine and autoregressive integrated moving average). Application results indicate that the proposed hybrid forecasting approach performs well in terms of prediction accuracy and is especially suitable for short-term HSR passenger flow forecasting.     

基于支持向量机的装载机齿轮箱故障智能诊断研究

在分析现有齿轮箱故障诊断方法的基础上,提出了采用多分类器支持向量机齿轮箱故障智能诊断方法,简介了该方法的系统结构、实现原理、特征提取与故障类别,重点讨论了齿轮箱故障多分类器支持向量机智能诊断模型与算法。仿真试验结果说明了采用多分类器支持向量机智能方法进行齿轮箱故障智能诊断的可行性与正确性。     

基于Takens理论和SVM的滑坡位移预测

针对滑坡变形时序非线性,数据量少的特点,引入Takens理论,采用支持向量机(SVM)建立其预测模型,建模过程中,比较了由不同核函数获得的SVM模型的性能,同时将SVM与RBF、El-man神经网络模型进行外推7步预测试验比较。结果表明:RBF核函数具有更好的工程实用价值;在有限样本情况下,SVM预测模型具有更好的准确性和泛化性,其7步预测平均误差率控制在5%以内,可见该方法在滑坡变形预测方面极具潜力。     

预应力曲线箱梁和异形箱梁的研究

近年来 ,国内外学者对曲线箱梁和异形箱梁的静力分析理论和计算方法作过大量的研究 ,但这些理论和方法在某种程度上都存在着一定的局限性 ,特别是在实际设计工作中 ,运用起来不能得心应手。为此本文在综合前人已取得经验下 ,针对桥梁结构设计中分析曲线箱梁、异形箱梁 ,经常遇到的难题进行了研究 ,建立一个较为完善的理论和方法 ,编制了等参元空间分析程序。在实际工程中进行实桥试验 ,验证了本文理论和方法的正确性。本文的研究工作更准确描述了箱梁的荷载响应 ,为设计人员提供直观的设计依据。对曲线箱梁和异形箱梁受力特性有了更一步的理解 ,并提出了新的见解     

基于盲数理论的我国海上战略通道安全风险评价

对我国海上战略通道进行安全风险评价是保障海上通道安全的重要环节。由于海上战略通道的安全风险具有多种不确定性，故可运用盲数理论建立我国海上战略通道安全风险等级评价的盲数模型。通过专家打分的方法对影响因素进行未确知测度，构造判断矩阵获得影响因素的权重，从而得到模型的综合未确知测度，根据既定的评价准则获得海上通道的安全风险级别。文中对我国重要的海上通道马六甲海峡进行了安全风险评价，其评价结果为：马六甲海峡的安全级别为较危险级别，验证了该盲数模型的有效性。     

矢量型电子河道图岸线提取方法研究

为快速准确获取河道岸形线的数据,生成缺乏岸线数据资料的河道矢量型轮廓图,提出一种通过处理雷达图像获取矢量型电子河道图岸形线数据的方法。采用了数学形态学方法实施对雷达图像处理,主要的处理过程包括:雷达图像灰度处理,灰度雷达图像转变为二值图像,二值雷达图像的滤波处理,在以上处理过程的基础上构造了数学形态学结构元素,实施对河道岸线提取,并矢量化处理了离散点。在二值化过程中提出新的方法,针对雷达图像的特点,依据航路规则设计了特殊的滤波过程,提出了提取河道任意边缘的方法。     

一种基于乘性规则和支持向量域的水中目标识别分类器探讨

目标识别是水中设备智能化的关键技术之一.通过阐述支持向量域描述(SVDD)以及乘性规则(GA)的原理,提出基于乘性规则和支持向量域结合的方法对水中目标进行分类识别,对比SVM算法需要支持向量数多,运算速度慢的缺点,该方法能有效提高优化识别速度.