基于符号有向图的汽车涡轮增压系统故障诊断

基于符号有向图SDG(Signed Directed Graph)的传统故障诊断方法融入了定量推理的方法,提高了诊断精度,然而对不可测节点的处理大多采取等效删除以及假设状态信息扩展有效节点的方法,容易引起信息丢失和诊断效率低下的问题.结合汽车涡轮增压系统诊断实例,针对含有不可测节点的故障传播路径,提出引入模糊聚类的方法...     

生态公路模糊综合评价理论研究

以《公路建设项目环境影响评价规范》为依据,建立了完善的生态公路环境影响评价指标体系,将定性指标按照有关规则定量化,然后将定量指标转化为百分制分数来量度,最终建立评价模型对生态公路建设项目的环境影响做出定量的评估。提出了基于模糊数学原理的生态公路环境影响模糊综合评价法,并形成了一套对道路全线环境影响定量评价方法理论,其具体过程采用实例加以介绍。     

一种基于模糊神经网络的交通方式划分模型

模糊神经网络具有良好的模式分类能力，而交通方式划分问题本质上也是一个模式分类问题。文章利用模糊神经网络方法对交通方式划分问题进行了建模，通过对FNN和BP神经网络（BPNN）方法运算结果的比较分析。证实模糊神经网络具有收敛速度快、精度高等优点：是模式划分问题的一种实用方法。     

Ship selection using a multiple-criteria synthesis approach

A method is presented for selecting a preferred ship from a group of candidates as a reference ship for a new design. The method is based on a recently developed approach for multiple-criteria decision analysis under uncertainty, the evidential reasoning approach. Using this method, both quantitative and qualitative attributes of a complicated nature can be considered in the selection process. The method consists of three phases: identifying suitable candidate ships, evaluating them in terms of both conventional techno-economical and qualitative attributes, and aggregating all the attributes using the evidential reasoning approach. This three-phase procedure is illustrated by means of an oil tanker selection example. The results of this study show that the evidential reasoning approach can support multiple-criteria ship selection processes when both qualitative and quantitative information with or without uncertainties have to be taken into account. The outcomes generated by the method include the ranking of the candidate ships and indications of their strengths and weaknesses in the format of performance distributions over different assessment grades. Such information is vital in helping decision makers to make an informed selection and be aware of any risk implication associated with the selection.     

汽车方案设计智能决策支持系统

从汽车整体设计的需要出发,分析了汽车总体方案设计的特点。介绍了一种智能化方案设计推理决策系统,该系统是在一个面向对象的数据库管理系统基础上开发的。在ACDIDSS中,问题求解主要采用基于实例的推理,辅之以基于规则的推理模式。论述了ACDIDSS系统的设计思想和各个主要模块的功能,并重点介绍了实例推进器的设计与实现。     

基于模糊专家系统的雷达干扰资源分配模型

在对目标信息进行综合利用的基础上,针对现代海战特点,建立了基于模糊专家系统的雷达干扰资源分配模型,详细地阐述了舰艇雷达干扰系统的知识表示和知识库构建方法,简要介绍了推理策略,充分利用专家经验,体现了定性分析与定量计算的特点。该研究对未来海战中干扰资源的分配决策具有一定的指导意义。     

基于BP神经网络的故障诊断技术在装备维修中的应用

传统故障诊断方法在装备保障中的诸多局限性。文章介绍了基于BP模型的神经网络,研究了基于BP模型神经网络的故障诊断推理方法,并利用Matlab仿真软件对结果进行了运行和计算。结果证明,基于BP神经网络的故障诊断技术对装备故障诊断是行之有效的。     

A Comparative Study of Three Machine Learning Methods for Software Fault Prediction

The contribution of this paper is comparing three popular machine learning methods for software fault prediction. They are classification tree, neural network and case-based reasoning. First, three different classifiers are built based on these three different approaches. Second, the three different classifiers utilize the same product metrics as predictor variables to identify the fault-prone components. Third, the predicting results are compared on two aspects, how good prediction capabilities these models are, and how the models support understanding a process represented by the data.     

公路隧道地质信息系统及其应用

工程地质是隧道施工的重要依据,由于公路隧道地质数据类型多、数据量庞大,所以开发隧道地质信息系统是必要的.在系统分析的基础上,以VB.net作为前台开发程序,用Access建立后台数据库,以ADO作为数据传输通道,开发了公路隧道地质信息系统.将该系统应用于沪蓉西高速公路王子石隧道的围岩定性分析上,大大提高了工作效率与围岩定性分析精度.     

桥梁智能CAD系统中的类比技术研究

首先分析了工程设计的实现,然后以工程设计过程的理论模型－规划控制下的二阶段设计模型为理论依据,讨论了桥梁数据结构的设计方法,并制定了相应的类比推理模型。