基于数据挖掘算法的网络入侵检测系统研究

回顾了当前入侵检测技术和数据挖掘技术,分析了Snort网络入侵检测系统存在的问题,重点研究了数据挖掘中的关联算法Apriori算法和聚类算法K一均值算法;在Snort入侵检测系统的基础上,增加了正常行为挖掘模块、异常检测模块和新规则生成模块,构建了基于数据挖掘技术的网络入侵检测系统模型。新模型能够有效地检测新的入侵行为,而且提高了系统的检测效率。     

基于免疫模型的故障诊断方法及应用

提出一种基于人工免疫模型的故障诊断方法。根据免疫系统机理构建模型框架,模拟T细胞和B细胞功用,分别设计模型中的T模块和B模块。T模块采用实向量阴性选择算法生成异常检测器,完成系统的异常状态检测;B模块响应系统实际状态,运用聚类原理动态进化,形成告警信息反馈至T模块。2个模块相互作用,共同实现系统状态的在线实时检测。应用结果表明,该模型具有正确性和有 效性。     

MATLAB/SIMULINK通用异步电机模型的分析与应用

详细介绍了MATLAB/SIMULINK中异步电机模块所用模型及其实现细节,分析了该模型的优缺点,并用该模块构建了一个简洁三电平直接转矩控制仿真系统。仿真结果验证了仿真系统的正确性。     

三维城市道路仿真模型构建

通过对现有城市道路模型的分析,提出了使用ArcGIS软件构建三维城市道路仿真模型。构造了道路几何网络模块、交通检测模块和控制管理设施模块的二维和三维模型。重点介绍了交叉口节点的二维模型建立,以及基于数字高程图得到城市道路的三维模型。最后将该模型应用于微观交通仿真系统中,可以为仿真系统中其它仿真模型提供空间参照、几何模型和逻辑模型,为各类交通行为数学模型提供存储空间和作用空间,为各种程序算法提供调度接口。与其它道路模型比,该模型能更准确、细致地反映道路网的拓扑关系和道路几何条件,从而为交通仿真模型真实地反映路网交通状态奠定了基础。     

基于人机交互增强算法的英语机器翻译系统设计

针对传统系统在英语机器翻译中的功能和性能难以满足交互性需求的问题,本研究设计了一种基于人机交互增强算法的英语机器翻译系统。在设计系统总体架构的基础上,通过设计服务器和翻译器完成对硬件结构的设计。在软件设计中,利用增强算法分析了人机交互中输入英语语句的语义特征,根据分析结果设计解码算法,并构建英语机器翻译模型。系统测试结果表明：该系统中,会话模块和对话模块的功能都满足交互性设计的要求,其能够有效提高英语机器翻译的质量。     

基于FPGA的视频预处理系统的建模与仿真

为了提高基于FPGA的视频处理效果,降低FPGA处理视频的开发难度,结合使用开发工具System Generator和Accel-DSP,对基于IP的系统开发方法进行了研究,构建了一种视频预处理系统模型。利用双线性插值算法进行Bayer格式图像的彩色还原,通过中值滤波器模块降低图像噪声,来提高图像整体画质。研究基于FPGA的DSP开发新方法,利用已有模块和AccelDSP开发的新模块,系统地设计整个模块。最后,以实例展示了基于System Generator的模型,验证了该方法的可行性和有效性。     

基于改进多目标狼群算法的微电网调度优化

为获得微电网系统建设成本、环境成本和运行成本的多重目标优化,以构建系统独立运行模块和仿真模块为核心,设计了微电网系统的多目标调度模型。使用能量模块对微电网调度模型的建设成本、环境成本和运行成本指标进行评价,优化调度算法模块则使用基于个体密度多目标狼群算法(Multi-objective wolf colony algorithm,MOWCA)。在MOWCA算法中引入了非支配排序和个体密度多样性保持操作,有效提高了多目标优化的前沿分布多样性和收敛精度。将所提优化调度算法基于Docker容器技术,对风柴蓄光微电网系统进行调度优化模拟,验证了所提调度算法在多重目标优化上的有效性。     

基于最大熵的汉语人名识别方法研究

本文针对人名的特点,建立了特征模板,并在此基础上提取了特征集,利用特征选择算法提取了有效特征,并建立了一个基于最大熵的人名识别模型。基于最大熵模型,探索性地构建了一个人名识别的系统,取得了较好的效果。该系统将潜在人名发现和使用最大熵模型进行标注两个阶段的工作有机地结合到一起。较好地解决了人名竞争问题;并对重点模块的算法进行了详细描述。     

一种基于统计思想的网格负载平衡调度算法

针对层次化网格模型结构,运用统计思想提出了一种新的资源分配与任务调度算法,不仅能够提高资源的利用率和系统的吞吐率,而且能够实现网格系统内部的负载平衡。算法主要包含三个功能模块,即负载跟踪模块、作业分配模块和负载监视模块。在解释了方案中各功能部件的作用及其相互之间关系的基础上,给出了相应的算法伪码。仿真实验表明,该算法是有效的。     

基于ARM的分布式电源接入容量均衡控制系统

以控制分布式电源接入容量以及容量均衡为目的,设计一种基于ARM的分布式电源接入容量均衡控制系统。系统由上位机显示模块、ARM控制模块、下位机检测模块、均衡控制模块、保护报警模块等组成,采用以ARM Cortex-M3内核为核心的EXP-LM3S811 ARM微控制器,以实现分布式电源数据采集、自动保护、温度与下位机容量的均衡控制。构建最优接入容量计算模型,利用萤火虫算法对该模型进行求解,根据最优接入容量计算结果,利用均衡控制模块动态均衡控制分布式电源接入容量。应用结果显示,该系统信息传输误差和最优接入容量计算误差分别低于5μrad和0.5%,说明该系统可显著提升分布式电源接入容量均衡性,具有较强的实际应用价值。     

工艺规则知识管理系统的研究与开发

本文重点阐述了工艺规则知识管理系统的研究与开发原理,论述了通用的基于关系数据库的工艺决策知识模型构建方法。提出了工艺决策产生式规则表示方法,摒弃了传统的利用固定加工方法或加工规则设计数据库字段的方法,有效地保证了系统的通用性和移植性。     

Automatic feature extraction of waveform signals for in-process diagnostic performance improvement

In this paper, a new methodology is presented for developing a diagnostic system using waveform signals with limited or with no prior fault information. The key issues studied in this paper are automatic fault detection, optimal feature extraction, optimal feature subset selection, and diagnostic performance assessment. By using this methodology, a diagnostic system can be developed and its performance is continuously improved as the knowledge of process faults is automatically accumulated during production. As a real example, the tonnage signal analysis for stamping process monitoring is provided to demonstrate the implementation of this methodology.     

制造执行系统的生产管理控制研究

车间调度是制造执行系统生产管理控制的核心功能,因此制造执行系统必须实现车间的优化调度。文章分析了制造执行系统的生产管理控制方法,提出了制造执行系统的车间调度方法。一个已在某航天制造企业使用的制造执行系统软件证实了制造执行系统的生产管理控制方法的正确性。     

税务信息系统风险分析方法研究*

研究了税务信息系统的风险分析方法.首先识别对象系统的特征;然后给出完整的基于矩阵的相对量化风险分析方法和步骤;最后以陕西省国家税务局信息系统为实例,得到对象系统的风险分析结果.     

Object-oriented specification of automated manufacturing systems

The design of automated manufacturing systems (AMSs) requires an effective system specification that helps designers to deal with the changes in system requirements. This paper presents an object-oriented rule-based methodology for the specification of AMSs, which extends the capability of the existing object-oriented specification methods to support system integration and the explicit representation of control policies. The methodology is characterised by the use of rule-based modelling techniques to specify object behaviours in terms of processes. The application of the methodology is illustrated by the specification of a flexible manufacturing system.     

Robust Neural Network Motion Tracking Control of Piezoelectric Actuation Systems for Micro/Nanomanipulation

This paper presents a robust neural network motion tracking control methodology for piezoelectric actuation systems employed in micro/nanomanipulation. This control methodology is proposed for tracking of desired motion trajectories in the presence of unknown system parameters, nonlinearities including the hysteresis effect and external disturbances in the control systems. In this paper, the related control issues are investigated, and a control methodology is established including the neural networks and a sliding control scheme. In particular, the radial basis function (RBF) neural networks are chosen for function approximations. The stability of the closed-loop system, as well as the convergence of the position and velocity tracking errors to zero, is assured by the control methodology in the presence of the aforementioned conditions. An offline learning procedure is also proposed for the improvement of the motion tracking performance. Precise tracking results of the proposed control methodology for a desired motion trajectory are demonstrated in the experimental study. With such a motion tracking capability, the proposed control methodology promises the realization of high-performance piezoelectric actuated micro/nanomanipulation systems.      

航空航天数字博物馆系统的设计与实现

提出了一种数字博物馆系统设计与实现的方法。该系统对现有的数字化藏品进行标准化，并且进行统一管理，使这些藏品能够以多种方式得以在线展示，令用户得到数字博物馆的各种交互体验。该系统目前应用于教育部大学数字博物馆二期建设中的航空航天数字博物馆，实验结果证明已经达到了预期的良好效果。     

Methodology for quantitative evaluation and selection of complex systems

In this paper a methodology is developed for quantitative evaluation and selection of complex systems satisfying the desired specifications. The proposed methodology is based on the development of a figure of merit combining both problem and system specifications and permitting the evaluation and selection of the most appropriate system from a set of candidate systems suitable for a wide range of applications for which the system can be used. A case study is investigated showing the validity of the developed methodology.     

Specification and analysis of real-time systems with PARAGON

This paper describes a methodology for the specification and analysis of distributed real-time systems using the toolset called PARAGON. PARAGON is based on the Communicating Shared Resources paradigm, which allows a real-time system to be modeled as a set of communicating processes that compete for shared resources. PARAGON supports both visual and textual languages for describing real-time systems. It offers automatic analysis based on state space exploration as well as user-directed simulation. Our experience with using PARAGON in several case studies resulted in a methodology that includes design patterns and abstraction heuristics, as well as an overall process. This paper briefly overviews the communicating shared resource paradigm and its toolset PARAGON, including the textual and visual specification languages. The paper then describes our methodology with special emphasis on heuristics that can be used in PARAGON to reduce the state space. To illustrate the methodology, we use examples from a real-life system case study. This revised version was published online in June 2006 with corrections to the Cover Date.     

The application of the methodology for secure cyber–physical systems design to improve the semi-natural model of the railway infrastructure

The paper suggests a new methodology for secure cyber–physical systems design. The proposed methodology consists of two main cycles. The main goal of the first cycle is in design of the system model, while the second one is about development of the system prototype. The key idea of the methodology is in providing of the most rational solutions that are improving the security of cyber–physical systems. Such solutions are called alternatives and built according to functional requirements and non-functional limitations to the system. Each cycle of the methodology consists of the verification process and seven stages that are associated with the used cyber–physical system model. The objective of the verification process is in checking of constructed models and prototypes in terms of their correctness and compatibility. The model represents cyber–physical systems as sets of building blocks with network between them, takes elements internal structure into account and allows direct and reverse transformations. The novelty of the suggested methodology is in the combination of design, development and verification techniques within a single approach. To provide an example of the design methodology application, in this paper it is used to improve the semi-natural model of the railway infrastructure.