Knowledge and strategies in diagnostic skill

A theoretical framework for diagnosis in technical environments is presented, consisting of three layers. At the first layer, the task structure, top-level goals of the diagnostic tasks are identified that have to be fulfilled during task execution. This task structure may also be viewed as a global strategy to carry out the diagnostic task. The second layer of knowledge consists of the relevant local strategies by means of which values are obtained for goals in the task structure. The third layer consists of underlying domain knowledge. This theoretical framework is used to interpret the results as presented in the literature on diagnosis in technical environments. Finally, based on this framework, recommendations are made with respect to the training of diagnostic skill.     

智能教学中的知识模型与教学评价的研究

目前,基于Web的智能教学系院是计算机应用于教育领域的研究方向之一。本文从知识点及其关系出发构建一个知识网络模型,并基于该模型介绍如何进行领域知识表示及考核试题设置,然后设计了试题难度系数的动态更新方法,还提出一种简捷的知识诊断方法,准确地将学生学习缺陷定位到具体的知识点,得出学习路径方面的建议,从而增强了教学的针对性。     

Patterns for context-based knowledge fusion in decision support systems

The here presented research focuses on the context-based knowledge fusion patterns. Patterns are discovered based on an analysis and investigation of knowledge fusion processes in a context aware decision support system at the operational stage of the system functioning. At this stage the context-based knowledge fusion processes are manifested around the context. The patterns are generalized in regard to the following three aspects: (1) the effects that the knowledge fusion processes produce in the system; (2) the preservation of internal structures for the context and multiple sources the information/knowledge is fused from; and (3) the preservation of multiple sources and the context autonomies. At that, seven knowledge fusion patterns have been discovered: simple fusion, extension, instantiated fusion, configured fusion, adaptation, flat fusion, and historical fusion.     

多尺度变换像素级医学图像融合：研究进展、应用和挑战

基于多尺度变换的像素级图像融合是计算机视觉领域的研究热点,广泛应用于医学图像处理等领域。本文对多尺度变换的像素级图像融合进行综述,阐述多尺度变换图像融合的基本原理和框架。在多尺度分解方面,以时间为序梳理了塔式分解、小波变换和多尺度几何分析方法的发展历程。在融合规则方面,围绕Piella框架和Zhang框架,讨论通用的像素级图像融合框架;在低频子带融合规则方面,总结基于像素、区域、模糊理论、稀疏表示和聚焦测度的5种融合规则;在高频子带融合规则方面,综述基于像素、边缘、区域、稀疏表示和神经网络的5种融合规则。总结12种跨模态医学图像融合方式,讨论该领域面临的主要挑战,并对未来的发展方向进行展望。本文系统梳理了多尺度变换像素级图像融合过程中的多尺度分解方法和融合规则,以及多尺度变换在医学图像融合中的应用,对多尺度变换像素级医学图像融合方法的研究具有积极的指导意义。     

专家系统中不确定性知识的表示和处理

知识表示和处理是专家系统的基本问题，不确定性知识的表示和处理一直是专家系统研究的热点。本文在阐述不确定性知识概念的基础上，简单介绍传统的不确定知识表示和处理方法，重点讨论近年来出现的新的不确定知识表示和处理方法。     

缺陷诊断专家系统的知识表达与推理技术

针对航空铝镁铸件缺陷分析的实际问题,基于规则的知识表达方式,运用正反向混合推理控制策略及确定性理论来处理知识的不确定性问题。采用TurboProlog人工智能语言,开发了铸件缺陷诊断专家系统软件。该文重点介绍了系统软件设计的知识表达、推理技术及系统软件的组成与功能。     

Knowledge granulation, knowledge entropy and knowledge uncertainty measure in ordered information systems

In this paper, concepts of knowledge granulation, knowledge entropy and knowledge uncertainty measure are given in ordered information systems, and some important properties of them are investigated. From these properties, it can be shown that these measures provides important approaches to measuring the discernibility ability of different knowledge in ordered information systems. And relationship between knowledge granulation, knowledge entropy and knowledge uncertainty measure are considered. As an application of knowledge granulation, we introduce definition of rough entropy of rough sets in ordered information systems. By an example, it is shown that the rough entropy of rough sets is more accurate than classical rough degree to measure the roughness of rough sets in ordered information systems.     

多信息融合电路故障诊断系统设计与开发

基于多源信息融合的电路故障诊断,当融合的信息源数目增加时,计算量变得越来越大,采用手工方式融合多源信息,具有劳动强度大、诊断结果准确率低等问题。针对这些问题,设计开发了基于信息融合的电路故障诊断系统。系统以MATLAB7.0和Microsoft Access 2003为开发工具,采用模块化设计思想,具有使用方便、稳定性好、通用性强、易扩展等特点。同时,给出了系统的体系结构及用到的融合算法流程图,并以一具体实验电路检测数据为对象,进行故障诊断,说明了系统的特点及功能。     

大型知识库知识存储结构的研究及其在知识发现系统中的应用

在基于数据库和知识库的知识发现系统(KDD&K)的研究中,需对知识库中的重复、冗余、矛盾、循环的知识进行实时校验、修改,并能够发现知识短缺,指导KDD过程进行聚焦;在KDK过程中,需要找出有关联的知识组成的知识域以便于归纳、解释等具体应用需求,针对于此,该文提出了一种基于知识节点(属性)的图矩阵、二维链表、产生式规则的三级管理模式和数据存储结构,通过知识库管理系统(KBMS)实现了二层逻辑结构和一层物理结构的三层独立映射关系,大大压缩了知识的搜索空间。经在KDD&K原型系统中的具体应用,该知识库系统结构的定义以及相应的KBMS完全满足上述要求,并可推广至通用的大、中型知识库系统。     

广义系统信息融合稳态与自校正满阶Kalman滤波器

基于线性最小方差标量加权融合算法和射影理论,对带多个传感器和带相关噪声的广义系统,提出了分布式标量加权融合稳态满阶Kalman滤波器.推得了任两个传感器子系统之间的稳态满阶滤波误差互协方差阵,其解可任选初值离线迭代计算.所提出的稳态融合滤波器避免了每时刻计算协方差阵和融合权重,减小了在线计算负担.当系统含有未知模型参数时,基于递推增广最小二乘算法和标量加权融合算法,提出了一种两段融合自校正状态滤波器.其中第1段融合获得未知参数的融合估计;第2段融合获得分布式自校正融合状态滤波器.与局部估计和加权平均融合估计相比,所提出的标量加权融合参数估计和自校正状态估计都具有更高的精度.仿真研究验证了其有效性.     

Decision fusion systems for fault detection and identification in industrial processes

Numerous fault detection and identification methods have been developed in recent years, whereas, each method works under its own assumption, which means a method works well in one condition may not provide a satisfactory performance in another condition. In this paper, we intend to design a fusion system by combining results of various methods. To increase the diversity among different methods, the resampling strategy is introduced as a data preprocessing step. A total of six conventionally used methods are selected for building the fusion system in this paper. Decisions generated from different models are combined together through the Dempster-Shafer evidence theory. Furthermore, to improve the computational efficiency and reliability of the fusion system, a new diversity measurement index named correlation coefficient is defined for model pruning in the fusion system. Fault detection and identification performances of the decision fusion system are evaluated through the Tennessee Eastman process.     

基于物联网和数据融合的空调故障诊断系统及方法*

针对传统的诊断方法模型难以精确建立的问题,设计了一种基于物联网和数据融合的空调故障诊断系统。首先提出了空调故障诊断系统的体系结构,对系统涉及的关键技术进行了介绍;然后给出了系统所采用的数据分析和综合诊断方法,并给出了系统的应用实例。该空调故障诊断系统可对空调设备的运行状态进行监控,通过对系统数据库中的数据分析、判断,采取相应的合理决策,实现对建筑用电设备物联网中的空调设备进行故障诊断的目的。     

Lagrange子流形理论在约束力学系统正则变换和勒让德变换中的应用

Lagrange方程与Hamilton方程之间的勒让德变换理论和Hamilton方程的正则变换理论在分析力学中具有重要的地位,从局域坐标的角度很难找到勒让德变换和正则变换之间的相关性. 本文主要基于辛流形的Lagrange子流形理论从全局上给出正则变换理论和勒让德变换理论的统一几何解释,进而在几何力学的角度清晰的描述Hamilton系统的正则变换和Lagrange方程与Hamilton方程之间的勒让德变换的几何结构.     

Knowledge hoarding and user acceptance of online discussion board systems in eLearning: A case study

This paper aims to reveal the determinants of the effectiveness of online discussion board systems (ODBSs) in eLearning environments to foster the interactions among the learners and/or instructors. A case in which an ODBS failed to foster the interactions among learners/instructors for knowledge sharing is introduced and hypotheses to explain the failure are developed based on thorough literature review in technology acceptance model (TAM) and knowledge hoarding. The hypotheses are tested via statistical analysis on the data collected from a questionnaire survey against the students who actually involved in the case study. The result shows that the low perceived usefulness of the ODBS by the students played major role in the failure of the system. Also it is hinted that network externalities as an intrinsic motivator is more effective than extrinsic motivators to increase the students’ activities on the ODBS. Finally the paper provides the designers of eLearning systems with advice for successful operation of ODBS in eLearning.     

Mutual tests using immunity-based diagnostic mobile agents in distributed intrusion detection systems

Distributed intrusion detection systems have several advantages over centralized systems, such as scalability, adaptability, and fault tolerance. A current research topic in distributed systems is self-monitoring to identify corrupted intrusion detection systems. One way of self-monitoring is for intrusion detection systems to check each other. As we describe herein, this can be done by mobile agents using an immunity-based diagnostic method modeled on idiotypic network theory. In simulations, the credibility of normal intrusion detection systems remained near 1, while it fell to about 0 for corrupted intrusion detection systems, thus enabling identification of the latter. We also confirmed what effects some parameters have on the diagnostic capability.This work was presented, in part, at the 8th International Symposium on Artificial Life and Robotics, Oita, Japan, January 24–26, 2003     

信息系统中的知识距离与知识粗糙熵

本文基于知识即划分的观点,证明了论域中所有知识构成一个距离空间,研究了知识距离空间中知识距离的一些性质,并应用知识距离度量信息系统中知识的粗糙熵。这些结果有利于更加深刻地分析信息系统中知识间的关系和知识的粗糙性。     

Knowledge seekers’ and contributors’ reactions to recommendation mechanisms in knowledge management systems

We examined the behavior of knowledge seekers and contributors to an internal Knowledge Management System (KMS) in a multinational organization. The system has two selection mechanisms, based on semantic algorithms and user ratings. The first utilizes an algorithm to ‘measure’ the quality of knowledge contributions and ranks them accordingly, while the second averages the ratings that knowledge items receive from KMS users. Building on appraisal theory, we found that knowledge seekers and contributors reacted differently to the two mechanisms. The rating-based rankings positively influenced knowledge seekers’ tendency to access, comment on, and spread the knowledge shared in the KMS, while the algorithm-based ranking positively influenced knowledge contributors’ to continue sharing knowledge via the system. Moreover, shorter (or longer) time delay between the time that the knowledge was shared and the time when knowledge contributors received their first comments seemed to positively (or negatively) influence the contributors’ tendency to continue sharing knowledge via the KMS. Our study adds to the existing KMS literature by investigating knowledge seekers’ and contributors’ reactions to the two different knowledge recommendation mechanisms, and recommends that managers understand the importance of implementing algorithm-based rankings in their KMS as well as the simpler and more commonly adopted rating-based ranking.     

Knowledge distilling based model compression and feature learning in fault diagnosis

Recently, there has been interest in developing diagnosis methods that combine model-based and data-driven diagnosis. In both approaches, selecting the relevant measurements or extracting important features from historical data is a key determiner of the success of the algorithm. Recently, deep learning methods have been effective in automating the feature selection process. Autoencoders have been shown to be an effective neural network configuration for extracting features from complex data, however, they may also learn irrelevant features. In addition, end-to-end classification neural networks have also been used for diagnosis, but like autoencoders, this method may also learn unimportant features thus making the diagnostic inference scheme inefficient. To rapidly extract significant fault features, this paper employs end-to-end networks and develops a new feature extraction method based on importance analysis and knowledge distilling. First, a set of cumbersome neural network models are trained to predict faults and some of their internal values are defined as features. Then an occlusion-based importance analysis method is developed to select the most relevant input variables and learned features. Finally, a simple student neural network model is designed based on the previous analysis results and an improved knowledge distilling method is proposed to train the student model. Because of the way the cumbersome networks are trained, only fault features are learned, with the importance analysis further pruning the relevant feature set. These features can be rapidly generated by the student model. We discuss the algorithms, and then apply our method to two typical dynamic systems, a communication system and a 10-tank system employed to demonstrate the proposed approach.     

High-voltage equipment condition monitoring and diagnosis system based on information fusion

As high-voltage electric equipment has complex structure and works in harsh environments, fiber Bragg grating (FBG) sensors are applied to realize the real-time monitoring of some parameters in which temperature is the main parameter. Using FBG sensors to monitor temperature of high-voltage electric equipment can overcome the disadvantages of harsh monitoring environment such as high-voltage, big current, strong electromagnetic interference and so on. The fault of high-voltage electric equipment is difficult to be distinguished as there may be many different reasons. The traditional or simple methods cannot totally meet the demand of fault diagnosis of high-voltage electric equipment. First, taking neural network as a classifier to distinguish different fault types from complex fault information in the feature layer can supply a good foundation to final information fusion diagnosis. Second, Dempster–Shafer evidence theory is used to make a comprehensive diagnosis of fault information in the decision layer. All the uses above can increase the speed and accuracy of diagnosis and have practical significance. The fault diagnosis system shows good results and provides an effective way to realize the real-time condition monitoring and more accurate fault diagnosis of high-voltage electric equipment.     

Multi-sensor distributed fusion filtering for networked systems with different delay and loss rates

This paper mainly focuses on the multi-sensor distributed fusion estimation problem for networked systems with time delays and packet losses. Measurements of individual sensors are transmitted to local processors over different communication channels with different random delay and packet loss rates. Several groups of Bernoulli distributed random variables are employed to depict the phenomena of different time delays and packet losses. Based on received measurements of individual sensors, local processors produce local estimates that have been developed in a new recent literature. Then local estimates are transmitted to the fusion center over a perfect connection, where a distributed fusion filter is obtained by using the well-known matrix-weighted fusion estimation algorithm in the linear minimum variance sense. The filtering error cross-covariance matrices between any two local filters are derived. The steady-state property of the proposed distributed fusion filter is analyzed. A simulation example verifies the effectiveness of the algorithm.