融合案例与规则推理的故障预测专家系统

根据故障预测的特点和要求，将案例推理引入到故障预测专家系统的设计中，阐述了案例的描述和检索方法。并以全新的角度提出了基于案例与规则的故障预测推理机制，对二者的结合方式作了阐述，给出了专家系统的整体实现结构。     

基于案例推理的竖炉故障预报系统

为降低竖望炉焙烧过程的故障发生率,基于故障机理的分析,将过程参量预报与案例推理技术相集成,提出了竖炉焙烧过程的智能故障预报方法.参量量预报模型对不易在线连续测量但能反映故障征兆的关键工艺参数进行实时预报,在此基础上,采用案例推理技术对焙烧过程进行全面分析并给出一些典型故障发生的概率和操作指导.将所建立的故障预报系统成功应用于竖炉焙烧过程的生产实际中,故障发生率明显降低,取得了显著应用成效.     

基于E语言的故障建模方法研究

为适应故障注入的自动化和实时性要求,针对试验人员需在试验开始前给出故障信息和编写试验方案,提出产品故障、元故障和故障模型概念,提取产品故障和元故障特征。在此基础上,采用IEEE Std 1647TM-2006的“E”功能验证语言,描述故障特征、构建故障模型,并给出故障模式的描述方式。最后以某电子飞行显示系统为应用案例,案例表明,故障模型及其描述方法可有效地提高故障注入的自动化和实时性水平。     

基于B／S结构的注塑机远程故障诊断系统的设计

为了提高注塑机故障诊断效率,提高企业经济效益,解决诊断人员不足的问题,提出将远程故障诊断系统应用到注塑机故障诊断中。给出了远程诊断的系统框架,基于三层B／S结构的系统模式,采用将子时段PCA、小波包分析和案例推理相结合的技术作为系统的故障诊断技术,有效实现了注塑机的远程故障诊断。     

案例推理在汽车故障诊断中的应用*

以奇瑞汽车故障诊断为应用背景,研究并开发了一个基于案例推理的汽车故障诊断系统原型,以实现对汽车故障的智能诊断。系统依据故障的特征属性和内容将汽车故障案例进行分类,进而根据最近邻算法对某一种类的案例集进行检索,最后构建了软件原型系统。通过对汽车故障样本案例进行仿真测试,表明了设计思想是合理的,实现方法是有效的。     

一起规约转换装置故障引起的远动数据不刷新案例分析

本文介绍了一起发生在500kV变电站,由于规约转换装置故障引起的调度主站远动数据不刷新的案例。文中对故障时的发生表象进行描述,对检修技术人员现场技术处理过程进行了详细说明,对案例涉及相应技术数据进行了分析,最后给出了相应的解决方法。     

基于知识图谱的电力变压器绝缘故障监测方法

通过传感器采集电力变压器数据，只能获取当前运行数据，导致变压器绝缘故障监测结果与实际情况不一致，为此提出基于知识图谱的电力变压器绝缘故障监测方法。采用RBF神经网络建立了变压器绝缘故障监测模型；依据知识图谱三元组成和生命周期，设计数据抽取步骤，抽取变压器历史数据，构建电力变压器知识图谱；设置变压器温度和功率值，设计故障监测步骤，实现变压器绝缘故障监测。实验结果表明：本文方法在案例1和案例2中，监测变压器绝缘故障产生原因与案例设置原因一致，监测效果较好。     

基于故障树的故障诊断IDSS的设计

将智能决策支持技术引入故障诊断，给出系统的总体设计，并详细阐述基于故障树的知识库和推理机的设计。采用面向对象基于框架、规则、元知识集成的广义故障树知识表示方法，同时给出了基于故障树最小割集和最小路集的故障快速推理算法，实现了故障的迅速诊断。     

双剑合璧，谁与争锋——今天，和关机故障说Bye—Bye!

Windows的关机故障令人头痛，我们在去年第6期的《轻轻地我走了--关机的故障解决与技巧》一文中介绍了不少经典的Windows 98／XP关机故障解决案例．小编和一些作者通过长期在国内，国外著名电脑论坛、新闻组潜水，并且与许多公司的技术支持人员交流．又搜集了众多发病率颇高的关机案例．下面就将它们整理出来打造为一把倚天剑，与去年第6期那篇屠龙刀双剑合璧．成就当夸最经典的终极Windows关机故障解决方案!     

直觉模糊Petri网的双向模糊故障推理算法

针对故障诊断中故障现象与故障原因之间复杂的不确定关系,利用直觉模糊集表达不确定性信息的优势和Petri网的图形处理问题的能力,给出了基于直觉模糊Petri网的双向模糊故障推理算法。该算法首先利用反向直觉模糊推理算法对模型进行约减,查找故障原因,再利用正向直觉模糊推理算法对模型进行计算,输出结果。该算法既可将故障信息化繁为简,降低推理过程的时间复杂度,还能够使故障诊断的确定性程度得到进一步提高。汽车发动机诊断案例表明了所给双向直觉模糊推理算法的可行性和有效性。     

Fragment Method of Restoring the Operation of Digital Systems with the Structure of a Minimal Quasicomplete Graph with Two Paths between Two Users

The developed approach to the fragment method of restoring the operation of digital systems (DS) structured as a minimal quasicomplete graph with two paths between two users is to alternately restore individual DS fragments. The analyzed DS fragment consists of a tested user, a switch, and two communication lines between the switch and the testing and tested users. For a single fragment, we construct a typical base program unit which can serve as a reference for the base units for other DS fragments. Based on the results of diagnostics for the components of the fragment, the testing user replaces functions of the faulty component with functions of operational components. The developed approach guarantees to remove the influence of a single faulty component in a digital system of the analyzed structure.     

Fault diagnosis of a power system based on a description of the structure and function of the relay system

Abstract: This paper proposes a method of fault diagnosis of power systems based on a knowledge-based approach. It makes use of information on relays and circuit breakers. The feature of this method is that the relay sequence is represented by a logical circuit. In this circuit the following two relations are represented; a logical relation between inputs and output of a gate and a connective relation between logical gates. These two relations are expressed by production rules in the knowledge base. When the information from relays and circuit breakers is given to the logical circuit, faulty components are pointed out.     

基于Volterra频域核辨识的非线性模拟电路故障诊断

基于Volterra级数时域频域混合模型,提出了辨识非线性模拟电路频域核的故障诊断方法.利用混合模型辨识算法和范德蒙特法估计各种故障状态下电路响应的前3阶频域核,提取故障特征并与相应的故障模式一起构成特征样本集,借助于支持向量机多分类器进行分类识别,实现非线性模拟电路的故障诊断.阐述了诊断原理及诊断步骤,并给出了诊断实例.仿真结果表明,该方法的故障识别率较高,便于计算机计算.     

Example-based model-transformation testing

A major concern in model-driven engineering is how to ensure the quality of the model-transformation mechanisms. One validation method that is commonly used is model transformation testing. When using this method, two important issues need to be addressed: the efficient generation/selection of test cases and the definition of oracle functions that assess the validity of the transformed models. This work is concerned with the latter. We propose a novel oracle function for model transformation testing that relies on the premise that the more a transformation deviates from well-known good transformation examples, the more likely it is erroneous. More precisely, the proposed oracle function compares target test cases with a base of examples that contains good quality transformation traces, and then assigns a risk level to them accordingly. Our approach takes inspiration from the biological metaphor of immune systems, where pathogens are identified by their difference with normal body cells. A significant feature of the approach is that one no longer needs to define an expected model for each test case. Furthermore, the detected faulty candidates are ordered by degree of risk, which helps the tester inspect the results. The validation results on a transformation mechanism used by an industrial partner confirm the effectiveness of our approach.     

The development of a fault-tolerant control approach and its implementation on a flexible arm robot

This article presents a robust sensor fault-tolerant control (FTC) scheme and its implementation on a flexible arm robot. Sensor faults affect the system's performance in the closed loop when the faulty sensor readings are used to generate the control input. In this article, the non-faulty sensors are used to reconstruct the faults on the potentially faulty sensors. The reconstruction is subtracted from the faulty sensors to generate a 'virtual sensor' which (instead of the normally used faulty sensor output) is then used to generate the control input. A design method is also presented in which the virtual sensor is made insensitive to any system uncertainties (which could corrupt the fault reconstruction) that cannot fit into the framework of the model used. Two fault conditions are tested: total failure and incipient faults. Then the scheme robustness is tested and evaluated through its implementation on two flexible arm systems, one with a flexible joint and the other with a flexible link. Excellent results have been obtained for both cases (joint and link); the FTC scheme produced system performance almost identical to the fault-free scenario, whilst providing an indication that a fault is present, even for simultaneous faults.     

Visual analysis of quality-related manufacturing data using fractal geometry

Improving manufacturing quality is an important challenge in various industrial settings. Data mining methods mostly approach this challenge by examining the effect of operation settings on product quality. We analyze the impact of operational sequences on product quality. For this purpose, we propose a novel method for visual analysis and classification of operational sequences. The suggested framework is based on an Iterated Function System (IFS), for producing a fractal representation of manufacturing processes. We demonstrate our method with a software application for visual analysis of quality-related data. The proposed method offers production engineers an effective tool for visual detection of operational sequence patterns influencing product quality, and requires no understanding of mathematical or statistical algorithms. Moreover, it enables to detect faulty operational sequence patterns of any length, without predefining the sequence pattern length. It also enables to visually distinguish between different faulty operational sequence patterns in cases of recurring operations within a production route. Our proposed method provides another significant added value by enabling the visual detection of rare and missing operational sequences per product quality measure. We demonstrate cases in which previous methods fail to provide these capabilities.     

Fault diagnosis of continuous annealing processes using a reconstruction-based method

The continuous annealing process line (CAPL) has complex process characteristics, such as strong correlation of a large number of process variables and interconnected multi-subsystems and multiple operation zones. Practitioners are concerned with typical process faults, such as strip-break and roll-slippage, whose effects are often confined in a specific zone. Considering the large-scale process characteristics and fault characteristics, a multi-block fault diagnosis method is proposed. A novel reconstruction-based block contribution (RBBC) is first proposed in order to diagnose the faulty block. The reconstruction-based variable contribution (RBVC) within a block is also proposed to determine the faulty variables. The proposed RBBC-RBVC hierarchical scheme is applied successfully to a real CAPL on two fault cases. A finite state machine is utilized to diagnose strip-break and reconstructed combined index is studied to diagnose roll-slippage.     

Effective fault detection and routing scheme for wireless sensor networks

In a wireless sensor network (WSN), random occurrences of faulty nodes degrade the quality of service of the network. In this paper, we propose an efficient fault detection and routing (EFDR) scheme to manage a large size WSN. The faulty nodes are detected by neighbour node’s temporal and spatial correlation of sensing information and heart beat message passed by the cluster head. In EFDR scheme, three linear cellular automata (CA) are used to manage transmitter circuit/ battery condition/microcontroller fault, receiver circuit fault and sensor circuit fault representation. On the other hand, L-system rules based data routing scheme is proposed to determine optimal routing path between cluster head and base station. The proposed EFDR technique is capable of detecting and managing the faulty nodes in an efficient manner. The simulation results show 86% improvement in the rate of energy loss compared to an existing algorithm.     

Proof that pyramid networks are 1-Hamiltonian-connected with high probability

Wu revealed in 2001 that pyramid networks are Hamiltonian-connected. This investigation demonstrates that a pyramid network with one faulty node or one faulty edge is Hamiltonian-connected, excluding some special faulty cases by building a Hamiltonian path between any two distinct nodes in it. Although a pyramid network with one fault is not Hamiltonian-connected, this study indicates that a pyramid network is 1-Hamiltonian-connected with a very high probability.     

基于时空特性的无线传感器网络节点故障诊断方法

无线传感器网络中故障节点会产生并传输错误数据,这将消耗节点的能量和带宽,同时会形成错误的决策。利用节点感知数据的空间相似性,提出了节点故障诊断的算法,通过对邻节点所感知的传感数据进行比较,从而确定检测节点的状态,并将测试状态向网络中其他相邻节点进行扩散。对于网络中存在的节点瞬时故障,通过时间冗余的检测方法,降低故障诊断的虚警率。该算法对实现故障节点的检测具有较好的性能,实验结果验证了算法的可行性和有效性。