Development of Fault Diagnosis System for Spacecraft Based on Fault Tree and G2

Some ideas in the development of fault diagnosis system for spacecraft are introduced. Firstly, the architecture of spacecraft fault diagnosis is proposed hierarchically with four diagnosis frames, i.e., system level, subsystem level, component level and element level. Secondly, a hierarchical diagnosis model is expressed with four layers, i.e., sensors layer, function layer, behavior layer and structure layer. These layers are used to work together to accomplish the fault alarm, diagnosis and localization. Thirdly, a fault-tree-oriented hybrid knowledge representation based on frame and generalized rule and its relevant reasoning strategy is put forward. Finally, a diagnosis case for spacecraft power system is exemplified combining the above with a powerful expert system development tool G2.

Application of Maximum Probability Approach to the Fault Diagnosis of a Servo System

In an actual control system, it is often difficult to find out where the faults are if only based on the outside fault phenomena, acquired frequently from a fault system. So the fault diagnosis by outside fault phenomena is considered. Based on the theory of fuzzy recognition and fault diagnosis, this method only depends on experience and statistical data to set up fuzzy query relationship between the outside phenomena (fault characters) and the fault sources (fault patterns). From this relationship the most probable fault sources can be obtained, to attain the goal of quick diagnosis. Based on the above approach, the standard fuzzy relationship matrix is stored in the computer as a system database. And experiment data are given to show the fault diagnosis results. The important parameters can be on line sampled and analyzed, and when faults occur, faults can be found, the alarm is given and the controller output is regulated.

Optimization of a dynamic uncertain causality graph for fault diagnosis in nuclear power plant

Fault diagnostics is important for safe operation of nuclear power plants(NPPs). In recent years, data-driven approaches have been proposed and implemented to tackle the problem, e.g., neural networks, fuzzy and neurofuzzy approaches, support vector machine, K-nearest neighbor classifiers and inference methodologies. Among these methods, dynamic uncertain causality graph(DUCG)has been proved effective in many practical cases. However, the causal graph construction behind the DUCG is complicate and, in many cases, results redundant on the symptoms needed to correctly classify the fault. In this paper, we propose a method to simplify causal graph construction in an automatic way. The method consists in transforming the expert knowledge-based DCUG into a fuzzy decision tree(FDT) by extracting from the DUCG a fuzzy rule base that resumes the used symptoms at the basis of the FDT. Genetic algorithm(GA) is, then, used for the optimization of the FDT, by performing a wrapper search around the FDT: the set of symptoms selected during the iterative search are taken as the best set of symptoms for the diagnosis of the faults that can occur in the system. The effectiveness of the approach is shown with respect to a DUCG model initially built to diagnose 23 faults originally using 262 symptoms of Unit-1 in the Ningde NPP of the China Guangdong Nuclear Power Corporation. The results show that the FDT, with GA-optimized symptoms and diagnosis strategy, can drive the construction of DUCG and lower the computational burden without loss of accuracy in diagnosis.

Iterative Learning Fault Diagnosis Algorithm for Non-uniform Sampling Hybrid System

For a class of non-uniform output sampling hybrid system with actuator faults and bounded disturbances,an iterative learning fault diagnosis algorithm is proposed.Firstly,in order to measure the impact of fault on system between every consecutive output sampling instants,the actual fault function is transformed to obtain an equivalent fault model by using the integral mean value theorem,then the non-uniform sampling hybrid system is converted to continuous systems with timevarying delay based on the output delay method.Afterwards,an observer-based fault diagnosis filter with virtual fault is designed to estimate the equivalent fault,and the iterative learning regulation algorithm is chosen to update the virtual fault repeatedly to make it approximate the actual equivalent fault after some iterative learning trials,so the algorithm can detect and estimate the system faults adaptively.Simulation results of an electro-mechanical control system model with different types of faults illustrate the feasibility and effectiveness of this algorithm.

Use of Discrete Wavelet Features and Support Vector Machine for Fault Diagnosis of Face Milling Tool

This paper presents the fault diagnosis of face milling tool based on machine learning approach.While machining,spindle vibration signals in feed direction under healthy and faulty conditions of the milling tool are acquired.A set of discrete wavelet features is extracted from the vibration signals using discrete wavelet transform(DWT)technique.The decision tree technique is used to select significant features out of all extracted wavelet features.C-support vector classification(C-SVC)andν-support vector classification(ν-SVC)models with different kernel functions of support vector machine(SVM)are used to study and classify the tool condition based on selected features.From the results obtained,C-SVC is the best model thanν-SVC and it can be able to give 94.5%classification accuracy for face milling of special steel alloy 42CrMo4.

Comparative Study on Tool Fault Diagnosis Methods Using Vibration Signals and Cutting Force Signals by Machine Learning Technique

The state of cutting tool determines the quality of surface produced on the machined parts.A faulty tool produces poor sur face,inaccurate geometry and non-economic production.Thus,it is necessary to monitor tool condition for a.machining process to have superior quality and economic production.In the pre-sent study,fault classification of single point cutting tool for hard turning has been carried out by employing machine learning technique.Cutting force and vibration signals were acquired to monitor tool condition during machining.A set of four tooling conditions namely healthy,worn flank,broken insert and extended tool overhang have been considered for the study.The machine learning technique was applied to both vibration and cutting force signals.Discrete wavelet features of the signals have been extracted using discrete wavelet trans formation(DWT).This transformation represents a large dataset into approximation coeffcients which contain the most useful information of the dataset.Significant features,among features extracted,were selected using J48 decision tree technique.Clas-sification of tool conditions was carried out us ing Naive Bayes algorithm.A 10 fold cross validation was incorporated to test the validity of classifier.A comparison of performance of classifier was made between cutting force and vibration signal to choose the best signal acquisition method in classifying tool fault conditions using machine learning technique.

Fuzzy Fault Diagnosis of a Diesel Engine Non-start

The diesel locomotive plays an important role in the field of transport, and the engine maintenance work is the prerequisite and gnarantee for the locomotive normal working. In this paper, we first establish the fault tree model of locomotive engine 16V240ZJ on the basis of engine non-start as the top event. Then we combines the fitzzy mathematics the- ory and fault tree analysis method for failure diagnosis of 16V240ZJ engine＇s abnormal start-up. We obtained the fuzzy probability curve and top events probability confidence interval by analyzing the fuzzy fault tree qualitatively and quantitatively. It provides a fuzzy analysis basis for solving the problem of 16V240ZJ engine＇s abnormal start-up.

Design and implementation of an expert system for remote fault diagnosis in ship lift

In this paper an expert system for remote fault diagnosis in the ship lift was developed by analysis of the fault tree and combination with VPN. The fault tree was constructed based on the operation condition of the ship lift. The diagnosis model was constructed by hierarchical classification of the fault tree structure, and the inference mechanism was given. Logical structure of the fault diagnosis in the ship lift was proposed. The implementation of the expert system for remote fault diagnosis in the ship lift was discussed, and the expert system developed was realized on the VPN virtual network. The system was applied to the Gaobaozhou ship lift project, and it ran successfully.

FUZZY PETRI NET FOR FAULT DIAGNOSIS

Because of the stochastic property of fault occurrence and fuzziness offault phenomenon, machine fault diagnosis technique in use, such as fault tree analysis,cause consequence tree method, etc., cannot exactly describe the properties of fault phe-nomenon and coherence of fault space. In this paper, based on the theory of generalPetri net, fault tree technique and theory of fuzzy set, a theory system of fuzzy Petri net(FPN) suitable for fault diagnosis is established, which is applied to an example of faultdiagnosis for FMS. This method has the properties of of rbjectivity, strong expressionability, easy inference, etc., which can solve the problems of stochastic property andfuzziness of fault.

Single Point Cutting Tool Fault Diagnosis in Turning Operation Using Reduced Error Pruning Tree Classifier

Tool wear is inevitable in daily machining process since metal cutting process involves the chip rubbing the tool surface after it has been cut by the tool edge.Tool wear dominantly influences the deterioration of surface finish,geometric and dimensional tolerances of the workpiece.Moreover,for complete utilization of cutting tools and reduction of machine downtime during the machining process,it becomes necessary to understand the develop-ment of tool wear and predict its status before happening.In this study,tool condition monitoring system was used to monitor the behavior of a single point cutting tool to predict flank wear.A uniaxial accelerometer was attached to a single point cutting tool under study.The accelerometer acquires vibrational signals during turning operation on a lathe machine.The acquired signals were then used to extract statistical features such as standard error,variance,skewness,etc.The substantial features were recognized to reduce the utilization of computing resources.They were used to classify the signals as good and three different measures of flank wear by a decision tree algorithm.Frequency domain features were also extracted and shown to be less effective in classification in comparison to statistical features.REPTree(Reduced Error Pruning Tree)algorithm was used in this study.REPTree decision tree algorithm achieved a maximum classification accuracy of 72.77%for all signals combined.When spindle speed and feed rate are considered as the variables the accuracy is about 86.25%.When spindle speed is the only variable parameter the accuracy is about 82.71%.When depth of cut,feed rate and speed of the spindle are considered as variable parameters,the accuracy of the decision tree is around 93.51%.This study demonstrates the performance of REPTree classifier in tool condition monitoring.It can be utilized for tool wear identification and thus improve surface finish,dimensional accuracy of the work piece and reduce machine down-time.Any additional research on the work may involve analysis of different classifier algorithms which could potentially predict tool wear with greater accuracy.

Feature Extraction and Diagnosis System Using Virtual Instrument Based on CI

Through investigating intelligent diagnosis method of Computational Intelligence (CI) and studying its application in fault feature extraction, a gear fault detection and Virtual Instrument Diagnostic System is developed by using the two hybrid programming method which combines both advantages of VC++ and MATLAB. The interface is designed by VC++ and the calculation of test data, signal processing and graphical display are completed by MATLAB. The pro-gram converted from M-file to VC++ is completed by interface software, and a various multi-functional gear fault di-agnosis software system is successfully obtained. The software system, which has many functions including the intro-duction of gear vibration signals, signal processing, graphical display, fault detection and diagnosis, monitoring and so on, especially, the ability of diagnosing gear faults. The method has an important application in the field of mechanical fault diagnosis.

FTA在应急通信车网络故障诊断系统的应用

针对应急通信车通信网络综合组网复杂性和故障关联关系复杂性越来越高的问题,提出了基于故障树分析(Fault Tree Analysis,FTA)法的应急通信车通信网络故障集中诊断方法。该方法可以实现通信网络故障的快速诊断,并能够将诊断结果反馈到应急通信车智能通信网络管控系统,通过故障专家知识库支撑和资源调控智能化辅助,实现人工干预或通信网络自适应快速调整和恢复,从而提升应急通信车可靠性、维修性水平。该设计方法可推广应用到大型复杂通信系统和通信、指挥车辆平台通信网络的运维管理系统中,具有较广阔的设计分析和工程应用前景。

Attribute-driven Fuzzy Fault Tree Model for Adaptive Lubricant Failure Diagnosis

Lubricant diagnosis serves as a crucial accordance for condition-based maintenance(CBM)involving oil changing and wear examination of critical parts in equipment.However,the accuracy of traditional end-to-end diagnosis models is often limited by the inconsistency and random fluctuations in multiple monitoring indicators.To address this,an attribute-driven adaptive diagnosis method is developed,involving three attributes:physicochemical,contamination,and wear.Correspondingly,a fuzzy fault tree(termed FFT)-based model is constructed containing the logic correlations from monitoring indicators to attributes and to lubricant failures.In particular,inference rules are integrated to mitigate conflicts arising from the reverse degradation of multiple indicators.With this model,the lubricant conditions can be accurately assessed through rule-based reasoning.Furthermore,to enhance its intelligence,the model is dynamically optimized with lubricant analysis knowledge and monitoring data.For verification,the developed model is tested with lubricant samples from both the fatigue experiment and actual aero-engines.Fatigue experiments reveal that the proposed model can improve the lubricant diagnosis accuracy from 73.4%to 92.6%compared with the existing methods.While for the engine lubricant test,a high accuracy of 90%was achieved.

基于故障树反演的复合材料成形生产线故障诊断

复合材料成形装备生产线因其复杂性和高度集成性,故障的产生可能涉及多个环节和因素,因此需要一种系统性的方法来准确地分析和定位故障源。本文梳理了复合材料产品制造过程中可能出现的故障类型和影响因素,构建了一个全面的复合材料成形装备产线故障树,借助故障树反演技术,将实际故障事件映射到故障树上,通过逆向推导,得出可能导致这些故障事件的基本故障事件,该方法在提高生产质量、降低故障风险方面具有重要意义,为复合材料制造领域的技术改进和创新提供了有力支持。

基于虚拟化技术的电子信息设备故障诊断与虚拟仿真实验室设计

阐述使用虚拟化技术构建电子信息设备故障诊断虚拟仿真实验室的方案,通过使用虚拟化技术将电子信息设备的硬件环境虚拟化,使用仿真软件模拟设备的运行状态和故障场景,实现设备的故障诊断。

海上油田仪表设备故障诊断以及维修探析

探讨海上油田仪表设备面临的复杂地层和侵蚀性海洋环境对其产生的负面影响,以及一系列创新的技术措施,如先进的传感技术、自动化维修机器人、3D打印维修部件等,来提高设备的监测、维护和修复效率,确保油田的持续高效生产。

基于CART决策树的FPSO单点系泊系统电滑环故障诊断

为了保障FPSO单点系泊系统电滑环运行安全,有必要开展电滑环故障诊断方法的研究,为单点系泊系统电滑环故障预警与排查提供依据。本文针对FPSO单点电滑环故障的诊断问题,采用了一种基于CART决策树算法的故障诊断模型;进一步利用有限元制作样本数据集,并通过该数据集训练得到了电滑环故障诊断模型;最后,通过后剪枝法完成了诊断模型的简化,实现了对电滑环的故障诊断。分析结果可以得到,该模型具有较高的准确率和较快的诊断速度,能够对电滑环进行有效的诊断,以便工作人员及时采取措施修复或更换电滑环,保证FPSO的安全运行。

基于Morlet小波与CART决策树的滚动轴承故障诊断方法

针对滚动轴承故障诊断过程中样本处理、故障识别等技术问题,提出一种基于Morlet小波和分类回归树(Classification and Regression Tree,CART)的滚动轴承故障诊断方法。首先,利用Morlet小波分析方法和移动窗方法对轴承振动信号进行样本处理。其次,对提取的短样本进行变分模态分解与特征提取,完成训练集和测试集的构建。然后,使用训练集训练CART决策树分类模型,同时引入随机搜索和K折交叉验证用于模型关键参数优化,以获取理想的轴承故障分类模型。测试集验证结果表明,该方法不但能实现多种轴承故障的有效诊断、在含噪测试集中表现良好,而且单个样本的数据长度和采样时长的缩短效果明显。

基于故障树和产生式规则的故障诊断专家系统设计

[目的]为充分运用核动力装置的运行管理经验辅助核动力操纵人员进行故障诊断,设计一种船用核动力装置故障诊断专家系统。[方法]首先,根据故障树与产生式规则之间的逻辑一致性,提出一种将故障树知识转化为产生式规则的方法;然后,对采用正、反向混合推理方法的专家系统知识库和推理机进行优化设计,并依据故障树最小割集和重要度分析结果设计正向推理策略以简化推理流程;最后,根据人工对故障状态判断的思路设计状态监测模块,实时采集关键设备参数以转化为专家系统可识别的设备信息。[结果]结果显示,采用所提方法可解决专家系统知识获取困难的问题,能在保证推理准确度的前提下提升推理效率,实现了专家系统的在线故障诊断功能。[结论]研究表明采用所提方法可提升专家系统获取知识的能力和推理效率,对保障核动力装置的运行管理安全具有重要意义。

BSPST:形变监测仪器故障分类算法

针对现有形变监测仪器发生故障时故障类别难以准确分类的问题,提出了一种基于最大区分子序列(Shapelet)转换的时间序列分类算法(best qualify Shapelet Transform,BSPST)。为了提升Shapelet质量,利用布隆过滤器和相似度匹配保留一组高质量的候选Shapelet来构建分类模型,BSPST利用布隆过滤器筛选出同类别中重复的符号聚合近似(symbolic aggregation approximation,SAX)单词。随后通过位图中标记的单词来评价SAX单词的重复度,以此去除类别中相似的SAX单词。最终将处理后的符号聚合近似单词转化为高质量的Shapelet。通过Shapelet转换技术,对数据进行转换。最后采取集成分类器进行分类。根据地震形变仪器故障数据建立了7个地震设备故障数据集,并结合东安格利亚大学和加州大学河滨分校时间序列分类仓库中选取的44个数据集和具代表性的最先进的方法进行了充分的实验验证。结果表明,BQST算法在分类精度、分类速度上稳居前列,有效解决了形变监测仪器的故障分类问题。