Research on intelligent fault diagnosis based on time series analysis algorithm

Aiming to realize fast and accurate fault diagnosis in complex network environment, this article proposes a set of anomaly detection algorithm and intelligent fault diagnosis model. Firstly, a novel anomaly detection algorithm based on time series analysis is put forward to improve the generalized likelihood ratio （GLR） test, and thus, detection accuracy is enhanced and the algorithm complexity is reduced. Secondly, the intelligent fault diagnosis model is established by introducing neural network technology, and thereby, the anomaly information of each node in end-to-end network is integrated and processed in parallel to intelligently diagnose the fault cause. Finally, server backup solution in enterprise information network is taken as the simulation scenario. The results demonstrate that the proposed method can not only detect fault occurrence in time, but can also implement online diagnosis for fault cause, and thus, real-time and intelligent fault management process is achieved.     

Implementation of Dynamic System Control Circuit Board Test System of Pure Electric Vehicles

The dynamic system control circuit board(DSCCB)is one of the most important components for dynamic system of pure electric vehicles. The current detection of the DSCCB is done manually, which is not only inefficient in the detection but also difficult to guarantee the data accuracy. In order to improve the detection efficiency and accuracy, a new testing system is designed by Labview. The total test time can be further reduced by about 75% compared with the results of the manual detection. In this paper, the three-parameter sine wave curve-fit algorithm theory is applied to the phase delay detection of the current sensor sampling circuit on the DSCCB. This method solves the problem of big error in the phase delay detection.     

On the Effectiveness of the System Validation Based on the Black Box Testing Methodology

With the advancement of technology in recent years, effective fault diagnosis became a necessity to verify the performance and ensure the quality of complex systems. In this paper, an original verification methodology for complex consumer electronic devices is presented. Verification of the system which consists of hardware （integrated circuit） and corresponding software within a flat panel TV set is in the focus. Proposed methodology provides reliable functional failure detection using the concept of black box testing. Further, the approach is fully automated, improving the reliability and speed of failure detection. The methodology effectiveness has been experimentally evaluated and the analysis results have been reported.     

A Hierarchical Modeling and Fault Diagnosis Method for Complex Electronic Devices

Due to the shortcomings of the diagnosis systems for complex electronic devices such as failure models hard to build and low fault isolation resolution, a new hierarchical modeling and diagnosis method is proposed based on multisignal model and support vector machine （SVM）. Multisignal model is used to describe the failure propagation relationship in electronic device system, and the most probable failure printed circuit boards （PCBs） can be found by Bayes inference. The exact failure modes in the PCBs can be identified by SVM. The results show the proposed modeling and diagnosis method is effective and suitable for diagnosis for complex electronic devices.     

Reliability of NFV Using COTS Hardware

This paper describes a study on the feasibility of using commercial off- the- shelf(COTS) hardware for telecom equipment. The study outlines the conditions under which COTS hardware can be utilized in a network function virtualization environment. The concept of silent-error probability is introduced to account for software errors and/or undetectable hardware failures, and is included in both the theoretical work and simulations. Silent failures are critical to overall system availability. Site-related issues are created by combined site maintenance and site failure. Site maintenance does not noticeably limit system availability unless there are also site failures. Because the theory becomes extremely involved when site failure is introduced, simulation is used to determine the impact of those facts that constitutes the undesirable features of using COTS hardware.     

Composite failure prediction of π-joint structures under bending

In this article, the composite π-joint is investigated under bending loads. The "L" preform is the critical component regard- ing composite π-joint failure. The study is presented in the failure detection of a carbon fiber composite π-joint structure under bending loads using fiber Bragg grating (FBG) sensor. Firstly, based on the general finite element method (FEM) software, the 3-D finite element (FE) model of composite π-joint is established, and the failure process and every lamina failure load of composite π-joint are investigated by maximum stress criteria. Then, strain distributions along the length of FBG are extracted, and the reflection spectra of FBG are calculated according to the strain distribution. Finally, to verify the numerical results, a test scheme is performed and the experimental spectra of FBG are recorded. The experimental results indicate that the failure sequence and the corresponding critical loads of failure are consistent with the numerical predictions, and the computational error of failure load is less than 6.4%. Furthermore, it also verifies the feasibility of the damage detection system.     

A fault detection sensor for circuit aging using double-edge-triggered flip-flop

In nanoscale technology, transistor aging is one of the most critical problems that impact on the reliability of circuits. Aging sensor is a good online way to detect the circuit aging, which performs during the operating time with no influence of the normal operation of circuits. In this paper, a Double-edge-triggered Detection Sensor for circuit Aging (DSDA) is proposed, which employs data signal of logic circuits as its clock to control the sampling process. The simulation is done by Hspice using 45 nm technology. The results show that this technique is not sensitive to the process variations. The worst case of the detection precision is more than 80% under the different process variations. It can detect aging fault effectively with the 8% power cost and 30% performance cost.     

FPGA-Based Network Traffic Security： Design and Implementation Using C5.0 Decision Tree Classifier

In this work, a hardware intrusion detection system （IDS） model and its implementation are introduced to perform online real-time traffic monitoring and analysis. The introduced system gathers some advantages of many IDSs： hardware based from implementation point of view, network based from system type point of view, and anomaly detection from detection approach point of view. In addition, it can detect most of network attacks, such as denial of services （DOS）, leakage, etc. from detection behavior point of view and can detect both internal and external intruders from intruder type point of view. Gathering these features in one IDS system gives lots of strengths and advantages of the work. The system is implemented by using field programmable gate array （FPGA）, giving a more advantages to the system. A C5.0 decision tree classifier is used as inference engine to the system and gives a high detection ratio of 99.93%.     

PERFORMANCE OF MULTIUSER DETECTION FOR CDMA SYSTEM IN A FLAT RAYLEIGH FADING ENVIRONMENT

In a CDMA communication network using conventional signal detection, system capacity is limited and its performance is degraded by the multi-access interference (MAI). Multiuser detection, which makes use of cross-correlation information between spread spectrum codes, can reduce or eliminate the MAI in a Gaussian channel so as to mitigate the near-far effects and increase the system capacity. This paper extends the multiuser detector to a flat Rayleigh fading CDMA environment, and discusses the bit error rate of typical multiuser detection algorithms in such a environment by combining theoretical analysis and computer simulation. It is shown that multiuser detection is superior to conventional detections in the flat Rayleigh fading channels.     

Availability requirement for a fault-management server in high-availability communication systems

This paper investigates the availability requirement for the fault management server in high-availability communication systems. This study shows that the availability of the fault management server does not need to be 99.999% in order to guarantee a 99.999% system availability, as long as the fail-safe ratio (the probability that the failure of the fault management server does not bring down the system) and the fault coverage ratio (probability that the failure in the system can be detected and recovered by the fault management server) are sufficiently high. Tradeoffs can be made among the availability of the fault management server, the fail-safe ratio, and the fault coverage ratio to optimize system availability. A cost-effective design for the fault management server is proposed.     

一种基于Openstack的虚拟机高可用方案

针对openstack的高可用性问题,目前大部分的研究都集中在控制节点的高可用上,对于虚拟机的高可用研究较少。已有的虚拟机高可用方案存在无法适应多种故障场景、无法针对单个虚拟机粒度进行故障处理等问题。本文提出了一种基于openstack的虚拟机高可用方案,方案使用控制组件和agent组件,配合不同故障的检测逻辑,实现多种故障场景下的虚拟机高可用。同时方案还引入了自治组概念,解决了agent组件故障或管理网故障场景下,agent组件无法继续进行故障检测、上报的问题。     

Using a neural/fuzzy system to extract heuristic knowledge ofincipient faults in induction motors: Part II-Application

The use of electric motors in industry is extensive. These motors are exposed to a wide variety of environments and conditions which age the motor and make it subject to incipient faults. These incipient faults, if left undetected, contribute to the degradation and eventual failure of the motors. This paper uses a hybrid neural/fuzzy fault detector to solve the motor fault detection problem. As an illustration, the neural/fuzzy fault detector is used to monitor the condition of a motor bearing and stator winding insulation. The initialization and training of this fault detector is in accordance with the procedures outlined in Part I of this paper. Once the neural/fuzzy fault detector is trained, the detector not only can provide accurate fault detector performance, but can also provide the heuristic reasoning behind the fault detection process and the actual motor fault conditions. With better understanding of the heuristics through the use of fuzzy rules and fuzzy membership functions, a better understanding of the fault detection process of the system is available, thus better motor protection systems can be designed     

基于AR模型参数的导航系统故障检测

为了解决导航系统中小幅值突变故障难以检测的问题，提出了一种基于AR模型参数的故障检测算法。该方法利用AR模型参数变化来进行实时故障检测。文中通过仿真实验，完成了对该算法性能的分析验证。结果表明，该算法能够有效的进行故障诊断，不仅对大的突变故障具有良好的检测效果，对小幅值突变故障也有较好的检测效果。     

Using a neural/fuzzy system to extract heuristic knowledge ofincipient faults in induction motors. Part I-Methodology

The use of electric motors in industry is extensive. These motors are exposed to a wide variety of environments and conditions which age the motor and make it subject to incipient faults. These incipient faults, if left undetected, contribute to the degradation and eventual failure of the motors. Artificial neural networks have been proposed and have demonstrated the capability of solving the motor monitoring and fault detection problem using an inexpensive, reliable, and noninvasive procedure. However, the major drawback of conventional artificial neural network fault detection is the inherent black box approach that can provide the correct solution, but does not provide heuristic interpretation of the solution. Engineers prefer accurate fault detection as well as the heuristic knowledge behind the fault detection process. Fuzzy logic is a technology that can easily provide heuristic reasoning while being difficult to provide exact solutions. The authors introduce the methodology behind a novel hybrid neural/fuzzy system which merges the neural network and fuzzy logic technologies to solve fault detection problems. They also discuss a training procedure for this neural/fuzzy fault detection system. This procedure is used to determine the correct solutions while providing qualitative, heuristic knowledge about the solutions     

Software Reliability Analysis and Measurement Using Finite and Infinite Server Queueing Models

Software reliability is often defined as the probability of failure-free software operation for a specified period of time in a specified environment. During the past 30 years, many software reliability growth models (SRGM) have been proposed for estimating the reliability growth of software. In practice, effective debugging is not easy because the fault may not be immediately obvious. Software engineers need time to read, and analyze the collected failure data. The time delayed by the fault detection & correction processes should not be negligible. Experience shows that the software debugging process can be described, and modeled using queueing system. In this paper, we will use both finite, and infinite server queueing models to predict software reliability. We will also investigate the problem of imperfect debugging, where fixing one bug creates another. Numerical examples based on two sets of real failure data are presented, and discussed in detail. Experimental results show that the proposed framework incorporating both fault detection, and correction processes for SRGM has a fairly accurate prediction capability.     

Real-time furnace modeling and diagnostics

Precise control of process temperature has become increasingly important in today's semiconductor industry. Multizone batch furnaces are used widely in current manufacturing lines, and high reliability of furnace systems is a crucial factor in achieving high product yield. However, uncertainty caused by sensor noise and failure may degrade reliability. In this work, the authors develop a methodology based on thermal modeling and sensor fusion techniques to detect temperature sensor failures, power supply failures, and system faults for the multizone furnace systems. The typical types of failures have been defined. The impact of single failures and different combinations of failures on the system behavior has been studied. The furnace system has been modeled based on both physical considerations and experimental data extraction. The fault detection methodology has been tested in simulations. Principal component analysis is utilized for choosing data types for different fault detection purposes. Sensor fusion is used to enhance reliability. Simulation results show that all different types of failures can be detected when data are rich enough. Experimental results show that all single failures and some of the failure combinations can be estimated when only steady-state and cooling-down data are utilized.     

A method for transformation of the system fault tree and repair policies into equivalent state-space diagram

In this paper is presented the algorithm which automatically forms the state space diagram from the fault tree. Proposed algorithm is designed to minimize the number of states. This is achieved by grouping identical modules in one base event, by merging identical system states and without expanding those branches in the space diagram which can not eventually lead to the system failure. Second algorithm described adds transitions which represent repairs to the state-space diagram formed by the first algorithm. Diagram, which is generated by the above algorithms can be solved by any numerical method, giving reliability or availability of the system.     

Cost analysis of a man-machine system operating under changing operator conditions

This paper deals with the stochastics behaviour of a man-machine system which is affected by the operator physical conditions. Operator physical condition is subject to a Markov process with two states - good and poor and is independent of the system state. Operating unit fails either due to operator error or system fault. Using Markov reneval process several characteristics such as mean time to system failure (MTSF), pointwise availability in (0,t], expected busy period of the repairman in (0,t] and expected profit earned by the system in (0,t] have been obtained.     

太阳能工程热水器控制器的设计与实现

设计了一套全自动太阳能工程热水器控制器。该系统利用低功耗高性能的RISC单片机AVR作为控制电路的核心实时监测水温及水位,可实现温度、水位检测管理,故障及相关报警提示等功能,利用E2PROM对设置的参数保存,具有断电记忆功能,断电后,参数无须重新设置。该款全自动太阳能热水器控制器具有使用方便、稳定性高、节能等特点,实用性高。