Support-Vector-Machine-Based False Alarm Filter of Mechatronic Built-in Test

Diagnosing intermittent fault is an important approach to reduce built-in test（BIT） false alarms. Aiming at solving the shortcoming of the present diagnostic method of intermittent fault, and according to the merit of support vector machines （ SVM） which can be trained with a small-sample, an SVM-based diagnostic model of 3 states that include OK state, intermittent state and faulty state is presented. With the features based on the reflection coefficients of an alarm rate （ AR ） model extracted from small vibration samples, these models are trained to diagnose intermittent faults. The experimental results show that this method can diagnose multiple intermittent faults accurately with small training samples and BIT false alarms are reduced.     

地震波频谱特性对高速列车动态脱轨行为的影响

为研究地震下高速列车的动态响应及地震波频谱特性对车辆动态脱轨行为的影响,发展了一种地震激励下车辆/轨道耦合动力学数值模型,车辆模型被简化为考虑悬挂非线性特性的35自由度多刚体系统,板式轨道被视为由钢轨、扣件系统、轨道板及CA砂浆层组成的弹性支承结构,钢轨被视为连续弹性离散点支承基础上的Timoshenko梁,轨道板用三维实体有限元模拟。采用移动轨下支承模型分析离散的轨枕支承对系统动力响应的影响,地震波被简化为周期性的横向正弦波加入计算模型中。基于仿真计算,对地震情况下高速列车的动力响应进行了详细分析,并重点分析了地震波频谱特性对高速车辆动态脱轨机理的影响。分析结果表明:地震波的频谱特性对车辆的动态响应、脱轨机理及车辆的运行安全有着重要的影响。     

Optimal Scheduling of Track Maintenance on a Railway Network

To ensure the safety and continued operation of the railway network system, many maintenance and renewal activities are performed on the track every month. Unplanned maintenance activities are expensive and would cause low service quality. Therefore, the track condition should be monitored, and when it has degraded beyond some acceptable limit, it should be scheduled for maintenance before failure. An optimal timetable of the maintenance activities is needed to be scheduled, planning the monthly workload, to reduce the effect on the transportation service and to reduce the potential costs. Considering the uncertainties of the deterioration process, the safety of transportation service, the lifetime loss of the replaced track, the maintenance cost and the travel cost, this article advances an optimisation model for the maintenance scheduling of a regional railway network. An enhanced genetic algorithm approach is proposed to search for a solution producing maintenance schedule such that the overall cost is minimised in a finite planning horizon. A case study is given to demonstrate the application of the method. The case study results were derived by using an enhanced genetic algorithm method, which is specifically developed to deal with the characteristics of the railway maintenance problem. Copyright © 2012 John Wiley & Sons, Ltd.     

Optimal working zone division for safe track maintenance in The Netherlands

After a sequence of serious accidents, the safety of rail track workers became an urgent and political problem in The Netherlands. It turned out that the rail track workers had one of the most dangerous jobs. The board of the Dutch Railways decided that the Dutch railway infrastructure had to be divided into so-called working zones. Moreover, to carry out maintenance activities, that particular working zone of the railway system had to be taken out of service. An essential problem was how to divide the Dutch railway infrastructure into working zones such that all parties involved are satisfied. Since many parties with conflicting interests were involved, this problem was extremely difficult. In this paper we show the division rules we developed, and which had been implemented in The Netherlands.     

世界铁路发展状况及其关键力学问题 全国结构工程学术会议特邀报告

论述了世界部分发达国家和我国铁路发展情况、铁路运输的优点及其在经济建设中所发挥的作用。介绍了世界发达国家和我国铁路发展历史和未来轨道交通发展方向。详细讨论了现有铁路运输存在的问题和未来高速铁路亟待解决的关键力学问题。它们主要是:(1)弓网/列车/轨道(桥梁)大系统耦合动力学; (2)车辆结构强度和可靠度问题;(3)轮轨关系(脱轨、粘着、滚动接触疲劳和波浪形磨损、轮轨噪声);(4)高速列车弓网动力学和高速受流条件下摩擦磨损;(5)轨道结构关键力学和严酷环境下轨道工程破坏问题。这些问题直接危及到行车的安全和运行品质.并提出今后解决这些问题的主要方向。     

地震作用下车辆-轨道系统轮轨动态响应试验研究

为研究地震作用下高速铁路地震预警阈值,进行准静态全尺寸车辆-轨道模型振动台试验研究,对车辆轨道模型施加正弦地震波,试验结果显示《铁道车辆动力学性能评定和试验鉴定规范》中所规定的轮重减载率限值和脱轨系数限值可能偏于保守,且导致列车脱轨的原因是由于地震作用使轨道结构发生大幅的水平向振动,引起车轮发生水平向晃动,致使车辆发生侧向滚摆运动所造成的;接着对车辆轨道模型施加实测地震波,试验结果表明地震波频谱特性对列车运行安全有一定的影响;对车辆轨道模型同时施加水平向和垂向地震波,发现对车辆轨道系统动力响应影响较大的为水平向地震波,垂向地震波则对其影响较小;根据振动台试验模型建立与之对应的多刚体、多自由度三维车辆-轨道数值模型,研究当考虑轨道不平顺时,地震作用下不同车速对列车轮动动力响应的影响,通过数据分析表明,在一定范围内,地震作用下的列车脱轨与列车速度关系不大,为高速铁路地震预警阈值的研究提供了一定的理论依据。     

A passive road-rail crossing design to minimise wheel-rail contact failure risk under frontal collision of trains onto stuck trucks

Derailments of trains often occur due to the wheel-rail contact failure caused by the impact of the trains with road vehicles at road-rail crossings. Frontal collisions of passenger trains onto stuck road vehicles occur frequently at such road-rail crossings even where active warning systems are installed. Such collisions are often fatal and cause significant damages to vehicles and the infrastructure especially when they incur derailments. Innovations in passive railway infrastructure designs for mitigating the severity of collision induced derailments are rare. This paper presents a formulation for a passive road-rail crossing involving stiffened edges of the raised road pavement to minimise the risk of failure of wheel–rail contact using a nonlinear three-dimensional multibody dynamics model. Severe derailment scenarios of trains passing through the passive and normal road-rail crossings have been analysed and presented. The innovative design of the road-rail crossing with passive track structure presented in the paper is shown to reduce the failure of the wheel-rail contact and hence the train-truck frontal collision derailment potential.     

Reducing the threat of in-transit derailments involving dangerous goods through effective placement along the train consist

Train derailments are important safety concerns, and they become increasingly so when dangerous goods (DG) are involved. One way to reduce the risk of DG derailments is through effective DG railway car placement along the train consist. This paper investigates the relationship between DG railway car placement and derailment for different route attributes and DG shipments. A model is presented for estimating the probability of derailment by position, based on the estimated point of derailment (POD) and the number of cars derailing. A DG placement model that considers in-transit derailment risk is shown to provide a sound scientific basis for effective DG marshalling in conventional rail hump yard operations.     

Principal component analysis applied to filtered signals for maintenance management

This paper presents an approach for detecting and identifying faults in railway infrastructure components. The method is based on pattern recognition and data analysis algorithms. Principal component analysis (PCA) is employed to reduce the complexity of the data to two and three dimensions. PCA involves a mathematical procedure that transforms a number of variables, which may be correlated, into a smaller set of uncorrelated variables called ‘principal components’. In order to improve the results obtained, the signal was filtered. The filtering was carried out employing a state–space system model, estimated by maximum likelihood with the help of the well‐known recursive algorithms such as Kalman filter and fixed interval smoothing. The models explored in this paper to analyse system data lie within the so‐called unobserved components class of models. Copyright © 2009 John Wiley & Sons, Ltd.     

Failure analysis and diagnostics for railway trackside equipment

In the future, the dependability of the railway system must be improved to accommodate higher train speeds, greater axle loads, and increased service frequency. One way of increasing the dependability is through improved maintenance and failure management. The collection and processing of information to ascertain the condition of railway infrastructure allows remedial action to be undertaken in a more efficient manner. This paper describes the development of a condition monitoring system based on pattern recognition for detecting and diagnosing point machine failures. It is shown that initially, when data is acquired from a point machine, it is difficult to detect faults. However, upon the application of a moving average filter, fault conditions can be more straightforwardly detected and diagnosed. Using data collected from a set of points under test it is shown that all potentially tested failure modes can be successfully detected and diagnosed.     

Risk-informed optimisation of railway tracks inspection and maintenance procedures

Nowadays, efforts are being made by the railway industry for the application of reliability-based and risk-informed approaches to maintenance optimisation of railway infrastructures, with the aim of reducing the operation and maintenance expenditures while still assuring high safety standards.In particular, in this paper, we address the use of ultrasonic inspection cars and develop a methodology for the determination of an optimal strategy for their use. A model is developed to calculate the risks and costs associated with an inspection strategy, giving credit to the realistic issues of the rail failure process and including the actual inspection and maintenance procedures followed by the railway company.A multi-objective optimisation viewpoint is adopted in an effort to optimise inspection and maintenance procedures with respect to both economical and safety-related aspects. More precisely, the objective functions here considered are such to drive the search towards solutions characterized by low expenditures and low derailment probability. The optimisation is performed by means of a genetic algorithm. The work has been carried out within a study of the Norwegian National Rail Administration (Jernbaneverket).     

RCM predictive maintenance of railway systems based on unobserved components models

Turnouts are probably the most important infrastructure elements of the railway system because of its effect on the system safety, reliability and quality of the service. In this paper, a predictive maintenance system in point mechanism, called RCM², has been implemented for increasing the quality service. RCM² is based on the integration of the two other types of maintenance techniques, namely Reliability Centred Maintenance (RCM₁) and Remote Condition Monitoring (RCM₂). The core of the system consists of an Unobserved Components model set-up in a State Space framework, in which the unknown elements of the system are estimated by Maximum Likelihood. The detection of faults in the system is based on the correlation estimate between a curve free from faults (that is, continuously updated as new curves are incorporated in the data base) with the current curve data. If the correlation falls far from one, a fault is at hand. The detection system is tested on a set of 476 experiments carried out by the Universities of Sheffield and Castilla-La Mancha.     

Composite real-time image processing for railways track profilemeasurement

Checking railway status is critical to guarantee high operating safety, proper maintenance schedule, and low maintenance and operating costs. This operation consists of the analysis of the rail profile and level as well as overall geometry and undulation. Traditional detection systems are based on mechanical devices in contact with the track. Innovative approaches are based on laser scanning and image analysis. This paper presents an efficient composite technique for track profile extraction with real-time image processing. High throughput is obtained by algorithmic prefiltering to restrict the image area containing the track profile, while high accuracy is achieved by neural reconstruction of the profile itself     

Rail defects: an overview

For about 150 years, the steel rail has been at the very heart of the world's railway systems. The rail works in a harsh environment and, as part of the track structure, it has little redundancy; thus, its failure may lead to catastrophic derailment of vehicles, the consequences of which can include death, injury, costs and loss of public confidence. These can have devastating and long‐lasting effects on the industry. Despite the advances being made in railway permanent way engineering, inspection and rail‐making technology, continually increasing service demands have resulted in rail failure continuing to be a substantial economic burden and a threat to the safe operation of virtually every railway in the world. This paper presents an overview of rail defects and their consequences from the earliest days of railways to the present day.     

Prognosis of gas turbine remaining useful life using particle filter approach

Gas turbines are commonly used in distributed power generation. Because of high speed nature, they require good maintenance for increased reliability and availability. Remaining useful life prediction is therefore an essential part of condition‐based maintenance to better foresee future state hence guaranteeing design efficiency, reduced maintenance cost, and improved safety. Gas turbines also contain a lot of sensors data that need to be processed for better prediction. In this paper, a probabilistic approach called particle filter is used for prediction. The proposed approach is tested using Turbofan degradation data provided by NASA as a benchmark problem. Meanwhile, through time the gas turbines experiences a change from normal state to degraded state attributed to aging, corrosion and erosion etc. Hence, in the context of abundant data, it is helpful to know the transition between states. For the same reason, the present paper suggests a statistical approach called Z‐test. The test results show that the proposed technique provides score and MAPE values of 559.9 and 21.6 respectively, comparable to past reported performance.     

A Study of Control Chart for Monitoring Exponentially Distributed Characteristics Based On Type‐II Censored Samples

In this paper, control charts for monitoring the exponential type‐II censoring samples are investigated. Such data are very common in many practical inspection scenarios in reliability context when items are replaced in groups after a period of time. The average time to signal, which involves both the number and the time of samples inspected until a signal occurs, is a good criterion to evaluate the performance of control charts. We propose an average time to signal‐unbiased control chart with known parameter and compare the proposed method with the traditional ones. The results indicate the proposed control chart is more sensitive to system deterioration. Then the effects of parameter estimation on the proposed control charts are evaluated. Because the control limits with estimated parameters result in more false alarms, an adjusted control chart with estimated parameters is proposed and the self‐starting control chart based on a sequential sampling scheme is adopted to solve the phase I problem. Finally, two examples are given to illustrate the implementation of the proposed approach. Copyright © 2017 John Wiley & Sons, Ltd.     

State‐Based Prognostics with State Duration Information

Failure prediction (i.e. prognostics) is critical for effective maintenance because it greatly impacts the competitiveness of organizations through its direct connection with operating and support costs, system availability, and operational safety. In recent years, research has focused on state‐based prognostics that forecast future progression by first identifying the current state. The duration spent in a state is a factor that influences the expected time to be spent in that state in the future; however, previous works on state‐based prognostics have ignored the effect of duration. Hidden Markov Models are the most famous state‐based prognostics methods in the literature with practicality problems such as computational complexity, requirement of excessive data, and dependency on initialization. This paper presents a new, simple and easy to implement state‐based prognostic method using state duration information. The presented method is applied to two real systems (railway turnout systems and drill bits), and the results are compared with the existing methods presented in the literature. The results show that the presented method outperforms the existing methods. Copyright © 2012 John Wiley & Sons, Ltd.     

Signal Processing for Remote Condition Monitoring of Railway Points

Abstract:  The dependability of railway points (turnouts or switches) is a key part of any railway system; the Potters Bar crash (10 May 2002) in the UK, which led to seven fatalities is a key example of a failure of this subsystem. Present maintenance of points involves overly frequent inspection by maintenance staff. A remote condition monitoring approach would lead to more efficient inspection routines and directed anticipatory maintenance trips. To assist the creation of a suitable fault-detection algorithm, the authors analysed existing force and current data for the 'as commissioned' case of a turnout and for situations with different fault conditions. Signal processing of this data revealed several different methods that can be used to distinguish between fully functioning points, and different fault conditions of the points. Specifically, clustering of statistical parameters and their application to wavelet levels and coefficients, provided clear discrimination of most critical faults. This demonstrates a good first step towards a condition monitoring-based maintenance regime for points that is both safer for passengers and maintenance personnel and that has the potential to be more effective and economical.     

Health state evaluation of an item: A general framework and graphical representation

This paper presents a general theoretical framework to evaluate the health state of an item based on condition monitoring information. The item's health state is defined in terms of its relative health level and overall health level. The former is evaluated based on the relative magnitude of the composite covariate and the latter is evaluated using a fractile life of the residual life distribution at the decision instant. In addition, a method is developed to graphically represent the degradation model, failure threshold model, and the observation history of the composite covariate. As a result, the health state of the monitored item can be intuitively presented and the evaluated result can be subsequently used in a condition-based maintenance optimization decision model, which is amenable to computer modeling. A numerical example is included to illustrate the proposed approach and its appropriateness.     

Applying RCM in large scale systems: a case study with railway networks

In 2000, the European Union founded a project named ‘RAIL: Reliability centered maintenance approach for the infrastructure and logistics of railway operation’ aimed to study the application of Reliability centered maintenance (RCM) techniques to the railway infrastructure. In this paper, we present the results obtained into the RAIL project, including a RCM methodology adapted to large infrastructure networks and a RCM toolkit to perform the RCM analysis, including cost aspects and maintenance planning guidance. This paper addresses the problem of applying RCM to large scale railway infrastructure networks to achieve an efficient and effective maintenance concept. Railways use nowadays very traditional preventive maintenance (PM) techniques, relying mostly on ‘blind’ periodic inspection and the ‘know-how’ of maintenance staff. RCM was seen as a promising technique from the beginning of the RAIL project because of several factors. First, technical insights obtained were better than the existing, so that several maintenance processes could be revised and adjusted. Second, the interdisciplinary approach used to make the analysis was very enriching and very encouraging for maintenance staff consulted. Third, using the RCM structured approach allowed to achieve well-documented analysis and clear decision diagrams. Our methodology includes some new features to overcome the problems of RCM observed in other projects. As a whole, our methodology and Computerized Maintenance Management Systems have produced two short-term benefits: reduction of time and paperwork because databases and tools are accessible through Internet, and creation of a permanent, accurate, and better collection of information. It will also have some long-term benefits: better PM will increase equipment life and will help to reduce corrective maintenance costs; Production will increase as unscheduled downtime decreases; purchase costs of parts and materials will be reduced; more effective and up-to-date record of inventory/stores reports; and better knowledge of the systems to help the company to chose those systems with the best LCC. The results have been corroborated with the application of our methodology to signal equipment in several railway network sections, as shown in this paper. Because of the successful conclusion of the project, the Spanish railway company (RENFE) and the German railway company (DB A.G.), not only decided to adopt RCM to enhance PM, but they have started a large project to implement Total Preventive Maintenance relying on the implantation of the RCM methodology.