The hard equation of railway safety versus the high commercial profits can only be achieved through the use of new inspection methods supported by modern technologies. The track and its components can have different types of troubles, such as rail surface defects, broken sleepers, missing fasteners, and irregular ballast levels. Each component of the track infrastructure plays a significant role, where the failure or the absence of any of them can pave the way to undesired situations. The rail is designed to carry and direct the train, the sleepers are meant to maintain the level of the rail, and the ballast mission is to keep all components floating on the surface of the ground. The fasteners are used to fasten the rail to the sleepers, and therefore too many missing fasteners can lead to sever unsteady tracks, which can, in turn, result in derailment. Therefore, there is a high demand for advanced inspection methods to monitor the railway track and its components continuously. The presence of such advanced inspection models would help the railway industry avoid obstacles such as high operation and maintenance costs, dangerous accidents, and uncomfortable passenger's experience.   This master thesis aims to present an efficient method to classify the track and its components by combining image processing techniques and deep learning algorithms. This method was able to detect the missing fasteners in the set of images captured by a line camera, continuously monitoring the rail and its associated fasteners. The experimental results obtained in this thesis showed that the proposed method is efficient and robust for detecting the track and its components in complex environments. The thesis also discusses the idea of building one complete model that can process and classify all track components at once. The image processing technique was employed to extract different components of the track, individually: fasteners, rail, ballast, and sleepers. The model was trained and used to classify the state of the fasteners. Classification of other components of the track will be a part of the future work.

No description available.

Orientador: Aparecido Carlos Gonçalves / Resumo: Pares engrenados são elementos de transmissão de potência amplamente utilizados em máquinas e equipamentos, todavia as falhas catastróficas desses componentes são comuns e dispendiosas. A análise de vibrações está entre as técnicas de diagnóstico de defeitos incipientes utilizadas em manutenção preditiva, posto que a presença de uma falha altera o comportamento dinâmico do sistema e o estado de degradação pode ser detectado pelo monitoramento dos sinais de vibração. Na indústria atual, onde as aquisições de dados, tanto para controle de processos, quanto para o monitoramento das condições de integridade de equipamentos, são realizadas em tempo real, faz-se necessário o desenvolvimento de métodos que aumentem a confiabilidade das tomadas de decisões em relação à identificação, localização e prognóstico de falhas. O objetivo deste trabalho é desenvolver um modelo matemático de par de engrenagens que auxilie no monitoramento da condição e validar o modelo dinâmico com dados de vibração de um multiplicador de velocidades obtidos experimentalmente. Para tanto, foi elaborada uma metodologia baseada no modelo dinâmico de par engrenado com 6 graus de liberdade para simulação de sinais de vibração; nesse modelo, inclui-se erros geométricos no perfil do dente; de maneira analítica, simula-se uma a trinca do dente de uma das engrenagens que ocasiona a queda de rigidez em função do tempo; desenvolveu-se também um experimento com um multiplicador de velocidades; e, por fim, algumas técnic... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Spur gears are transmission power elements widely used in machinery, however catastrophic failures of this components are just as common and onerous. Vibration analysis is a technique, in among of others, that can be used in diagnostics of incipient damages, common in predictive maintenance, because they change the dynamic behavior of the mechanical system, and the degradation state can be detected by vibration signal or noise. In the current industry production, in which real-time data acquisition - whether for processes control, or for health condition monitoring of equipment - is the reality, it is necessary to develop auxiliary methods that provide high reliability to identification, localization and failure prognostics. In this work, the main objective is to provide a spur gears’ model-based methodology for condition-monitoring and to validate a dynamic model with experimental vibration data of a gearbox. Hence, a dynamic model of spur meshing gears was developed considering a 6 degrees of freedom and time-varying meshing stiffness to simulate vibrations signals; a tooth profile error was also included; in this analytical model, a straight crack was simulated by reducing the meshing stiffness in a tooth; experiments with a gearbox experimental set were run; and, some signal processing was apllied in the vibration data. The results allowed the model validation with the comparison between simulate and experimental signals, in time-domain and frequency-domain / Mestre

This thesis deals with the reliability and maintenance of structures that are damaged by shocks arriving randomly in time. The degradation is modeled as a cumulative stochastic point process. Previous studies mostly adopted expected cost rate criterion for optimizing the maintenance policies, which ignores practical implications of discounting of maintenance cost over the life cycle of the system.Therefore, detailed analysis of expected discounted cost criterion has been done, which provides a more realistic basis for optimizing the maintenance. Examples of maintenance policies combining preventive maintenance with age- based replacement are analyzed. Derivation for general cases involving preventive maintenance damage level have been discussed. Special cases are also considered.

This thesis deals with the reliability and maintenance of structures that are damaged by shocks arriving randomly in time. The degradation is modeled as a cumulative stochastic point process. Previous studies mostly adopted expected cost rate criterion for optimizing the maintenance policies, which ignores practical implications of discounting of maintenance cost over the life cycle of the system.Therefore, detailed analysis of expected discounted cost criterion has been done, which provides a more realistic basis for optimizing the maintenance. Examples of maintenance policies combining preventive maintenance with age- based replacement are analyzed. Derivation for general cases involving preventive maintenance damage level have been discussed. Special cases are also considered.

Företag kan använda sig av olika strategier för underhåll. Det kan vara avhjälpande underhåll som utförs först när ett fel uppkommer eller förebyggande underhåll. Ofta används en kombination av båda. Det förebyggande underhållet kan vara förutbestämt eller tillståndsbaserat. Fördelar med att använda sig av tillståndsbaserat underhåll är exempelvis att utbyte av enheter inte behöver ske i onödan utan först när en observation visar att ett fel är på väg att ske. Vid val av förebyggande underhåll kan RCM-metoden användas för att utröna vilka feltillstånd som kan uppstå och som orsakar funktionsfel. Val av förebyggande underhåll kan baseras på fakta om nya tekniker, felhistorik samt vilken utrustning och kompetens som finns tillgänglig. Volvo Cars i Skövde använder sig just nu av i stort sett likadant förebyggande underhåll på nya verktygsmaskiner som på gamla. Företaget använder sig av tillståndsbaserat underhåll på vissa komponenter och enheter. Det består då främst av inspektioner, subjektiva tillståndskontroller, och vibrationsövervakning på motorspindlar. Genom intervjuer framkommer att nya tekniker sällan införs och att lagda planer sällan ändras. Företaget är dock medvetet om att nya tekniker för tillståndsbaserat underhåll finns och är intresserat av att undersöka om ett utökat tillståndsbaserat underhåll är lämpligt på verktygsmaskiner. De tillståndsbaserade teknikerna som det talats om är främst ballbarmätning, övervakning av processparametrar och geometrisk verifiering. Ett underlag för att se om nya tekniker bör införas togs fram genom datainsamling av felhistorik på maskiner. Avgränsning gjordes genom att en fem år gammal bearbetningslinje för cylinderhuvuden studerades. Genom sortering av data från haverier ur underhållssystemet Maximo från de senaste åren och prioritering genom Paretoprincipen visade det sig att återkommande haverier på kulskruvar finns. Till komponenten finns ett tillståndsbaserat underhåll kopplat, den inspekteras en gång om året. Det är dock sällan som fel på komponenten upptäcks på inspektionen, bara fyra av tjugosju bytta kulskruvar de senaste fem åren är bytta efter anmärkning från inspektion. Genom att kartlägga komponentens haverier på femton verktygsmaskiner och när FU gjorts hittades flera förbättringsmöjligheter. Kostnaden för att byta kulskruv när väl fel uppstått är upp till tio gånger så stor jämfört med att byta den förebyggande. När fel uppstått har det medfört kassationer av producerade detaljer och lång stilleståndstid. Motiv för att införa ett bättre förebyggande underhåll finns därför framför allt i minskade kostnader och ökad tillgänglighet. Företaget rekommenderas att införa ballbarmätning som ett nytt tillståndsbaserat underhåll. Detta för att öka den objektiva kontrollen av mekaniska slitdelar. Mätmetoden är inte helt okänd för företaget och relativt lätt att införa. Den subjektiva kontrollen som görs idag bör göras om för att bättre fånga begynnelse till fel. Kontrollen kräver idag en hel del driftstoppstid vilket gjort att den inte utförts i tid och bör därför kortas ner. Företaget rekommenderas också att undersöka nya metoder för förebyggande underhåll kontinuerligt. Idag finns ingen anställd med uppdraget och för att utveckla underhållet måste företaget hålla sig uppdaterade på nya tekniker. / A company can use different strategies when performing maintenance. One strategy is corrective maintenance where maintenance is carried out after a failure has occurred. Another strategy is preventive maintenance. A combination of the two is often used. The preventive maintenance can be predetermined or condition based. Advantages with the condition based maintenance are e.g. that the replacement of parts can be planned according to observations indicating there’s an increasing risk of failure. When choosing preventive maintenance, the RCM method can be used to determine risk of failure modes and the cause of function failures. Decisions regarding the preventive maintenance should be based on knowledge in new techniques, history of failures and the equipment and competence available. Volvo Cars in Skövde is doing more or less the same preventive maintenance on machine tools regardless of whether it’s a new or old machine. The company is using condition based maintenance on some of the components and units. Mostly it consists of human inspections, a subjective control of the machine’s condition, and spindle vibration analysis. Through interviews it has been determined that new techniques are rarely implemented and that the decided maintenance plan for a machine is rarely changed. The company is aware of the development of new techniques for condition based maintenance and wants to investigate whether it is appropriate to evolve their condition based maintenance on machine tools. The techniques further investigated are measurement with Ball bar, monitoring of process parameters and geometrical verification. To make accurate decisions regarding the implementation of new techniques, a data collection of the history of frequent failures was done. To limit the amount of data a five year old processing line was studied. Data from the maintenance system Maximo was sorted by long failures from the recent years and by prioritizing with the Pareto principle it showed the recurring failures of ball screws. The component do have a condition based maintenance activity today, there is an inspection once a year. However, the inspection is rarely able to predict or find a failure on the ball screw. Four out of twenty-seven ball screws with fault have been changed after inspection over the last five years. By mapping the components failures on fifteen machine tools and when preventive maintenance has been done, several options for improvements were found. The cost of the replacement of a ball screw when a failure has already occurred is as much as ten times the cost of replacement before failure. This is caused by cost of scrap and long down time. A new, improved preventive maintenance task is therefore highly justified. The motif is both reducing the scrap cost related to failure and with increased availability. The company is recommended an investment in Ball bar as a new method for condition based maintenance. It should be used to increase the objective control of the mechanical parts of a machine tool. The method is not totally new for the company and relatively easy to implement. The current subjective control on the machine tools should be revised to increase the probability of finding degradation of functions. Today the activity takes rather long time and has therefore not been done in time, it should be shorter. The company is also recommended to investigate new methods for preventive maintenance continually. Today there is no employee with that mission and to evolve maintenance, the company has to be updated on new techniques.

This dissertation presents a model-based reasoning architecture with a two fold purpose: to detect and classify component faults from observable system behavior, and to generate fault propagation models so as to make a more accurate estimation of current operational risks. It incorporates a novel approach to system level diagnostics by addressing the need to reason about low-level inaccessible components from observable high-level system behavior. In the field of complex system maintenance it can be invaluable as an aid to human operators. The first step is the compilation of the database of functional descriptions and associated fault-specific features for each of the system components. The system is then analyzed to extract structural information, which, in addition to the functional database, is used to create the structural and functional models. A fault-symptom matrix is constructed from the functional model and the features database. The fault threshold levels for these symptoms are founded on the nominal baseline data. Based on the fault-symptom matrix and these thresholds, a diagnostic decision tree is formulated in order to intelligently query about the system health. For each faulty candidate, a fault propagation tree is generated from the structural model. Finally, the overall system health status report includes both the faulty components and the associated at risk components, as predicted by the fault propagation model.

abstract: Current economic conditions necessitate the extension of service lives for a variety of aerospace systems. As a result, there is an increased need for structural health management (SHM) systems to increase safety, extend life, reduce maintenance costs, and minimize downtime, lowering life cycle costs for these aging systems. The implementation of such a system requires a collaborative research effort in a variety of areas such as novel sensing techniques, robust algorithms for damage interrogation, high fidelity probabilistic progressive damage models, and hybrid residual life estimation models. This dissertation focuses on the sensing and damage estimation aspects of this multidisciplinary topic for application in metallic and composite material systems. The primary means of interrogating a structure in this work is through the use of Lamb wave propagation which works well for the thin structures used in aerospace applications. Piezoelectric transducers (PZTs) were selected for this application since they can be used as both sensors and actuators of guided waves. Placement of these transducers is an important issue in wave based approaches as Lamb waves are sensitive to changes in material properties, geometry, and boundary conditions which may obscure the presence of damage if they are not taken into account during sensor placement. The placement scheme proposed in this dissertation arranges piezoelectric transducers in a pitch-catch mode so the entire structure can be covered using a minimum number of sensors. The stress distribution of the structure is also considered so PZTs are placed in regions where they do not fail before the host structure. In order to process the data from these transducers, advanced signal processing techniques are employed to detect the presence of damage in complex structures. To provide a better estimate of the damage for accurate life estimation, machine learning techniques are used to classify the type of damage in the structure. A data structure analysis approach is used to reduce the amount of data collected and increase computational efficiency. In the case of low velocity impact damage, fiber Bragg grating (FBG) sensors were used with a nonlinear regression tool to reconstruct the loading at the impact site. / Dissertation/Thesis / Ph.D. Aerospace Engineering 2011

Examensarbetet genomfördes på AstraZeneca, Snäckviken hos fabriken API. Dess ångsystem har länge drabbats av oavsiktliga avbrott och detta har inte åtgärdats trots förebyggande insatser, vilket i sin tur har resulterat i produktionsbortfall. Syftet med denna studie är därmed att ta fram en långsiktig underhållsplan på komponentnivå som ska minska samtliga avbrott i ångsystemet. För att genomföra detta var det nödvändigt med litteraturstudier, avbrottanalys, nulägesanalys, besök på Snäckviken samt intervjuer. Studiens teoriavsnitt omfattades bland annat av väsentliga begrepp såsom underhåll, tidsbaserat- och tillståndsbaserat underhåll. Dessa termer bidrog till förståelsen av arbetet och framtagningen av resultatet och i sin tur även diskussionen. Det slutliga resultatet påvisade faktumet att det fanns tre komponenter som orsakade flest avbrott i systemet, och för en av dessa skapades det en underhållsplan. Planen omfattas av en underhållsbeskrivning, reservdelar/utbyteskomponenter, tidsutförande samt underhållsreperationer som inkluderar rekommenderad utförarkompetens. / The project was carried out at AstraZeneca, Snäckviken at the API factory. Its steam system has long been affected by unintentional interruptions and this has not been remedied despite preventive measures, which in turn has resulted in production losses. The purpose of this study is therefore to develop a long-term maintenance plan at component level that will reduce all interruptions in the steam system. To implement this, it was necessary with literature studies, current situation analysis, interruption analysis, visits to Snäckviken and interviews. The theoretical section of the study included, among other things, essential concepts such as maintenance, time-based- and condition-based maintenance. These terms contributed to the understanding of the study and the result, and in turn also the discussion. The result demonstrated the fact that there were three components that caused the most interruptions in the steam system, and for one of these a maintenance plan was created. The plan is covered by a maintenance description, spare parts / replacement

Yes / Wind Energy published by John Wiley & Sons Ltd. Maintenance is essential in keeping wind energy assets operating efficiently. With the development of advanced condition monitoring, diagnostics and prognostics, condition-based maintenance has attracted much attention in the offshore wind industry in recent years. This paper models various maintenance activities and their impacts on the degradation and performance of offshore wind turbine components. An integrated maintenance strategy of corrective maintenance, imperfect time-based preventive maintenance and condition-based maintenance is proposed and compared with other traditional maintenance strategies. A maintenance simulation programme is developed to simulate the degradation and maintenance of offshore wind turbines and estimate their performance. A case study on a 10-MW offshore wind turbine (OWT) is presented to analyse the performance of different maintenance strategies. The simulation results reveal that the proposed strategy not only reduces the total maintenance cost but also improves the energy generation by reducing the total downtime and expected energy not supplied. Furthermore, the proposed maintenance strategy is optimised to find the best degradation threshold and balance the trade-off between the use of condition-based maintenance and other maintenance activities. / UK Engineering and Physical Sciences Research Council (EPSRC). Grant Number: EP/P009743/1