• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 30
  • 9
  • 5
  • 4
  • 3
  • 2
  • 1
  • Tagged with
  • 68
  • 68
  • 68
  • 33
  • 15
  • 15
  • 15
  • 14
  • 14
  • 13
  • 13
  • 13
  • 11
  • 10
  • 9
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
61

Tillståndsövervakning av rullningslager med hjälp av E-näsa

Kristiansen, Pontus, Postnikov, Roman January 2018 (has links)
I dagsläget finns det ingen standardiserad metod för att mäta en enhets tillstånd medhjälp av dofter. Vid tillståndsövervakning av rullningslager är vibrationsmätning denmest dominanta metoden. I samband med vibrationsmätning används i vissa falltemperaturövervakning för att få en bättre insikt på rullningslagrets tillstånd. I det härarbetet undersöks de om en elektronisk näsa kan avgöra ett rullningslagers tillstånd.Innan några mätningar påbörjas monterades en elektronisk näsa ihop i ett hölje sombestår av ett kretskort, metalloxid-sensorer och en fläkt för att styra dofter med ettkonstant flöde mot sensorerna. Den elektroniska näsan styrs av en Arduino Nanomikrokontroller. Utöver e-näsan sättes en enhet ihop tillhörande två temperaturgivareoch en luftfuktighetsgivare som styrs av en Arduino UNO. Enhetens syfte är att kunnakontrollera de rådande förhållandena vid mätningar och för att leta någon form avkorrelation mot e-näsan vid eventuella utslag. Förstörande prover av kullager utfördesför att se om e-näsan reagerar innan ett lagerhaveri. Testerna gjordes i en öppen samtsluten miljö och tre stycken olika oljor används för att smörja lagret. Detta för att seom e-näsan reagerar olika beroende på vilken olja som används. En undersökningutförs ifall den elektroniska näsan kan separera på de tre oljorna som används ilagertesterna. För att utvärdera mätresultaten används Excel och Minitab, därprincipalkomponentanalyser genomförs på all mätdata. Efter att alla lagerprover harverkställts utfördes en uppföljning av rullningslagrena för att studera deras tillstånd,detta genom ett optiskt mikroskop.Det framgår i rapporten att med hjälp av analysmetoden PCA syns det att denelektroniska näsan kunde skilja på hydraulolja, motorolja och växellådsolja. Utslag iPCA för de olika mätserierna blev inte identiska men det blev tydligaklusterindelningar hos samtliga mätserier. Genomförd studie visade att med delagerhaveri samt temperaturer går det inte att avgöra ett kullagers tillstånd med hjälpav en elektronisk näsa. Eftersom att de specifika gas-sensorerna som användes till enäsaninte gav någon form av utslag vid mätningarna. Den elektroniska näsanreagerade däremot vid totalhaveri av kullager, vilket är för sent i ett förebyggandeunderhållsperspektiv. Detta medförde att den elektroniska näsan inte kan användas förtillståndsövervakning av det specifika kullagret som användes vid denna studie. / At present, there is no standardized method of measuring a device's condition with thehelp of odors. In condition monitoring of rolling bearings, vibration measurement isthe most dominant method. In case of vibration measurement, temperature monitoringis used in some cases to get a better insight into the condition of the bearing. In thiswork, it is investigated whether an electronic nose can determine the condition of arolling bearing.Before any measurements began, an electronic nose is assembled in a housingconsisting of a circuit board, metal oxide sensors and a fan for stearing odors with aconstant flow towards the sensors. The electronic nose is controlled by an ArduinoNano which is a microcontroller. In addition to the e-nose, a unit is connected to twotemperature sensors and a humidity sensor controlled by an Arduino UNO. The unit'spurpose is to monitor the status and to look for any kind of correlation with the e-nosein case of any possible findings. Destructive specimens of ball bearings are performedto see if the e-nose responds prior to a bearing failure. Tests are conducted in an openand closed environment and three different oils are used to lubricate the bearings.This to see if the e-nose acts differently depending on the oil that is used. Aninvestigation is conducted if the electronic nose can separate the three different typesof oils that is used in the destructive bearing tests. To evaluate the measurementresults, Excel and Minitab are used, where principal component analysis is performedon all measurement data. After all bearing tests have been performed, a follow-up ofthe rolling bearings condition is performed, this through an optical microscope.The report shows that using the PCA analysis method, it appears that the electronicnose could distinguish between hydraulic oil, engine oil and gear oil. In the PCA forthe different measurement series the results did not become identical, but clusterdivisions became clear in all measurement series. Completed study showed that withthese bearing failures and temperatures, it is not possible to determine the condition ofthis ball bearer using an electronic nose. Because the specific gas sensors used for thee-nose did not give any kind of impact during the measurements. On the other hand,the electronic nose responded to a total failure of a ball bearing, which is too late in apreventative maintenance perspective. Therefore, the electronic nose cannot be usedfor condition monitoring of the specific ball bearing used in this study.
62

Développement de stratégies de maintenance prévisionnelle de systèmes multi-composants avec structure complexe / Predictive maintenance strategies for multi-component systems with complex structure

Nguyen, Kim Anh 16 October 2015 (has links)
Aujourd'hui, les systèmes industriels deviennent de plus en plus complexes. Cette complexité est due d’une part à la structure du système qui ne se résume pas à des structures classiques en fiabilité, d’autre part à la prise en compte de composants présentant des phénomènes de dégradation graduelle que des systèmes de monitoring permettent de surveiller. Ceci mène à l'objectif de cette thèse portant sur le développement des stratégies de maintenance prévisionnelle pour des systèmes multi-composants complexes. Les politiques envisagées proposent notamment des stratégies de regroupement de composants permettant de tirer des dépendances économiques identifiées. Des facteurs d'importance permettant de prendre en compte la structure du système et la dépendance économique sont développés et combinés avec les évaluations de fiabilité prévisionnelle des composants pour l’élaboration de règles de décision de regroupement. De plus, un couplage des règles de décision de maintenance et de gestion des stocks est également étudié. L’ensemble des études menées montrent l’intérêt de la prise en compte de la fiabilité prévisionnelle des composants, des dépendances économiques et de la structure complexe du système dans l'aide à la décision de maintenance et de gestion des stocks. L’avantage des stratégies développées est vérifié en les comparant à d’autres existantes dans la littérature / Today, industrial systems become more and more complex. The complexity is due partly to the structure of the system that cannot be reduced to classic structure reliability (series structures, parallel structures, series-parallel structures, etc), secondly the consideration of components with gradual degradation phenomena that can be monitored. This leads to the main purpose of this thesis on the development of predictive maintenance strategies for complex multi-component systems. The proposed policies provide maintenance grouping strategies to take advantage of the economic dependence between components. The predictive reliability of components and importance measures allowing taking into account the structure of the system and economic dependence are developed to construct the grouping decision rules. Moreover, a joint decision rule for maintenance and spare parts provisioning is also studied.All the conducted studies show the interest in the consideration of the predictive reliability of components, economic dependencies as well as complex structure of the system in maintenance decisions and spare parts provisioning. The advantage of the developed strategies is confirmed by comparing with the other existing strategies in the literature
63

Maintenance modelling, simulation and performance assessment for railway asset management / Modélisation, simulation et évaluation de performances de la maintenance des infrastructures ferroviaires

Shang, Hui 25 September 2015 (has links)
Les travaux présentés dans ce manuscrit visent à développer des modèles de coût/performances pour améliorer les décisions de maintenance sur les infrastructures ferroviaires exploitées dans un environnement de plus en plus contraint: trafic accru, détérioration accélérée, temps de maintenance réduits. Les modèles de maintenance proposés sont construits à base de réseaux de Petri colorés ; ils sont animés par simulation de Monte Carlo pour estimer les performances (en termes de coût et de disponibilité) des politiques de maintenance considérées. Ils sont développés aux niveaux "composant" et "réseau", et plusieurs problèmes de maintenance différents sont étudiés. Au niveau "composant" (rail), des politiques de maintenance mettant en jeu différents niveaux d'information de surveillance sont comparées pour montrer l'intérêt de surveiller la détérioration graduelle du composant. L'effet de l'existence d'un délai de maintenance est également étudié pour les politiques conditionnelle et périodique. Au niveau système (ligne), une maintenance mettant en jeu différents types d'inspections complémentaires (automatique ou visuelle) est d'abord étudiée. On s'intéresse ensuite au cas de figure où l'évolution de la détérioration dépend du mode d'utilisation et de la charge de la voie : le problème de maintenance étudié vise alors à définir un réglage optimal des paramètres d'exploitation de la voie (vitesse limite) et de maintenance (délai d'intervention) / The aim of this thesis research work is to propose maintenance models for railways infrastructures that can help to make better maintenance decisions in the more constrained environment that the railway industry has to face, e.g. increased traffic loads, faster deterioration, longer maintenance planning procedures, shorter maintenance times. The proposed maintenance models are built using Coloured Petri nets; they are animated through Monte Carlo simulations to estimate the performance of the considered maintenance policies in terms of cost and availability. The maintenance models are developed both at the component and network levels, and several different maintenance problems are considered. At the rail component level, maintenance policies with different level of monitoring information (level of gradual deterioration vs binary working state) are compared to show the benefits of gathering monitoring information on the deterioration level. The effect of preventive maintenance delays is also investigated for both condition-based inspection policies and periodic inspection policies on a gradually deteriorating component. At the line level, a maintenance policy based on a two-level inspection procedure is first investigated. Then, considering the case when the deterioration process depends on the operation modes (normal vs limited speed), a maintenance optimization problem is solved to determine an optimal tuning of the repair delay and speed restriction
64

Prediktivní systém údržby obráběcích strojů s využitím vibrodiagnostiky / Predictive machine tools maintenance system with the use of vibrodiagnostics

Semotam, Petr January 2018 (has links)
This diploma thesis concerns issues of predictive and condition based maintenance system of machine tools with using a vibrodiagnostics. It studies and researches its impacts through the basic processes of the maintenance system and characterizes the vibration diagnosis as its tool and mean. There is also described a process of putting condition based maintenance into practice in the practical part of the thesis. The development is realized at Siemens Ltd. Brno with all its requirements and aspects such as a maintenance audit which means the decision on the suitability of condition based maintenance within the current maintenance system, technical analysis as a part of introduction of vibration diagnosis and the practical example of acquiring, recording and assessment of measured vibration. Prior to the end the economic evaluation of the planned predictive maintenance system and the design of the general model of development and implementation of the maintenance system into practice are included.
65

Prognostics for Condition Based Maintenance of Electrical Control Units Using On-Board Sensors and Machine Learning

Fredriksson, Gabriel January 2022 (has links)
In this thesis it has been studied how operational and workshop data can be used to improve the handling of field quality (FQ) issues for electronic units. This was done by analysing how failure rates can be predicted, how failure mechanisms can be detected and how data-based lifetime models could be developed. The work has been done on an electronic control unit (ECU) that has been subject to a field quality (FQ) issue, determining thermomechanical stress on the solder joints of the BGAs (Ball Grid Array) on the PCBAs (Printed circuit board assembly) to be the main cause of failure. The project is divided into two parts. Part one, "PCBA" where a laboratory study on the effects of thermomechanical cycling on solder joints for different electrical components of the PCBAs are investigated. The second part, "ECU" is the main part of the project investigating data-driven solutions using operational and workshop history data. The results from part one show that the Weibull distribution commonly used to predict lifetimes of electrical components, work well to describe the laboratory results but also that non parametric methods such as kernel distribution can give good results. In part two when Weibull together with Gamma and Normal distributions were tested on the real ECU (electronic control unit) data, it is shown that none of them describe the data well. However, when random forest is used to develop data-based models most of the ECU lifetimes of a separate test dataset can be correctly predicted within a half a year margin. Further using random survival forest it was possible to produce a model with just 0.06 in (OOB) prediction error. This shows that machine learning methods could potentially be used in the purpose of condition based maintenance for ECUs.
66

Towards the Implementation of Condition-based Maintenance in Continuous Drug Product Manufacturing Systems

Rexonni B Lagare (8707320) 12 December 2023 (has links)
<p dir="ltr">Condition-based maintenance is a proactive maintenance strategy that prevents failures or diminished functionality in process systems through proper monitoring and management of process conditions. Despite being considered a mature maintenance management strategy in various industries, condition-based maintenance remains underutilized in pharmaceutical manufacturing. This situation needs to change, especially as the pharmaceutical industry continues to shift from batch to continuous manufacturing, where the implementation of CBM as a maintenance strategy assumes a greater importance.</p><p dir="ltr">This dissertation focused on addressing the challenges of implementing CBM in a continuous drug product manufacturing system. These challenges stem from the unique aspects of pharmaceutical drug product manufacturing, which includes the peculiar behavior of particulate materials and the evolutionary nature of pharmaceutical process development. The proposed solutions to address these challenges revolve around an innovative framework for the practical development of condition monitoring systems. Overall, this framework enables the incorporation of limited process knowledge in creating condition monitoring systems, which has the desired effect of empowering data-driven machine learning models.</p><p dir="ltr">A key feature of this framework is a formalized method to represent the process condition, which is usually vaguely defined in literature. This representation allows the proper mapping of preexisting condition monitoring systems, and the segmentation of the entire process condition model into smaller modules that have more manageable condition monitoring problems. Because this representation methodology is based on probabilistic graphical modelling, the smaller modules can then be holistically integrated via their probabilistic relationships, allowing the robust operation of the resulting condition monitoring system and the process it monitors.</p><p dir="ltr">Breaking down the process condition model into smaller segments is crucial for introducing novel fault detection capabilities, which enhances model prediction transparency and ensures prediction acceptance by a human operator. In this work, a methodology based on prediction probabilities was introduced for developing condition monitoring systems with novel fault detection capabilities. This approach relies on high-performing machine learning models capable of consistently classifying all the initially known conditions in the fault library with a high degree of certainty. Simplifying the condition monitoring problem through modularization facilitates this, as machine learning models tend to perform better on simpler systems. Performance indices were proposed to evaluate the novel fault detection capabilities of machine learning models, and a formal approach to managing novel faults was introduced.</p><p dir="ltr">Another benefit of modularization is the identification of condition monitoring blind spots. Applying it to the RC led to sensor development projects such as the virtual sensor for measuring granule flowability. This sensor concept was demonstrated successfully by using a data-driven model to predict granule flowability based on size and shape distribution measurements. With proper model selection and feature extraction guided by domain expertise, the resulting sensor achieved the best prediction performance reported in literature for granule flowability.</p><p dir="ltr">As a demonstration exercise in examining newly discovered faults, this work investigated a roll compaction phenomenon that is usually concealed from observation due to equipment design. This phenomenon results in the ribbon splitting along its thickness as it comes out of the rolls. In this work, important aspects of ribbon splitting were elucidated, particularly its predictability based on RC parameters and the composition of the powder blend used to form the ribbon. These findings have positive ramifications for the condition monitoring of the RC, as correspondence with industrial practitioners suggests that a split ribbon is desirable in some cases, despite being generally regarded as undesirable in the limited literature available on the subject.</p><p dir="ltr">Finally, this framework was primarily developed for the pharmaceutical dry granulation line, which consists of particle-based systems with a moderate level of complexity. However, it was also demonstrated to be feasible for the Tennessee Eastman Process (TEP), a more complex liquid-gas process system with a greater number of process faults, variables, and unit operations. Applying the framework resulted in machine learning models that yielded one of the best fault detection performances reported in literature for the TEP, while also introducing additional capabilities not yet normally reported in literature, such as fault diagnosis and novel fault detection.</p>
67

The environmental and social impact from digitization in buildings : A case study of the transformation and current conditions on the University hospital of Northern Sweden

Melén, Matilda, Wenhov, Alma January 2022 (has links)
To improve sustainability, social, environmental and economic aspects needs to be considered. The most optimal result appears when all three aspects are balanced equally, this is however often overseen by private investors, who focuses only on reaching economic sustainability at the expense of social and environmental sustainability. Building digitization is one way to potentially improve the sustainability of a building socially, environmentally and economically. Focusing on the aspects that often are neglected, this thesis aims to investigate if digitizing a building improves social and environmental sustainability. The investigation is made by evaluating the implementation of a digital building automation tool from selected social and environmental sustainability criteria at the University hospital of Northern Sweden. This by performing an interview survey with the maintenance organisation and the tenants in the building, as well as performing CO2-e calculations on emissions connected to energy usage, transportation and production of HVAC-products. The evaluation indicated that the implementation had resulted in improved sustainability in the studied building, both socially and environmentally. Showing that digitizing a building improves social and environmental sustainability. The social sustainability had been positively affected from increased efficiency and effectiveness of the maintenance work in the building and improved well-being of the maintenance staff. However, the tenants were not completely satisfied when asked if reported errors were being solved, but on the other hand had the maintenance organisation experienced an improvement in satisfaction among the tenants since the implementation of the digital building automation tool. Furthermore, the tenants were generally more satisfied than dissatisfied with the indoor climate, except for experienced low temperatures in the winter and dry air. The environmental sustainability had been improved from a reduction in emitted CO2-e, generated from less energy usage and minimized transportation connected to maintenance operations. Furthermore, an estimation on increased technical lifetime of HVAC-products demonstrated on a potential further reduction in emitted CO2-e during the building's whole life span. Finally, the evaluation identified two combined effects between social and environmental sustainability. First, the increased efficiency and effectiveness of the maintenance work was one direct factor for the decrease in CO2-e emissions connected to transportation. Second, the tenants in the building expressed that they would feel prouder of their choice of employer if their employer focused more on reducing their climate impact, which motivates to work with environmental sustainability to achieve satisfaction and moreover an improved social sustainability.  The results of this case study indicate that digital building automation improves the social and environmental sustainability of a building, strengthening the statement on potential sustainability improvements from building digitization. For property owners wanting to increase their building's sustainability, digital building automation is therefore a proposed course of action. However, the performance on sustainability and the balance between the different aspects should continuously be evaluated, as the study showed that further improvements on the social and environmental sustainability still could be made. Property owners working towards an improved sustainability through digitization will both see long term positive effects on people's health, as well as help fulfilling the climate goals in the Paris agreement, resulting in a more sustainable world for present and future generations. / För att skapa en bättre hållbarhet måste hänsyn tas till både den sociala, miljömässiga samt den ekonomiska aspekten. Fokuset på dessa tre aspekter bör balanseras lika för att uppnå optimal hållbarhet, dock efterföljs detta inte vanligtvis av privata investerare som ofta endast fokuserar på att uppnå ekonomisk hållbarhet på bekostnad av den sociala- och miljömässiga hållbarheten. En byggnads hållbarhet kan potentiellt förbättras genom digitalisering av byggnaden, vilket kan förbättra den sociala, miljömässiga och ekonomiska hållbarheten. Genom att fokusera på de aspekter som ofta blir nedprioriterade undersöker denna studie om den sociala och miljömässiga hållbarheten i en byggnad ökar vid digitalisering. Detta genom att utvärdera implementeringen av ett digitalt verktyg på Norrlands Universitetssjukhus från några utvalda kriterier för social och miljömässig hållbarhet. Den sociala hållbarheten utvärderas med hjälp av en intervjustudie med underhållspersonalen och hyresgästerna i byggnaden, medan den miljömässiga hållbarheten utvärderades genom att beräkna CO2-e utsläpp kopplade till energianvändning, transporter samt produktionen av HVAC-produkter. Utvärderingen indikerade att implementeringen hade resulterat i en ökad social och miljömässig hållbarhet i byggnaden, vilket visar att en byggnads sociala och miljömässiga hållbarhet kan förbättras genom digitalisering. Den sociala hållbarheten hade ökat på grund av en ökad effektivitet i underhållsarbetet samt ett förbättrat välmående hos underhållspersonalen. Dock visade undersökningen att hyresgästerna i byggnaden inte var helt nöjda med arbetet kring felanmälningar, underhållsorganisationen hade dock upplevt att hyresgästerna var nöjdare efter implementeringen av det digitala verktyget än de var innan. Hyresgästerna var också mer nöjda än missnöjda med inomhusklimatet, förutom att de upplevde låg inomhustemperatur på vintern och att luften var torr. Den miljömässiga hållbarheten hade förbättrats genom en minskning av CO2-e utsläpp från minskad energianvändning och minskade transporter kopplade till underhållsarbetet. Den estimerade ökningen av den tekniska livslängden på HVAC-produkter visade också på potentiella minskningar av CO2-utsläpp under byggnadens hela livslängd. Denna studie identifierade också två kombinerade effekter mellan social- och miljömässig hållbarhet. Den första var att genom ökad effektivitet i arbetet för underhållspersonalen så minskade även CO2-e utsläppen från transporterna. Den andra var att hyresgästerna i byggnaden uttryckte att de skulle känna sig stoltare över sitt val av arbetsgivare om deras arbetsgivare fokuserade mer på att minska sin klimatpåverkan, vilket motiverar att arbeta med miljömässighållbarhet för att uppnå ökad tillfredsställelse hos hyresgästerna och därav ökad social hållbarhet.  Resultaten från denna fallstudie indikerar att digital fastighetsautomation förbättrar den sociala och miljömässiga hållbarheten av en byggnad, vilket styrker argumentet att en byggnads hållbarhet potentiellt kan förbättras genom digitalisering. För fastighetsägare som vill öka en byggnads hållbarhet är digital fastighetsautomation därför rekommenderat. Hållbarheten samt balansen mellan de olika hållbarhetsaspekterna behöver däremot kontinuerligt utvärderas, eftersom denna studie har visat att den sociala- och miljömässigahållbarheten fortfarande kan förbättras. Fastighetsägare som arbetar med att öka hållbarheten i byggnader genom digitalisering kommer uppleva långvariga positiva effekter för människors hälsa samt så kommer de bidra till att uppnå klimatmålen i Parisavtalet. Detta resulterar i en mer hållbar värld för nutida och framtida generationer.
68

Fallstudie om Prediktivt och Tillståndsbaserat Underhåll inom Läkemedelsindustrin / Case study regarding Predictive and Condition-based Maintenance in the Pharmaceutical Industry

Redzovic, Numan, Malki, Anton January 2022 (has links)
Underhåll är en aktivitet som varje produktion vill undvika så mycket som möjligt på grund av kostnaderna och tiden som anknyts till den. Trots detta så är en väl fungerande underhållsverksamhet väsentlig för att främja produktionens funktionssäkerhet och tillgänglighet att tillverka. En effektiv underhållsorganisation går däremot inte ut på att genomföra mer underhåll än vad som egentligen är nödvändigt utan att genomföra underhåll i rätt tid. På traditionellt sätt så genomförs detta genom att ersätta slitage delar och serva utrustningen med fastställda mellanrum för att förebygga att haveri, vilket kallas för förebyggande underhåll. De tidsintervaller som angivits för service bestäms av leverantörerna och grundar sig i en generell uppskattning av slitagedelarnas livslängd utifrån tester och analys. Till skillnad från att köra utrustningen till den går sönder som kallas för Avhjälpande underhåll så kan underhåll genomföras vid lämpliga tider så att det inte påverkar produktion och tillgänglighet. Men de tidsintervall som leverantörerna rekommenderar till företagen garanterar inte att slitage delen håller sig till det intervallet, delarna kan exempelvis rasa tidigare än angivet eller till och med hålla längre. Av denna anledning är det naturliga steget i underhållets utveckling att kunna övervaka utrustningens hälsa i hopp om att kunna förutspå när och varför ett haveri ska uppstå. Den här typen av underhåll kallas för tillståndsbaserat och prediktivt underhåll och medför ultimat tillgänglighet av utrustning och den mest kostnadseffektiva underhållsorganisationen, då god framförhållning och översikt uppnås för att enbart genomföra underhåll när det behövs. Det som gör tillståndsbaserat och prediktivt underhåll möjligt är den fjärde industriella revolutionen “Industri 4.0” och teknologierna som associeras med den som går ut på absolut digitalisering av produktionen och smarta fabriker. Teknologier som IoT, Big Dataanalys och Artificiell Intelligens används för att koppla upp utrustning till nätet med hjälp av givare för att samla in och lagra data som ska användas i analyser för att prognosera dess livslängd. Uppdragsgivaren AstraZeneca i Södertälje tillverkar olika typer av läkemedel som många är livsviktiga för de patienter som tar dessa mediciner. Om AstraZenecas produktion står still på grund av fel i utrustningen kommer det inte enbart medföra stora ekonomiska konsekvenser utan även påverka de människor som med livet förlitar sig på den medicin som levereras. För att försäkra produktionens tillgänglighet har AstraZeneca gjort försök att tillämpa tillståndsbaserat och prediktivt underhåll men det är fortfarande enbart i startgroparna. Eftersom ventilation är kritisk del av AstraZeneca produktion då ett fel i ventilationssystemet resulterar i totalt produktionsstopp i byggnaden förens problemet åtgärdas och anläggningen sanerats blev det även rapportens fokusområde. Arbetets uppgift går därför ut på att undersöka möjligheter för AstraZeneca att utveckla deras prediktiva och tillståndsbaserat underhåll på deras ventilationssystem, för att sedan kunna identifiera och presentera förslag på åtgärder. Dessa förslag analyserades sedan med hjälp av verktygen QFD-Matris och Pugh-Matris för att kunna uppskatta vilket förslag som är mest kostnadseffektivt, funktions effektivt samt vilket förslag som kommer tillföra mest nytta för underhållet på AstraZeneca. / Maintenance is an activity that every production wants to avoid as much as possible due to the costs and the time associated with it. Despite this, a well-functioning maintenance operation is essential to promote the production's availability to manufacture and operational reliability. Running an efficient maintenance operation is not about carrying out more maintenance than is necessary but carrying out the right amount of maintenance at the right time. Traditionally speaking this is done by replacing worn parts and servicing the equipment at set intervals to prevent breakdowns, this method is called preventive maintenance. The intervals specified for service are determined by the suppliers and are based on general estimates of the service life for the spare parts from test and analytics. Preventive maintenance allows for maintenance to be carried out at appropriate time to not affect production and availability unlike running the equipment until breakdown, which is called reactive maintenance. However, these intervals that the suppliers recommend do not guarantee that the parts adhere to the given interval, the part can for example break down earlier than expected or even outlast its prescribed lifetime. Because of this, the natural step in the development of maintenance is giving companies the ability to monitor the health of the equipment in hope of being able to predict potential breakdowns. This is what Condition-Based and predictive maintenance is and it provides the ultimate availability of equipment and the most cost-effective maintenance organization, because the good foresight and overview allows maintenance to be carried out only when needed. The fourth industrial revolution “Industry 4.0”, absolute digitalization of production, smart factories and all the technologies associated with this is what makes this type of maintenance possible. Technologies such as IoT, Big Data Analytics and Artificial Intelligence are used to connect equipment to the network using sensors so that data can be stored and collected to be analyzed to forecast the lifespan of parts and equipment. AstraZeneca in Södertälje manufactures different types of medicine, many of which are vital for the patients who take them. If their production comes to a standstill due to equipment failure, it will not only have major financial consequences but also greatly affect the people who rely on the medicine offered with their lives. To ensure the availability of production, AstraZeneca has made attempts to apply condition-based and predictive maintenance, but it is still only in its infancy. Since ventilation is a critical part of AstraZeneca's production, as a failure here will result in a total production stoppage for the building affected and will not resume before the problem is remedied and the plant is decontaminated, it also became the report's focus area. The task at hand is therefore to investigate the opportunities AstraZeneca must develop their predictive and condition-based maintenance for their ventilation systems, in order to be able to present proposals for measures. The proposals will then be analyzed using tools like the QFD-Matrix and the Pugh-Matrix in order to estimate which is more cost effective, function effective and which one will bring the most benefit to AstraZeneca.

Page generated in 0.1041 seconds