<p>One way to reduce the lifecycle cost and environmental impact of a product in a circular economy is to extend its lifespan by either creating longer-lasting products or managing the <a>product properly during its use stage. Life extension of a product is envisioned to help better utilize </a>raw materials efficiently and slow the rate of resource depletion. In the case of manufacturing equipment (e.g., an electric motor on a machine tool), securing reliable service life as well as the life extension are important for consistent production and operational excellence in a factory. However, manufacturing equipment is often utilized without a planned maintenance approach. Such a strategy frequently results in unplanned downtime, owing to unexpected failures. Scheduled maintenance replaces components frequently to avoid unexpected equipment stoppages, but increases the time associated with machine non-operation and maintenance cost. </p><p><br></p> <p>Recently, the emergence of Industry 4.0 and smart systems is leading to increasing attention to predictive maintenance (PdM) strategies that can decrease the cost of downtime and increase the availability (utilization rate) of manufacturing equipment. PdM also has the potential to foster sustainable practices in manufacturing by maximizing the useful lives of components. In addition, advances in sensor technology (e.g., lower fabrication cost) enable greater use of sensors in a factory, which in turn is producing greater and more diverse sets of data. Widespread use of wireless sensor networks (WSNs) and plug-and-play interfaces for the data collection on product/equipment states are allowing predictive maintenance on a much greater scale. Through advances in computing, big data analysis is faster/improved and has allowed maintenance to transition from run-to-failure to statistical inference-based or machine learning prediction methods.</p><p><br></p> <p>Moreover, maintenance practice in a factory is evolving from equipment “health management” to equipment “wellness” by establishing an integrated and collaborative manufacturing system that responds in real-time to changing conditions in a factory. The equipment wellness is an active process of becoming aware of the health condition and of making choices that achieve the full potential of the equipment. In order to enable this, a large amount of machine condition data obtained from sensors needs to be analyzed to diagnose the current health condition and predict future behavior (e.g., remaining useful life). If a fault is detected during this diagnosis, a root cause of a fault must be identified to extend equipment life and prevent problem reoccurrence.</p><p><br></p> <p>However, it is challenging to build a model capturing a relationship between multi-sensor signals and mechanical failures, considering the dynamic manufacturing environment and the complex mechanical system in equipment. Another key challenge is to obtain usable machine condition data to validate a method.</p><p><br></p> <p>A goal of the proposed work is to develop a systematic tool for maintenance in manufacturing plants using emerging technologies (e.g., AI, Smart Sensor, and IoT). The proposed method will facilitate decision-making that supports equipment maintenance by rapidly detecting a worn component and estimating remaining useful life. In order to diagnose and prognose a health condition of equipment, several data-driven models that describe the relationships between proxy measures (i.e., sensor signals) and machine health conditions are developed and validated through the experiment for several different manufacturing-oriented cases (e.g., cutting tool, gear, and bearing). To enhance the robustness and the prediction capability of the data-driven models, signal processing is conducted to preprocess the raw signals using domain knowledge. Through this process, useful features from the large dataset are extracted and selected, thus increasing computational efficiency in model training. To make a decision using the processed signals, a customized deep learning architecture for each case is designed to effectively and efficiently learn the relationship between the processed signals and the model’s outputs (e.g., health indicators). Ultimately, the method developed through this research helps to avoid catastrophic mechanical failures, products with unacceptable quality, defective products in the manufacturing process as well as to extend equipment service life.</p><p><br></p> <p>To summarize, in this dissertation, the assessment of technical, environmental and economic performance of the AI-driven method for the wellness of mechanical systems is conducted. The proposed methods are applied to (1) quantify the level of tool wear in a machining process, (2) detect different faults from a power transmission mini-motor testbed (CNN), (3) detect a fault in a motor operated under various rotation speeds, and (4) to predict the time to failure of rotating machinery. Also, the effectiveness of maintenance in the use stage is examined from an environmental and economic perspective using a power efficiency loss as a metric for decision making between repair and replacement.</p><br>

No description available.

Das Erkennen und die Lokalisierung kritischer Risse ist ein wesentlicher Schlüssel für eine sichere und nachhaltige Bauwerksnutzung. In diesem Beitrag wird ein neuartiges, kostengünstiges Sensorsystem vorgestellt, das zur Echtzeit-Zustandsüberwachung von sowohl neuen als auch Bestandsbauwerken geeignet ist. Erste Ergebnisse zeigen, dass das System prinzipiell in der Lage ist, die Gesamtdehnung eines Bauteiles zu erfassen sowie auftretende Risse zu erkennen und zu lokalisieren. Die Erkennungsgenauigkeit hängt dabei von technischen Parametern ab, wodurch das System auf verschiedene Einsatzszenarien angepasst werden kann.

During the last decades, the power grid is getting rapidly digitalised in order to contribute to theestablishment of Smart Grids and evaluate efficiently the extracted bidirectional data from the powersystem infrastructure. This thesis focuses on the MV grid, since its design and operation have changedmainly because of distributed generation installations and the increased demand of information fromstakeholders. Thus, asset management constitutes a significant tool that can increase the reliability ofthe MV network’s operation and its level of control. Studies have shown that a maintenance planbased on condition monitoring of power system apparatuses would be more effective compared to theimplemented time-based scheduled maintenance.This project focuses on MV remotely controlled disconnectors since studies have shown that theirnumber of failures is double compared to manually operated ones. Since maneuverability andsecondary function are the causes of a major failure with the highest occurrence rate, motor currentmonitoring is studied in this thesis. Some devices that have the capability to monitor disconnectors’motor current, are presented. Additionally, the obtained max motor current measurements areevaluated through a parametric and a non-parametric statistical test. The main challenge of this thesisis to show whether the behaviour of motor current can be an indicator regarding to the disconnector’scondition status.Hence, the impact of different factors on the behaviour of motor current is investigated. It is concludedthat disconnectors without a failure during the studied period are more likely to have max motorcurrent measurements higher than 8A and especially in the interval [10-12]A. The difference in motorcurrent of disconnectors with a work order and without failure is more significant in 2015/2016. Itseems that under the aforementioned values of max motor current, a disconnector is more probable tohave the capability to operate properly. It is also concluded that in case of malfunction “Mellanläge”,the value of max motor current is lower than 8A with higher probability and it maybe indicates aproblem of the studied disconnector.Through the comparison in pairs, it could be concluded that the effect of the external environmentalconditions is not so high on the behaviour of disconnectors’ max motor current measurements. Incontrast, it seems that the implementation of a work order, the number of operations and if adisconnector is installed more northerly in Zone 3 play a more significant role on the behaviour of thisdisconnector’s max motor current measurements. Consequently, based on the aforementioned results itis shown that some of the investigated factors could constitute an indicator whether a disconnector ismore or less probable to have the capability to operate properly.Finally, it is calculated the reduction in the interruption cost that could be achieved in case ofimplementation of motor current monitoring on Vattenfall’s remotely controlled distributeddisconnectors. / Under de senaste årtiondena har kraftnät blivit snabbt digitaliserad För att bidra till upprättandet hosSmart Grids och effektivt utvärdera de extraherade dubbelriktade data från kraftsystemetsinfrastruktur. Denna exjobbsrapport fokuserar på MV-nätet, eftersom dess design och drift harförändrats främst på grund av distribuerade produktionsanläggningar och ökad efterfrågan påinformation från intressenter. Därför utgör ”asset management’’ ett viktigt verktyg som kan öka elnätstillförlitligheten och styrning. Studier har visat att elnäts underhåll baserad på tillståndsövervakningpå kraftsystemkomponenter skulle kunna vara effektivare jämfört med tidsbaserade schemalagdaunderhåll.Detta exjobb fokuserar på MV-fjärrstyrda frånskiljare eftersom studier har visat att deras felfrekvensär dubbelt högre jämfört med manuella. Eftersom problem i manövrerbarhet och sekundär funktionkan orsaka allvarliga fel med hög frekvens, har studien fokuserats på motorströmövervakningen idetta exjobb. Vissa produkter som har förmåga att övervaka frånskiljares motorström, presenteras.Dessutom utvärderas de maximala motorströmsmätningarna genom både parametriskt och ickeparametrisktstatistiskt test. Huvudutmaningen i denna avhandling är att utreda om motors strömmarkan vara en indikator för frånskiljares tillstånd.Olika faktorer hos motorströmmar har också undersökts. Det dras slutsatsen att frånskiljare utanmisslyckande manövern under den studerade perioden är mer benägna att ha maximalamotorströmmar högre än 8A och speciellt i intervallet [10-12] A. Skillnaden i motors strömmar hosfrånskiljare med arbetsorder och utan fel är mer signifikant under åren 2015/2016. Det verkar som attenligt ovan nämnda värden på max motorström, är en frånskiljare mer sannolikt att fungera korrekt.Det kommer också fram till att i händelse av "Mellanläge" är värdet av max motorströmmar lägre än8A med högre sannolikhet, detta kan kanske indikera ett problem hos frånskiljaren.Genom jämförelsen kan man dra slutsatsen att effekten av de yttre miljöförhållandena inte är så högpå maximala motorströmmar hos frånskiljare. Däremot verkar det som om genomförandet av enarbetsorder, antalet operationer och om en frånskiljare är installerad i zon 3 spelar en viktig roll föruppförandet av denna frånskiljares maximala motors strömmen. På grundval av det ovan nämndaresultatet framgår det att några av de undersökta faktorerna kan utgöra en indikator på att om enfrånskiljare är mer eller mindre sannolikt att ha förmågan att fungera korrekt.Slutligen visar beräkningar att minskningen av avbrottskostnaden kan uppnås vid genomförande avmotorströmövervakning på Vattenfalls fjärrstyrda distribuerade frånskiljare.

Condition monitoring (CM) is widely used in industry, and there is a growing interest in applying CM on rail vehicle systems. Condition based maintenance has the possibility to increase system safety and availability while at the sametime reduce the total maintenance costs.This thesis investigates the feasibility of using condition monitoring of suspension element components, in this case dampers, in rail vehicles. There are different methods utilized to detect degradations, ranging from mathematicalmodelling of the system to pure "knowledge-based" methods, using only large amount of data to detect patterns on a larger scale. In this thesis the latter approach is explored, where acceleration signals are evaluated on severalplaces on the axleboxes, bogieframes and the carbody of a rail vehicle simulation model. These signals are picked close to the dampers that are monitored in this study, and frequency response functions (FRF) are computed between axleboxes and bogieframes as well as between bogieframes and carbody. The idea is that the FRF will change as the condition of the dampers change, and thus act as indicators of faults. The FRF are then fed to different classificationalgorithms, that are trained and tested to distinguish between the different damper faults.This thesis further investigates which classification algorithm shows promising results for the problem, and which algorithm performs best in terms of classification accuracy as well as two other measures. Another aspect explored is thepossibility to apply dimensionality reduction to the extracted indicators (features). This thesis is also looking into how the three performance measures used are affected by typical varying operational conditions for a rail vehicle,such as varying excitation and carbody mass. The Linear Support Vector Machine classifier using the whole feature space, and the Linear Discriminant Analysis classifier combined with Principal Component Analysis dimensionality reduction on the feature space both show promising results for the taskof correctly classifying upcoming damper degradations. / Tillståndsövervakning används brett inom industrin och det finns ett ökat intresse för att applicera tillståndsövervakning inom spårfordons olika system. Tillståndsbaserat underhåll kan potentiellt öka ett systems säkerhet och tillgänglighetsamtidigt som det kan minska de totala underhållskostnaderna.Detta examensarbete undersöker möjligheten att applicera tillståndsövervakning av komponenter i fjädringssystem, i detta fall dämpare, hos spårfordon. Det finns olika metoder för att upptäcka försämringar i komponenternas skick, från matematisk modellering av systemet till mer ”kunskaps-baserade” metodersom endast använder stora mängder data för att upptäcka mönster i en större skala. I detta arbete utforskas den sistnämnda metoden, där accelerationssignaler inhämtas från axelboxar, boggieramar samt vagnskorg från en simuleringsmodellav ett spårfordon. Dessa signaler är extraherade nära de dämpare som övervakas, och används för att beräkna frekvenssvarsfunktioner mellan axelboxar och boggieramar, samt mellan boggieramar och vagnskorg. Tanken är att frekvenssvarsfunktionerna förändras när dämparnas skick förändras ochpå så sätt fungera som indikatorer av dämparnas skick. Frekvenssvarsfunktionerna används sedan för att träna och testa olika klassificeringsalgoritmer för att kunna urskilja olika dämparfel.Detta arbete undersöker vidare vilka klassificeringsalgoritmer som visar lovande resultat för detta problem, och vilka av dessa som presterar bäst med avseende på noggrannheten i prediktionerna, samt två andra mått på algoritmernasprestanda. En annan aspekt som undersöks är möjligheten att applicera dimensionalitetsminskning på de extraherade indikatorerna. Detta arbete undersöker också hur de tre prestandamåtten som används påverkas av typiska förändringar i driftsförhållanden för ett spårfordon såsom varierande exciteringfrån spåret och vagnkorgsmassa. Resultaten visar lovande prestanda för klassificeringsalgoritmen ”Linear Support Vector Machine” som använder hela rymden med felindikatorer, samt algoritmen ”Linear Discriminant Analysis” i kombination med ”Principal Component Analysis” dimensionalitetsreducering.

Our society moves towards digitalization and the industry is not an exception. Siemenshas developed a wireless condition monitoring device called Simotics Connect in order tohelp them to move forward in the world of digitalization. The Simotics Connect has threeinbuilt sensors. One for temperature, one for vibrations and one for magnetic flux density,a product that is new in the market. This master thesis has investigated its usability forthird party motors, which has not been done.Four areas were investigated, the status in the current market, creating a motorgeometry estimation based on nameplate data, presenting a temperature model to calculatea motor’s cross section temperature and, finally, proposed a stator current model using themagnetic field measurement.Market research has shown that a space for the Simotics Connect to thrive in mostdefinitely exists.The motor geometry estimation, that is based on preliminary electromagnetic sizing,creates a digital twin for the motor that has sufficient accuracy as a tool when calculatinge.g. temperature calculations but lacks accuracy for more advanced and sensitivecalculations e.g for magnetic flux density measurement usability.The temperature model that is presented shows great accuracy when calculating thecross section temperature in the stator but the accuracy decreases for the cross sectiontemperature in the rotor.A stator current model is proposed using a proportional relationship between themagnetic flux density and stator current. The results indicates a linear relationship, thoughusing the digital twin to calculate the proportional constant were concluded to not beaccurate enough. / Sammhället rör sig idag mot digitalisering och industrin är ej ett undantag. Siemens harutvecklat en trådlös underhållsmätare kallad Simotics Connect för att hjälpa dem strävamot en värld inom digitalisering. Simotics Connect hat tre inbyggda sensorer. En för temperatur,en för vibrationer och en för magnetisk flödestäthet, vilket är nytt på marknaden.Detta masterprojekt har undersökt användningen av Simotics Connect för tredjepartsmotorer,vilket ej har gjorts tidigare.Fyra områden undersöktes, statusen på den nuvarande marknaden, en motorgeometriuppskattningmodellbaserad på namnskylsdata, en temperaturmodell för att beräknamotorns tvärsnittstemperatur och, slutligen, en statorströmmodell som använder sig avmagnetiska flödestäthetsmätningen.Marknadsundersökningen har visat att det finns ett utrymme för Simotics Connectatt blomstra inom på den nuvarande marknaden.Motorns geometriska uppskattning, som är baserad i preliminär elektromagnetiskgeometribestämning, skapar en digital tvilling av motorn som är tillräckligt noggrann föratt aggera som ett verktyg vid t.ex. temperatursberäkningar men saknar noggrannhet förmer avancerade och känsliga beräkningar, t ex för användbarhet inom magnetisk flödestäthetsberäkningar.Temperaturmodellen som presenteras visar stor noggrannhet vid beräkning av statornstvärsnittstemperatur, men noggrannheten minskar för rotorns tvärsnittstemperatur.En statorströmmodell föreslås med ett proportionellt förhållande mellan magnetflödesdensitetenoch statorströmmen. Resultaten indikerar ett linjärt förhållande, men användandetav den digitala tvillingen för att beräkna proportionell konstant konstateras attinte vara tillräckligt noggrann metod.

In recent years, deep learning has been widely used in industry to solve many complex problems such as condition monitoring and fault diagnosis. Powertrain condition monitoring is one of the most vital and complicated problems in the automation industry since the condition of the drive affects its health, performance, and reliability. Traditional methods based on thermal modeling require expertise in drive geometry, heat transfer, and system identification. Although the data-driven deep learning methods could avoid physical modeling, they commonly face another predicament: models trained and tested on the same dataset cannot be applied to other different situations. In real applications, where the monitoring devices are different and the working environment changes constantly, poor model generalization will lead to unreliable predictions. Transfer learning, which adapts the model from the source domain to the target domain, can improve model generalization and enhance the reliability and accuracy of the predictions in real-world scenarios. This thesis investigates the applicability of mainstream transfer learning approaches in the context of drive condition monitoring using multiple datasets with different probability distributions. Through the comparison and discussion of models and results, the scope of their application, as well as their advantages and disadvantages are expounded. Finally, it is concluded that in the drive condition monitoring under the industrial background, the target domain data has enough labels, and it is not necessary to maintain the performance of the model in the source domain. In this case, fine-tuning based on the model trained in the source domain is the best method for this scenario. / Under de senaste åren har djupinlärning använts i stor utsträckning inom industrin för att lösa många komplexa problem såsom tillståndsövervakning och feldiagnos. Övervakning av drivlinans tillstånd är ett av de viktigaste och mest komplicerade problemen inom automationsindustrin eftersom driftens tillstånd påverkar dess hälsa, prestanda och tillförlitlighet. Traditionella metoder baserade på termisk modellering kräver expertis inom drivgeometri, värmeöverföring och systemidentifiering. Även om de datadrivna djupinlärningsmetoderna skulle kunna undvika fysisk modellering står de ofta inför en annan situation: modeller som tränats och testats på samma datauppsättning kan inte tillämpas på andra situationer. I verkliga applikationer, där övervakningsenheterna är olika och arbetsmiljön förändras ständigt, kommer dålig modellgeneralisering att leda till opålitliga förutsägelser. Transfer learning, som anpassar modellen från källdomänen till måldomänen, kan förbättra modellgeneraliseringen och öka tillförlitligheten och noggrannheten i förutsägelserna i verkliga scenarier. Denna avhandling undersöker tillämpligheten av traditionella överföringsinlärningsmetoder i samband med övervakning av drivtillstånd med hjälp av flera datauppsättningar med olika sannolikhetsfördelningar. Genom jämförelse och diskussion av modeller och resultat förklaras omfattningen av deras tillämpning, liksom deras fördelar och nackdelar. Slutligen dras slutsatsen att måldomändata vid övervakning av drivtillståndet under industriell bakgrund har tillräckligt med etiketter och att det inte är nödvändigt att upprätthålla modellens prestanda inom källdomänen. I det här fallet är finjustering baserad på modellen utbildad i källdomänen den bästa metoden för detta scenario. / Viime vuosina syväoppimista on käytetty laajalti teollisuudessa monien monimutkaisten ongelmien, kuten kunnonvalvonnan ja vikadiagnoosin, ratkaisemiseen. Voimansiirron kunnonvalvonta on yksi automaatioteollisuuden tärkeimmistä ja monimutkaisimmista ongelmista, koska taajuusmuuttajan kunto vaikuttaa sen kuntoon, suorituskykyyn ja luotettavuuteen. Perinteiset lämpömallinnukseen perustuvat menetelmät edellyttävät käyttögeometrian, lämmönsiirron ja järjestelmän tunnistamisen asiantuntemusta. Vaikka dataan perustuvat syväoppimismenetelmät voisivat välttää fyysisen mallinnuksen, ne kohtaavat usein toisen ahdingon: samalla tietojoukolla koulutettuja ja testattuja malleja ei voida soveltaa muihin erilaisiin tilanteisiin. Todellisissa sovelluksissa, joissa valvontalaitteet ovat erilaisia ja työympäristö muuttuu jatkuvasti, huono mallin yleistäminen johtaa epäluotettaviin ennusteisiin. Siirto-oppiminen, joka mukauttaa mallin lähdealueelta kohdealueelle, voi parantaa mallin yleistämistä ja parantaa ennusteiden luotettavuutta ja tarkkuutta todellisissa skenaarioissa. Tässä väitöskirjassa tutkitaan valtavirran siirto-oppimisen lähestymistapojen soveltuvuutta taajuusmuuttajan kunnonvalvonnan kontekstissa käyttämällä useita tietojoukkoja erilaisilla todennäköisyysjakaumilla. Mallien ja tulosten vertailun ja keskustelun avulla selitetään niiden soveltamisala sekä niiden edut ja haitat. Lopuksi päätellään, että taajuusmuuttajan kunnonvalvonnassa teollisen taustan alla kohdealueen tiedoilla on tarpeeksi tarroja, eikä mallin suorituskykyä tarvitse ylläpitää lähdealueella. Tässä tapauksessa lähdetoimialueella koulutettuun malliin perustuva hienosäätö on paras tapa tähän skenaarioon.

Grease is among the most widely used lubricants in rolling element bearings. Proper understanding of the effect of lubrication due to grease aging can provide a significant increase in the life of the engineering systems. However, at present, there is no sufficient understanding of the grease aging effect in rolling elements bearing. This restricts the optimal usage of the bearing and timely monitoring of the grease. The current research work tries to address this issue with an experimental investigation. This project studies the behavior of 4 types of greases in rolling elements bearings for various operating conditions by recording the temperature and acoustic emission data. The aged samples were prepared to keep in the oven at 150 °C for a series of time duration letting it go through the chemical changes and thermal degradation. Tests were carried out in a test rig with the different levels of oxidized greases for 5 hrs time. And the effects in bearing temperature, acoustic emission were recorded. This is an investigation to analyze the effects of grease composition and aging in rolling elements lubrication by means of acoustic emission and bearing temperature. The IR spectroscopy was carried from the samples collected from the oven in order to understand the change in lubricant composition. The results show that the grease with di-urea thickener and base oil of synthetic ether and polyolester gives the best bearing temperature and acoustic emission behavior compared to the other grease type. The possibility of using the acoustic emission and temperature data to monitor the grease aging is also presented. Along with this, the possibility of using the AE statistical methods, AE count method, and energy plot were also explored to relate with the degree of aging.

<p>  This paper explored the application of three machine learning models focused on predictive motor maintenance. Logistic Regression, Sequential Minimal Optimization (SMO), and NaïveBayes models. A comparative analysis of these models illustrated that while each had an accuracy greater than 95% in this study, the Logistic Regression Model exhibited the most reliable operation.</p>

Various improvements which have been made to the vehicle (reduced engine noise, reducedaerodynamic related NVH), have resulted in tire road noise as the dominant source of thevehicle interior noise. Generally, vehicle interior noise has two main sources, 1) travellinglow frequency excitation below 800 Hz from road surface through a structure- borne pathand 2) the high frequency (above 800 Hz) air-borne noise that is caused by air- pumpingnoise caused by tread pattern.The structure-borne waves of the circumference of the tire are generated by excitation atthe contact patch due to the road surface texture and characteristics. These vibrations arethen transferred from the sidewalls of the tire to the rim and then are transmitted throughthe spindle-wheel interface, resulting in high frequency vibration of vehicle body panels andwindows.The focus of this study is to develop several statistical-based models for analyzing the roadsurface and using them to predict the tire-road noise structure-borne component. In order todo this, a new methodology for sensing the road characteristics, such as asperities and roadsurface condition, were developed using virtual sensing and intelligent tire technology. In ad-dition, the spindle forces were used as an indicator to the structure-borne noise of the vehicle.Several data mining and multivariate analysis-based methods were developed to extractfeatures and to develop an empirical model to predict the power of structure-borne noiseunder different operational and road conditions. Finally, multiple data driven models-basedmodels were developed to classify the road types, and conditions and use them for the noisefrequency spectrum prediction. / Doctor of Philosophy / Multiple data driven models were developed in this study to use the vibration of the tirecontact patch as an input to sense some characteristics of road such as asperity, surface type,and the surface condition, and use them to predict the structure-borne noise power. Also,instead of measuring the noise using microphones, forces at wheel spindle were measuredas a metric for the noise power. In other words, a statistical model was developed that bysensing the road, and using the data along with other inputs, one can predict forces at thewheel spindle.