Arbetet beskriver möjligheten att kunna utföra prediktivt underhåll med hjälp av information frånCOMTRADE störningsfiler. En mjukvarualgoritm som hämtar tidsförlopp för händelser som uppstårvid störningar och kan ge indikationer på ifall reläer eller strömbrytare faller utanför optimalaarbetsförhållanden har utvecklats. På detta sett kan underhållsarbete utföras vid behov vilket kanspara tid och pengar för att inte göras efter schemalagda tider.Tillsammans med uppdragsgivare från Megger och Ellevio utfördes arbetet med syfte att utvecklaen programvara som stöd för prediktivt underhåll. Programvaran kunde ta ut tidshändelser förregistrerade störningar och kunde hantera flertalet scenarion för vilka typer av information somfunnits tillgängligt ur filen. En användare har tillgång till en automatisk algoritm som gör analysav filen och ett manuellt verktyg där vidare analyser kan göras ifall utfallet från algoritmen inte ärgodtyckligt.Trender över tid är något som finns möjlighet att få ut ur algoritmen, men det kräver en större mängddataset än som varit tillgänglig under arbetet. / The work describes the opportunities to perform preventive maintenance with the help of informationfrom COMTRADE disturbance files. A software algorithm was developed which collects disturbancedata and gives indications if equipment are not working within optimal conditions.Using thisinformation preventive maintenance can be performed based on need instead of scheduling to savetime and money.Together with supervisors from involved companies a software was developed to be used as a supportfor preventive maintenance. The software can extract disturbance times and handle multiple scenariosbased on information collected from disturbance files. A user has access to a algoritm that createsautomatical analysis of the COMTRADE file and a manual tool for extensive analysis when the algoritmdoes not give proper results.Trends over time can be analysed with the algortim, this do require a larger amount of data than whatwas available during the work.

To face climate change and transform the electricity supply to an environmentally friendly generation, wind plays an important role. Due to a yearly increase in installed wind power turbines, in the European Union, the need for maintenance increases as well. For reducing the maintenance times and, with that, the standstill time and resulting economical losses, the time for troubleshooting must be reduced. This work aims to show that the troubleshooting process of wind turbines can be reduced to a minimum with the automation. This can be reached by creating a scatter plot of the active power over the wind speed curve and investigating the data points where the turbine is not performing as it should. The data is extracted from a wind farm located in Finland for the wind year 2021. The methodological approach taken in this study is to build a normalised threshold power curve and compare it to monthly binned power curves of two selected turbines. The deviation between the threshold and the monthly power curve is investigated, and the months with a high deviation are chosen for further analysis, which includes the separation of the outlier data into four different categories. The outlier in bins with a higher deviation than 5 % are selected. The four categories are further inspected, and the reasons for the curtailments are extracted and analysed. In summary, these results show that the analysis of curtailment reasons based on a scatter plot of the active power of a wind turbine is possible. Moreover, the troubleshooting process can be reduced in time. Due to practical constraints, this work cannot provide an analysis with a threshold power curve built with data from more than one year. This makes the results less objective since fluctuations, which can occur during only one year, cannot be minimised.

In this paper, a statistical method is developed to improve predictive maintenance on railway track. The problem tackled is being able to predict when the next maintenance event should take place to guarantee a certain track quality class. To solve the problem, The prediction is made using track measurement data exclusively, with no maintenance history to support the data analysis. The dataset consists of track measurements taken over eleven years and 170 kilometres on the Bothnia line in Northern Sweden. Different track degradation models and machine learning approaches are discussed and implemented. In the end, the tool developed was able to predict track degradation with an error within reasonable bounds of the typical maintenance limit. This will allow an operator to predict the recommended date for the next maintenance event at all locations using only historical track measurements as an input and little to no user intervention on the programme. / I denna uppsats utvecklas en statistisk metod för att förbättra förebyggande underhåll av järnvägsspår. Det problem som utreds är att kunna förutsäga när nästa underhållsarbete bör äga rum för att garantera en viss kvalitetsklass på spåret. För att lösa problemet användes endast spårmätningar utan någon underhållshistorik som stöd för dataanalysen. Data består av spårmätningar som utförts under elva år och 170 kilometer på Botniabanan i norra Sverige. Olika modeller för spårförsämring och metoder för maskininlärning diskuteras och implementeras. I slutändan så kunde det utvecklade verktyget förutsäga spårets nedbrytning med ett fel som låg inom rimliga gränser av den typiska underhållsgränsen. Sammanfattningsvis så kommer detta att göra det möjligt för en operatör att förutsäga det rekommenderade datumet för nästa underhållsarbete på alla platser med endast historiska spårmätningar som indata och med liten eller ingen användarintervention i programmet.

No description available.

<p>Condition monitoring supported with artificial intelligence, cloud computing, and industrial internet of things (IIoT) technologies increases the feasibility of predictive maintenance (PdM). However, the cost of traditional sensors, data acquisition systems, and the information technology expert knowledge required to inform and implement PdM challenge the industry. This thesis proposes a hybrid condition monitoring system (CMS) architecture consisting of a distributed, low-cost IIoT-sensor solution. The CMS uses micro-electro-mechanical system (MEMS) microphones for data acquisition, edge computing for signal preprocessing, and cloud computing, including artificial neural networks (ANN) for higher-level information processing. The higher-level information processing includes condition detection and time-based prediction capabilities to inform PdM strategies. The system’s feasibility is validated using a testbed for reciprocating linear-motion axes.</p>

A non-invasive, on-line method for detection of mechanical (rotor, bearings eccentricity) and stator winding faults in a 3-phase induction motors from observation of motor line current supply input. The main aim is to avoid the consequence of unexpected failure of critical equipment which results in extended process shutdown, costly machinery repair, and health and safety problems. This thesis looks into the possibility of utilizing machine learning techniques in the field of condition monitoring of electromechanical systems. Induction motors are chosen as an example for such application. Electrical motors play a vital role in our everyday life. Induction motors are kept in operation through monitoring its condition in a continuous manner in order to minimise their off times. The author proposes a model free sensor-less monitoring system, where the only monitored signal is the input to the induction motor. The thesis considers different methods available in literature for condition monitoring of induction motors and adopts a simple solution that is based on monitoring of the motor current. The method proposed use the feature extraction and Support Vector Machines (SVM) to set the limits for healthy and faulty data based on the statistical methods. After an extensive overview of the related literature and studies, the motor which is the virtual sensor in the drive system is analysed by considering its construction and principle of operation. The mathematical model of the motor is used for analysing the system. This is followed by laboratory testing of healthy motors and comparing their output signals with those of the same motors after being intentionally failed, concluding with the development of a full monitoring system. Finally, a monitoring system is proposed that can detect the presence of a fault in the monitored machine and diagnose the fault type and severity / Ministry of Higher Education, Libya; Switchgear & Instruments Ltd.

The main purpose of this research is to present a solution that enable to manage efficient and reliable way, all of the information in relation to control, tracking and the hospital equipment maintenance. So, was taken as an object of study of Engineering Department of the Central Hospital of the Air Force of Peru, which presents a lot of administrative deficiencies character in its internal processes of reception, record and closing of Work Orders as well as the preventive and corrective maintenance of the hospital equipment of the HCFAP.The contemplated solution comprises from analysis and design to the development of some use cases more significant of the application. / El presente trabajo de investigación tiene como propósito fundamental presentar una solución que permita administrar de forma eficiente y confiable toda la información respecto al control, seguimiento y mantenimiento del equipamiento hospitalario. Para ello se tomó como objeto de estudio al Departamento de Ingeniería del Hospital Central de la Fuerza Aérea del Perú, el cual presenta muchas deficiencias de carácter administrativo en sus procesos internos de recepción, registro y cierre de Órdenes de Trabajo así como el mantenimiento preventivo y correctivo de los equipos hospitalarios del HCFAP. La solución contemplada abarca desde el análisis y diseño hasta el desarrollo de algunos casos de uso más significativos de la aplicación.

La mise en place d’une politique de maintenance prévisionnelle est un défi majeur dans l’industrie qui tente de réduire le plus possible les frais relatifs à la maintenance. En effet, les systèmes sont de plus en plus complexes et demandent un suivi de plus en plus poussé afin de rester opérationnels et sécurisés. Une maintenance prévisionnelle nécessite d’une part d’évaluer l’état de dégradation des composants du système, et d’autre part de pronostiquer l’apparition future d’une panne. Plus précisément, il s’agit d’estimer le temps restant avant l’arrivée d’une défaillance, aussi appelé Remaining Useful Life ou RUL en anglais. L’estimation d’une RUL constitue un réel enjeu car la pertinence et l’efficacité des actions de maintenance dépendent de la justesse et de la précision des résultats obtenus. Il existe de nombreuses méthodes permettant de réaliser un pronostic de durée de vie résiduelle, chacune avec ses spécificités, ses avantages et ses inconvénients. Les travaux présentés dans ce manuscrit s’intéressent à une méthodologie générale pour estimer la RUL d’un composant. L’objectif est de proposer une méthode applicable à un grand nombre de cas et de situations différentes sans nécessiter de modification majeure. De plus, nous cherchons aussi à traiter plusieurs types d’incertitudes afin d’améliorer la justesse des résultats de pronostic. Au final, la méthodologie développée constitue une aide à la décision pour la planification des opérations de maintenance. La RUL estimée permet de décider de l’instant optimal des interventions nécessaires, et le traitement des incertitudes apporte un niveau de confiance supplémentaire dans les valeurs obtenues. / Predictive maintenance strategies can help reduce the ever-growing maintenance costs, but their implementation represents a major challenge. Indeed, it requires to evaluate the health state of the component of the system and to prognosticate the occurrence of a future failure. This second step consists in estimating the remaining useful life (RUL) of the components, in Other words, the time they will continue functioning properly. This RUL estimation holds a high stake because the precision and accuracy of the results will influence the relevance and effectiveness of the maintenance operations. Many methods have been developed to prognosticate the remaining useful life of a component. Each one has its own particularities, advantages and drawbacks. The present work proposes a general methodology for component RUL estimation. The objective i to develop a method that can be applied to many different cases and situations and does not require big modifications. Moreover, several types of uncertainties are being dealt With in order to improve the accuracy of the prognostic. The proposed methodology can help in the maintenance decision making process. Indeed, it is possible to select the optimal moment for a required intervention thanks to the estimated RUL. Furthermore, dealing With the uncertainties provides additional confidence into the prognostic results.

Este trabalho apresenta abordagens para a avaliação do fenômeno da Degradação Induzida pelo Potencial (PID do inglês Potential Induced Degradation) em módulos e instalações fotovoltaicas de c-Si. Nos ensaios em laboratório, a IEC TS 62804-1:2015 foi aplicada e ações adicionais são sugeridas como forma de adaptação da especificação técnica para o acompanhamento da degradação durante o ensaio e para melhor indicar a propensão do equipamento a se recuperar das consequências da aparição de PID. Nos ensaios em campo, avaliou-se a solução convencional do mercado de reverter a degradação através de circuitos anti-PID, além de apresentar a aplicação de técnicas de detecção do fenômeno em sistemas operacionais. A abordagem teórica e os resultados práticos mostram que o procedimento de aferição de tensões individuais de operação é um método útil para detectar PID. Os estudos de caso apresentados indicam que esta metodologia é eficaz inclusive na detecção precoce do fenômeno para diferentes topologias de células fotovoltaicas de c-Si. / This work presents approaches to assess the Potential Induced Degradation (PID) on c-Si photovoltaic modules and installations. The IEC TS 62804-1:2015 was applied to the laboratory tests and some additional actions are suggested. The adaptation of the technical specification aims to monitor the degradation rates during the tests and also to consider the capacity of the photovoltaic modules to recover from the degradation. In the field detection methodologies are presented and anti-PID circuits were also tested. The theoretical approach reveals that individual voltage measurements are useful to detect PID even in its early stage, as can be seen on the case studies presented.

Com o aumento do uso de sistemas elétricos, eletrônicos e programáveis em aplicações de diversos domínios, tais como entretenimento, realização de transações financeiras, distribuição de energia elétrica, controle de processos industriais e sinalização e controle em transporte de passageiros e carga, é essencial que as políticas de manutenção utilizadas sejam capazes de minimizar os custos associados a eventuais falhas que afetem negativamente os serviços providos. Ao longo das últimas décadas, foi sedimentada a tendência de que a adoção de técnicas de manutenção preditiva representa uma das abordagens mais viáveis e promissoras para que falhas de sistemas utilizados em diversas aplicações possam ser detectadas antes de elas efetivamente ocorrerem. Considerando-se que uma parcela significativa dos estudos recentes na área de manutenção preditiva de sistemas apresenta como limitação o custo elevado para se instalar uma infraestrutura específica para realizar a coleta de dados que serão usados para dar suporte à predição das falhas futuras de um sistema, o modelo proposto no presente estudo visa permitir que os índices de dependabilidade e as falhas futuras de sistemas elétricos, eletrônicos e programáveis sejam estimados utilizando-se dados já disponíveis de falhas e manutenções passadas. Para tanto, foram empregadas técnicas como processos estocásticos, filtragem Kalman e modelos de incorporação de dados de histórico preconizados no padrão internacional RIAC-HDBK-217Plus. Como principal conclusão do presente trabalho, é possível ressaltar que foi possível atingir, com o modelo proposto, o objetivo de suporte à manutenção preditiva de sistemas elétricos, eletrônicos e programáveis a partir do uso de dados preexistentes de histórico operacional; no entanto, foram constatadas limitações no grau de utilização prática do modelo em situações nas quais a quantidade dos dados de histórico disponíveis para consulta é pequena. / With the increased use of electrical, electronic and programmable systems in various application fields such as entertainment, financial transactions, power distribution, industrial process control and signaling and control of transportation modes, it is essential for the maintenance policies used in those systems to be able to minimize the costs of any faults that may adversely affect the services provided. Over the past decades, the use of predictive maintenance techniques has shown to be a viable and promising approach to detect faults before they actually occur in systems used in different application fields. Considering that a significant part of the recent scientific research in the area of predictive maintenance usually demands high-cost infrastructure to be installed to support the acquisition of all the data that will be used to calculate the prediction of future faults of a system, the model proposed within this study was designed to allow both dependability levels and future faults of electrical, electronic and programmable systems to be estimated using past faults and maintenance data that may already be available. For this purpose, techniques such as stochastic processes, Kalman filtering and models prescribed within the international standard RIAC-HDBK-217Plus to incorporate history data to dependability calculation were used. As the main conclusion of this study, it is possible to highlight that the main objective of the model proposed, related to its ability to support predictive maintenance of electrical, electronic and programmable systems through the use of pre-existing operating history data, has been reached; nevertheless, limitation of practical use of the model was verified in situations in which not enough operating data is available.