Departamento de Engenharia Electromecânica
Permanent URI for this community
Browse
Browsing Departamento de Engenharia Electromecânica by Field of Science and Technology (FOS) "Engenharia e Tecnologia::Engenharia e Gestão Indústrial"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- Industrial Sensors Online Monitoring and Calibration Through Hidden Markov ModelsPublication . Martins, Alexandre Daniel Batista; Cardoso, António João Marques; Farinha, José Manuel TorresThis thesis aims to demonstrate a methodology able to diagnosis, through the Hidden Markov Model (HMM), the health state of production equipment, as well as the calibration state of sensors reading equipment. Through a well-defined methodology, the observations collected by the sensors are optimised to give input into a HMM, that are translated into hidden states, which represent the diagnosis of the equipment under study, being: State 1 - "Good working"; State 2 - "Warning"; State 3 - "Fault/Uncalibrated". After collecting the data, it goes through a cleaning process that will improve its quality and integrity. Then, a feature generation phase is performed. This phase is extremely important because the information can be managed for the desired equipment. It is through this stage that we can distinguish the diagnosis between the production equipment and the reading equipment. Next, a dimensional reduction of the data is performed, through Principal Component Analysis (PCA) and an extraction of new features that, although in smaller amounts, have more information each one. Then, the new data matrix is applied to a Clustering, performed by K-means, with the objective of grouping similar data within the same group. This will cause good working data to be in one cluster and bad working data to be in a different cluster. These clusters will be the optimized observable states that give input to the HMM. Subsequently, the HMM translates the observable states into a sequence of hidden states that represent the diagnosis of the equipment. Besides the methodology available to detect different types of information from the same data set, it has more capabilities, such as: imputing values in time series with few samples through Deep Neural Network (DNN) methods, namely the Multi-Layer Perceptron (MLP) model; performing the equipment health status prognosis through the Deep Neural Network (DNN), the Gated Recurrent Unit (GRU).
- Manutenção Lean em Ambiente de Indústria 4.0Publication . Mendes, David Samuel Fernandes Tavares; Gaspar, Pedro Miguel de Figueiredo Dinis Oliveira; Navas, Helena Victorovna GuitissPara que as empresas, independentemente da sua dimensão, se mantenham competitivas e ativas num mercado cada vez mais global, devem aumentar a produtividade, economizar recursos e melhorar os seus processos organizacionais. Com o aumento da automação e digitalização, um dos focos é colocado na gestão de ativos e manutenção, como sendo funções de agregação de valor ainda mais significativas. Os requisitos para o setor da manutenção, assim como para o pessoal integrante desta área, mudou consideravelmente ao longo dos anos por causa do aumento da digitalização e automação, e pela complexidade dos ativos. Para que esta área se enquadre na realidade atual, é necessária uma rápida reação e adaptação da estratégia de manutenção. Desta forma, o incremento das ferramentas inerentes à Filosofia Lean (FL) e às tecnologias inerentes à Indústria 4.0 (I4.0) são de todo importantes, já que permitiram às empresas melhorar o funcionamento do chão de fábrica. A FL surge como uma cultura promissora e geradora de resultados efetivos, tendo como objetivo a eliminação dos desperdícios e a criação de valor. Ligada à FL, assim como ao departamento da manutenção e produção, encontra-se a metodologia Total Productive Maintenance (TPM). Esta tem como objetivo potenciar o desempenho das empresas, através da realização de ações específicas, na contribuição para o aumento da eficiência produtiva, diminuição de desperdício, acidentes, defeitos, paragens e falhas ao longo do processo produtivo. Por outro lado, com a introdução de novas tecnologias no setor industrial, surge a necessidade deste se adaptar às alterações do mercado, de modo a fazer frente às necessidades de um mercado cada vez mais competitivo e global. Neste contexto, o presente trabalho apresenta um modelo que integra três conceitos: Manutenção, FL e a I4.0, para melhorar a gestão e todas as atividades inerentes da manutenção, passando pelo planeamento da manutenção até à intervenção da mesma. O modelo é composto por uma arquitetura constituída por sensores, gateway, e protocolos de comunicação: internet sem fios e o Bluetooth Low Energy (BLE) para assegurar a contínua e ininterrupta monitorização de vários indicadores relevantes da manutenção. Uma vez desenvolvido o modelo, e de forma a ilustrar o seu potencial em termos de aplicação e de validação em contexto industrial e real, é desenvolvido um estudo de caso numa fábrica de rações, mais concretamente aplicado a um tapete transportador que opera na área de transporte e movimentação de granéis. Constatou-se que a implementação deste modelo junto com a consciencialização e participação de todos os elementos que operam na área de transporte e movimentação de rações, trouxe inúmeros benefícios, como: o aumento da disponibilidade (aumento de funcionamento em 7%), melhoria no conhecimento e desempenho dos colaboradores que operam nesta área, intervenções e plano de manutenção mais ajustado à realidade diária de operação do tapete transportador, melhorando os tempos (redução do tempo médio de reparações em 53%) de paragens programadas, entre outros benefícios. Os resultados mostram que o modelo proposto é uma ferramenta com mais-valias para as empresas. Possibilita aos responsáveis pelos serviços da manutenção fundamentarem as suas decisões com base na análise de dados que podem ser visualizados de uma forma rápida e acessível. Com base na análise do histórico do tapete transportador conjugado com os dados adquiridos pelo sistema de monitorização contínua, foi possível observar a sua utilidade no dia-a-dia dos responsáveis da manutenção, através da seleção e utilização de parâmetros específicos da gestão da manutenção.
- A Predictive Maintenance Model based on Multivariate Analysis with Artificial IntelligencePublication . Rodrigues, João Carlos Antunes; Cardoso, António João Marques; Farinha, José Manuel TorresThe maintenance of physical assets is increasingly assuming a leading role in the success of companies, whether industrial or services. The pressure of budgets, combined with a strict maintenance policy, gives companies competitive advantages in an increasingly demanding market. This PhD thesis emerged with the aim of solving some Predictive Maintenance problems. The research also aims to respond to gaps identified in the state of the art as the prediction and classification of the long-term state of equipment. The present work describes novel contributions to the state of the art of lubricating oils. The results show that it is possible to create good models using Artificial Neural Networks (ANN) to classify oils considering all variables. Models can even possibly rank lubricants with a small error. Using Principal Component Analysis (PCA), the relevance of each variable for oil analysis was determined, thus providing a better insight into the importance of each parameter under analysis. The results also show that a neural model does not need to use all variables. Principal Component Analysis also allowed the creation of an algorithm that calculates the percentage of degradation of a lubricating oil, from the manufacturer's standard references so, this algorithm works for any industrial lubricant. It is noteworthy that lubricant classifiers (PCA, RNA and Human Experts) were compared with each other, having converged in more than 90%, which confirms the reliability of the classification. The developed algorithms can support industries, in a general way, since they provide information that is easy to interpret, and helps them to make decisions about the most appropriate time to replace oil in the assets. Through exhaustive research of the state of the art in prediction and industrial forecast, it was concluded that, to date, there is no published model for predicting failures with such a long-time span, which demonstrates the innovation and contribution of the present research for science and for the competitiveness of the industry. It should be noted that the developed algorithms have already been tested and applied, showing in general a prediction error below 10%. The current project has a short-term prediction model and another long-term prediction model, both using neural networks. The long-term forecasting model can predict asset failures 90 days in advance, which allows industries to make scheduled stops on their assets, thus avoiding losses resulting from unscheduled stops. Adequate feature input vectors in Artificial Neural Networks using sliding windows along time series greatly improved the training, leading to the conclusion that overlapping windows allow the network to learn in less iterations. Larger windows make it easier to capture peak values, but the optimal window size needs to be determined experimentally. Regarding short-term forecasting, it has been shown that data resampling can make the forecasting process faster, as it considerably reduces the input data set in the network. An algorithm was also developed to determine the expected equipment state through classification of the predicted sensor values. This way, the algorithm will be able to classify the probable state of the assets in the future in normal operation, alert or malfunction. This PhD thesis is very important for the industrial area, especially in the areas of maintenance, safety, quality, sustainability and efficiency, as it will maximize the availability of assets, contributing to the success of the Quality Management Systems and Maintenance Management Systems. Such positive increments in several sectors will have as main consequence the reduction of costs, increase of equipment availability and improvement of quality, what will become a competitive differentiator for the industries, because they will be able to approach the market with more competitive prices and quality. Part of the work was published in scientific articles and presented at several congresses and received the distinction of best presentation award in TEPEN 2021 & IncoME-VI congress in China. It also received the 2nd Young Engineer Innovation Award- PIJE 2021, from Ordem dos Engenheiros, Portugal.
- Production Optimization Indexed to the Market Demand Through Neural NetworksPublication . Mateus, Balduíno Patrício César; Cardoso, António João Marques; Farinha, José TorresConnectivity, mobility and real-time data analytics are the prerequisites for a new model of intelligent production management that facilitates communication between machines, people and processes and uses technology as the main driver. Many works in the literature treat maintenance and production management in separate approaches, but there is a link between these areas, with maintenance and its actions aimed at ensuring the smooth operation of equipment to avoid unnecessary downtime in production. With the advent of technology, companies are rushing to solve their problems by resorting to technologies in order to fit into the most advanced technological concepts, such as industries 4.0 and 5.0, which are based on the principle of process automation. This approach brings together database technologies, making it possible to monitor the operation of equipment and have the opportunity to study patterns of data behavior that can alert us to possible failures. The present thesis intends to forecast the pulp production indexed to the stock market value.The forecast will be made by means of the pulp production variables of the presses and the stock exchange variables supported by artificial intelligence (AI) technologies, aiming to achieve an effective planning. To support the decision of efficient production management, in this thesis algorithms were developed and validated with from five pulp presses, as well as data from other sources, such as steel production and stock exchange, which were relevant to validate the robustness of the model. This thesis demonstrated the importance of data processing methods and that they have great relevance in the model input since they facilitate the process of training and testing the models. The chosen technologies demonstrated good efficiency and versatility in performing the prediction of the values of the variables of the equipment, also demonstrating robustness and optimization in computational processing. The thesis also presents proposals for future developments, namely in further exploration of these technologies, so that there are market variables that can calibrate production through forecasts supported on these same variables.