| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| Dissertação de Mestrado | 1.08 MB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
As empresas nacionais deparam-se com a necessidade de responder ao mercado com uma
grande variedade de produtos, pequenas séries e prazos de entrega reduzidos. A
competitividade das empresas num mercado global depende assim da sua eficiência, da sua
flexibilidade, da qualidade dos seus produtos e de custos reduzidos. Para se atingirem estes
objetivos é necessário desenvolverem-se estratégias e planos de ação que envolvem os
equipamentos produtivos, incluindo: a criação de novos equipamentos complexos e mais
fiáveis, alteração dos equipamentos existentes modernizando-os de forma a responderem às
necessidades atuais e a aumentar a sua disponibilidade e produtividade; e implementação de
políticas de manutenção mais assertiva e focada no objetivo de “zero avarias”, como é o caso
da manutenção preditiva.
Neste contexto, o objetivo principal deste trabalho consiste na previsão do instante
temporal ótimo da manutenção de um equipamento industrial – um refinador da fábrica de
Mangualde da empresa Sonae Industria, que se encontra em funcionamento contínuo 24 horas
por dia, 365 dias por ano. Para o efeito são utilizadas medidas de sensores que monitorizam
continuamente o estado do refinador.
A principal operação de manutenção deste equipamento é a substituição de dois discos
metálicos do seu principal componente – o desfibrador. Consequentemente, o sensor do
refinador analisado com maior detalhe é o sensor que mede a distância entre os dois discos do
desfibrador.
Os modelos ARIMA consistem numa abordagem estatística avançada para previsão de
séries temporais. Baseados na descrição da autocorrelação dos dados, estes modelos
descrevem uma série temporal como função dos seus valores passados.
Neste trabalho, a metodologia ARIMA é utilizada para determinar um modelo que efetua
uma previsão dos valores futuros do sensor que mede a distância entre os dois discos do
desfibrador, determinando-se assim o momento ótimo da sua substituição e evitando paragens
forçadas de produção por ocorrência de uma falha por desgaste dos discos.
Os resultados obtidos neste trabalho constituem uma contribuição científica importante
para a área da manutenção preditiva e deteção de falhas em equipamentos industriais.
Globalization and competitiveness in existing markets currently cast an increasingly demanding challenge for organizations. The delivery of the product or service desired by the customer is becoming less a differentiating factor, but a matter of survival. The client demands that the product is produced according to the desired characteristics to the first, with guaranteed quality and on time. This increasingly challenge, driven by the need to continuously optimize the quality of products, made maintenance began to be treated in a different way. Maintenance, here, is seen as the set of technical and administrative actions designed to maintain acceptable conditions in manufacturing facilities and equipment to ensure regularity, quality and safety in production, with minimal total costs. Intelligent methods for collecting and organizing data and predict potential failures will contribute greatly to the effectiveness of the machine preventive/predictive maintenance. The prediction of failures and maintenance actions of industrial machines is a problem with interesting characteristics. We need to forecast certain rare events, which are supposed to be dependent on the recent values of a set of time series values. These time series describe the recent values of a set of sensors that monitor several aspects of the industrial machines. For each task being handled by these machines (a kind of working context), the sensors are expected to have a certain typical behavior. Deviations from this typical behavior are good indicators of a foreseen failure or some maintenance action. In this context, the main objective of this work is to forecast the precise timing of the maintenance of a industrial equipment whose main action is the replacement of two metallic discs of its main component - the shredder. The ARIMA methodology is used to identify a model that forecasts the future values of the sensor that measures the distance between the two disks of the shredder, thereby determining the optimal time of their replacement and avoiding forced downtime per occurrence of a failure by wear of the discs. These results obtained in this work constitute an important contribution in the field of predictive maintenance and fault detection in industrial equipment.
Globalization and competitiveness in existing markets currently cast an increasingly demanding challenge for organizations. The delivery of the product or service desired by the customer is becoming less a differentiating factor, but a matter of survival. The client demands that the product is produced according to the desired characteristics to the first, with guaranteed quality and on time. This increasingly challenge, driven by the need to continuously optimize the quality of products, made maintenance began to be treated in a different way. Maintenance, here, is seen as the set of technical and administrative actions designed to maintain acceptable conditions in manufacturing facilities and equipment to ensure regularity, quality and safety in production, with minimal total costs. Intelligent methods for collecting and organizing data and predict potential failures will contribute greatly to the effectiveness of the machine preventive/predictive maintenance. The prediction of failures and maintenance actions of industrial machines is a problem with interesting characteristics. We need to forecast certain rare events, which are supposed to be dependent on the recent values of a set of time series values. These time series describe the recent values of a set of sensors that monitor several aspects of the industrial machines. For each task being handled by these machines (a kind of working context), the sensors are expected to have a certain typical behavior. Deviations from this typical behavior are good indicators of a foreseen failure or some maintenance action. In this context, the main objective of this work is to forecast the precise timing of the maintenance of a industrial equipment whose main action is the replacement of two metallic discs of its main component - the shredder. The ARIMA methodology is used to identify a model that forecasts the future values of the sensor that measures the distance between the two disks of the shredder, thereby determining the optimal time of their replacement and avoiding forced downtime per occurrence of a failure by wear of the discs. These results obtained in this work constitute an important contribution in the field of predictive maintenance and fault detection in industrial equipment.
Description
Keywords
Manutenção preditiva Previsão de falhas Equipamento industrial Modelos ARIMA Manufacturing equipment Forecasting failures Predictive maintenance ARIMA models