Utilize este identificador para referenciar este registo: http://hdl.handle.net/10362/91108
Registo completo
Campo DCValorIdioma
dc.contributor.advisorOliveira, José-
dc.contributor.advisorLeitão, Paulo-
dc.contributor.authorPeres, Ricardo Alexandre Fernandes da Silva-
dc.date.accessioned2020-01-13T14:58:25Z-
dc.date.available2020-01-13T14:58:25Z-
dc.date.issued2019-
dc.date.submitted2019-
dc.identifier.urihttp://hdl.handle.net/10362/91108-
dc.description.abstractDue to the advancements in the Information and Communication Technologies field in the modern interconnected world, the manufacturing industry is becoming a more and more data rich environment, with large volumes of data being generated on a daily basis, thus presenting a new set of opportunities to be explored towards improving the efficiency and quality of production processes. This can be done through the development of the so called Predictive Manufacturing Systems. These systems aim to improve manufacturing processes through a combination of concepts such as Cyber-Physical Production Systems, Machine Learning and real-time Data Analytics in order to predict future states and events in production. This can be used in a wide array of applications, including predictive maintenance policies, improving quality control through the early detection of faults and defects or optimize energy consumption, to name a few. Therefore, the research efforts presented in this document focus on the design and development of a generic framework to guide the implementation of predictive manufacturing systems through a set of common requirements and components. This approach aims to enable manufacturers to extract, analyse, interpret and transform their data into actionable knowledge that can be leveraged into a business advantage. To this end a list of goals, functional and non-functional requirements is defined for these systems based on a thorough literature review and empirical knowledge. Subsequently the Intelligent Data Analysis and Real-Time Supervision (IDARTS) framework is proposed, along with a detailed description of each of its main components. Finally, a pilot implementation is presented for each of this components, followed by the demonstration of the proposed framework in three different scenarios including several use cases in varied real-world industrial areas. In this way the proposed work aims to provide a common foundation for the full realization of Predictive Manufacturing Systems.pt_PT
dc.language.isoengpt_PT
dc.rightsopenAccesspt_PT
dc.subjectPredictive Manufacturing Systemspt_PT
dc.subjectCyber-Physical Systemspt_PT
dc.subjectData Analyticspt_PT
dc.titleAn Industrial Data Analysis and Supervision Framework for Predictive Manufacturing Systemspt_PT
dc.typedoctoralThesispt_PT
thesis.degree.nameDoctor of Philosophy in Computer Science and Engineeringpt_PT
dc.identifier.tid101641133-
dc.subject.fosDomínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informáticapt_PT
Aparece nas colecções:FCT: DI - Teses de Doutoramento

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
Peres_2019.pdf11,12 MBAdobe PDFVer/Abrir


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.