Publicação
DIN Spec 91345 RAMI 4.0 compliant data pipelining: An approach to support data understanding and data acquisition in smart manufacturing environments
| Resumo: | Today, data scientists in the manufacturing domain are confronted with a set of challenges associated to data acquisition as well as data processing including the extraction of valuable in-formation to support both, the work of the manufacturing equipment as well as the manufacturing processes behind it. One essential aspect related to data acquisition is the pipelining, including various commu-nication standards, protocols and technologies to save and transfer heterogenous data. These circumstances make it hard to understand, find, access and extract data from the sources depend-ing on use cases and applications. In order to support this data pipelining process, this thesis proposes the use of the semantic model. The selected semantic model should be able to describe smart manufacturing assets them-selves as well as to access their data along their life-cycle. As a matter of fact, there are many research contributions in smart manufacturing, which already came out with reference architectures or standards for semantic-based meta data descrip-tion or asset classification. This research builds upon these outcomes and introduces a novel se-mantic model-based data pipelining approach using as a basis the Reference Architecture Model for Industry 4.0 (RAMI 4.0). |
|---|---|
| Autores principais: | Nagorny, Kevin Pierre |
| Assunto: | Data Pipeline Industry 4.0 RAMI 4.0 Smart Manufacturing Semantics |
| Ano: | 2022 |
| País: | Portugal |
| Tipo de documento: | tese de doutoramento |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | Today, data scientists in the manufacturing domain are confronted with a set of challenges associated to data acquisition as well as data processing including the extraction of valuable in-formation to support both, the work of the manufacturing equipment as well as the manufacturing processes behind it. One essential aspect related to data acquisition is the pipelining, including various commu-nication standards, protocols and technologies to save and transfer heterogenous data. These circumstances make it hard to understand, find, access and extract data from the sources depend-ing on use cases and applications. In order to support this data pipelining process, this thesis proposes the use of the semantic model. The selected semantic model should be able to describe smart manufacturing assets them-selves as well as to access their data along their life-cycle. As a matter of fact, there are many research contributions in smart manufacturing, which already came out with reference architectures or standards for semantic-based meta data descrip-tion or asset classification. This research builds upon these outcomes and introduces a novel se-mantic model-based data pipelining approach using as a basis the Reference Architecture Model for Industry 4.0 (RAMI 4.0). |
|---|
Atividades financiadas
Não foram encontrados projetos financiados.