ÁREA: 01. Operations and Process Management
RESUMO:
The Digital Twin (DT) is a key concept for the implementation of Cyber-Physical Systems (CPS) in manufacturing, which is one of the main elements of Industry 4.0. It represents a virtual counterpart of a physical entity and can be used to simulate distinct scenarios based on models, input data and sensor information. In the virtual space, data analysis allows to make predictions and optimizations in the model, which could lead to the performance improvement of a product or process in the physical twin. Data is the core element that interconnects the physical and virtual worlds. In a manufacturing process, several data are generated through sensors and machines. A relevant aspect is related to the ability of the system to deal with a large amount of multi-source heterogeneous data (e.g. virtual space, physical environment, historical databases) and its variety issues (e.g., inconsistent data, sensor failures, data compatibility). Therefore, efficient methods should be employed to increase data reliability. In this sense, data fusion is a technique that combines multiple sources in order to improve data quality, extract relevant information and aid decision making. So, the aim of this research is to conduct a quantitative analysis to investigate the employment of data fusion and its correlated terms applied in the context of DT, assisting the research community in future studies and providing support for the use of data fusion strategies.
PALAVRAS-CHAVE: digital twin, data fusion, data aggregation, data combination
DOI:
10.14488/ijcieom2020_full_0001_37234