What is it about?
The use of digital twins is widely adopted in optimization to reduce overall computational effort and could be considered a common practice nowadays. What is not usual is the inclusion of Machine Learning algorithms within the overall process automatically, in order to improve the quality of the digital twin and consequently also of the entire optimization process. This strategy significantly improves the overall quality of the optimization process, improving its reliability and precision, without the risk of failing to correctly identify the optimal solution due to the poor quality of the digital twin.
Featured Image
Why is it important?
Using a pair of digital twins to determine areas where they may provide inaccurate predictions ensures a progressive improvement in the predictive qualities of digital twins.
Perspectives
The application of this approach to different test cases and in different fields of application can help in the identification of critical aspects. Consideration of different structures for digital twins could also lead to a further improvement in the results obtainable, which are already at a high level.
Dr Daniele Peri
National Research Council of Italy - CNR
Read the Original
This page is a summary of: Machine learning algorithms in ship design optimization, Ship Technology Research, August 2023, Taylor & Francis,
DOI: 10.1080/09377255.2023.2250160.
You can read the full text:
Contributors
The following have contributed to this page
