Transforming raw DATA into insightful and actionable INFORMATION to obtain KNOWLEDGE
just in:
We are thrilled to announce that we will be presenting our paper, "Vessel Data Visions," at the World Maritime Technology Conference 2024, held on 4-5 December in Chennai, India.
This groundbreaking paper explores the integration of the Ship Digital Twin with advanced technologies such as knowledge graph databases and deep learning, aiming to revolutionize the operational and maintenance efficiencies of maritime vessels.
At the heart of this innovation are "vessel visions"—customized data views designed to meet the unique needs of diverse maritime stakeholders, including class societies, flag states, ship operators, port authorities, and more. Each vision is developed using a domain-specific language (DSL), enabling tailored interfaces that provide precise access to and interpretation of the digital twin’s data.
Join us in Chennai to dive into the future of maritime technology and discover how the Ship Digital Twin is shaping the industry!
At the heart of the 'Vessel Vision' project lies the concept of a 'Digital Twin'. For those unacquainted, think of it as a mirror image of a real-life ship but in a digital realm. This isn’t just a static representation but an evolving, data-driven model that keeps pace with its physical counterpart in real-time.
The neo4j graph database platform has been selected as a persistent store.
Life Cycle Costs Calculator the MA-CAD software has been ported to Flutter / Dart. This is version 3 of the software. The port means that for the same code base the application can run on mobile (Android, iOS), desktop (Linux, Windows), and in the web browser.
Failure analysis is the cornerstone of asset management via life-cycle costs optimizations. Knowledge graphs are semantic nets that are the next level of database technology. Deep learning is a field of inquiry devoted to understanding and building methods that “learn”, that is, methods that leverage data to improve performance on some set of tasks. We propose to structure the deep learning data into knowledge graphs to foster advanced failure analysis leveraging optimum life-cycle costs.