Digital Twin Ocean Engineering Ⅰ

Aims & Scope

The rapid advancement of Digital Twin technology is transforming the field of ocean engineering, enabling smarter, more efficient, and safer marine operations. As the challenges such as extreme weather conditions, complex offshore activities, and the increasing demand for sustainable energy solutions, Digital Twins offer a powerful tool for simulation, monitoring, and predictive analytics. 

From marine equipment and offshore renewable energy systems to disaster prevention and automated exploration, Digital Twin technology is reshaping the way we design, operate, and maintain critical ocean infrastructure. The integration of data-driven learning, real-time simulations, and intelligent risk assessment is paving the way for smarter and more resilient marine systems. This session is organized to bring together researchers, engineers, and industry leaders to explore the latest advancements in Digital Twins for ocean engineering. With discussions on cutting-edge research, platform architecture, and real-world applications, this session will provide valuable insights that will shape the future of digital and intelligent ocean. 

 

The conference will focus on the following aspects:

▪Digital twin in oncean renewable energy

▪Digital twin in maritime operations, and disaster prevention

▪Digital twin in automated ocean exploration and offshore platform equipment

▪Digital twin in intelligent marine equipment design, real-time monitoring, operational simulation, smart decision-making, and risk control
▪Digital twin in architecture for ocean engineering: data-driven online learning and standardization of data exchange


------


Your valuable insights are welcome! 

We cordially invite interested researchers to contact us for details and presentation applications at: secretariat@idea-global.net


Session Chairs

Presentations

  • Professor
    Jiangsu University of Science and Technology
    Title: Key Technologies and Applications of Intelligent Hull Plate Forming Driven by Digital Twins
    Abstract The manufacturing quality of ship hull plates determines their navigational performance and safety. Addressing the composite forming process of large-thickness, large-curvature, and large-scale ship hull plates with bidirectional constant/variable curvature, several technical challenges exist, including "coupled and variable processes, making geometric deformation quantification difficult," "complex spatial scales, leading to weak real-time detection capabilities," "heterogeneous data that are difficult to integrate, resulting in a lack of dynamic process evolution," and "asynchronous virtual-real interaction, diminishing controllability." To address these issues, a systematic approach integrating characterization, measurement, prediction, and control is proposed for the coordinated control of geometric accuracy in composite forming. A correlation mechanism between process parameters and geometric deformation in thick-curved plate composite forming is established to quantitatively characterize dynamic evolution patterns from semantic, temporal, and feature dimensions. A process-adaptive optimization strategy for geometric accuracy control is developed, along with a software-hardware system covering evolution characterization, accuracy detection, deformation prediction, and collaborative control. The proposed approach is validated through typical case studies.
  • Professor
    University of Aberdeen
    Title: From Prediction to Decision: Uncertainty-Informed Digital Twin Architectures for Integrity-Critical Engineering Systems
    Abstract This presentation introduces an uncertainty-informed digital twin architecture for risk-informed decision-making in ocean engineering systems. The framework integrates physics-based degradation models, machine-learning surrogates, probabilistic inference and human reliability representations within a unified architecture. It enables continuous estimation of degradation states, remaining useful life and probability of failure while propagating uncertainty across physical, statistical and operational layers. Case studies in offshore energy systems demonstrate applications in platform safety monitoring, occupational noise exposure prediction and corrosion management, illustrating how uncertainty-aware digital twins support auditable integrity management for offshore infrastructure.
  • Associate Professor
    Tongji University
    Title: AI for Assembly, Welding, and Direct Energy Deposition
    Abstract This report presents three AI‑enhanced methodologies for quality control and process prediction in smart ship manufacturing, targeting representative challenges across different manufacturing scales. The first work addresses large thin‑walled curved parts: a Kriging‑based metaheuristic jointly optimizes the number and positions of fixtures, significantly reducing assembly gaps and deformations. The second work focuses on spatiotemporal welding prediction: an end‑to‑end Wavelet Irregular Transformer with Gumbel Sampling fuses heterogeneous physical fields (deformation, stress, temperature) to achieve accurate and efficient predictions. The third work targets direct energy deposition (DED): an event series‑active learning framework efficiently predicts residual stress and flatness while minimizing the need for high‑quality training data. Case studies demonstrate that each method outperforms conventional approaches in accuracy, convergence speed, and computational cost, providing practical AI solutions for intelligent manufacturing systems.
  • Associate Professor
    HoHai University
    Title: NC machining process planning of 3+1 Axis CNC machined parts
    Abstract Against the backdrop of surging demand for multi-variety, small-batch and customized part manufacturing, 3+1-axis CNC machining centers have gained widespread adoption across manufacturing enterprises. Currently, achieving automated generation of 3+1-axis CNC machining process plans and enabling automatic tool path planning has emerged as a critical bottleneck demanding urgent breakthroughs for CNC machining enterprises. Relevant research covers core technologies including machining feature recognition, fixture face reasoning, working station sequence planning, feature process decision-making, and process sequencing of working station-associated features, which will provide core technical support for the development of generative process design software with independent intellectual property rights.
  • PhD Candidate
    Donghua University
    Title: Metatwin: A Meta-Level Organization and Constraint-Driven Collaboration Framework for Multi-Digital Twin Systems
    Abstract Digital twin systems are increasingly used to represent and analyze complex manufacturing processes. However, existing digital twins are often developed for specific objects, processes, or functions, which makes it difficult to organize multiple heterogeneous twins and coordinate them for complex tasks. To address this problem, this study proposes MetaTwin, a meta-level framework for multi-digital twin systems. Instead of replacing underlying digital twins, MetaTwin provides standardized descriptions of their boundaries, capabilities, inputs, outputs, constraints, and relationships. Based on this meta-level representation, constraint-driven reasoning is introduced to identify relevant twins, organize their dependencies, and support collaborative invocation under task requirements. The proposed framework enables more interpretable and scalable coordination among heterogeneous digital twins, providing a foundation for complex manufacturing scenarios such as shop-floor layout analysis, process evaluation, and cross-model decision support.