Today, our blog hosts a short interview with Dr Weiwei Chen, Associate Professor at The Bartlett School of Sustainable Construction, University College London
Weiwei, welcome. We are delighted to have you with us today as part of the #MeetTheD-HYDROFLEXTeam blog series. UCL is a partner in the D-HYDROFLEX consortium, leading the work on the dam digital twin architecture.
Q: Would you like to introduce yourself and your expertise?
A: Thank you for inviting me. I am Dr Weiwei Chen, Associate Professor in Building Information Modelling and Management at The Bartlett School of Sustainable Construction, University College London. My research focuses on digital twins, smart construction, infrastructure digitalisation, heritage digitisation, and digital modelling for the built environment. A central theme of my work is how digital technologies can help us understand, manage, and maintain complex physical assets across their life cycle. This includes the integration of geometric information, asset information, sensor data, and decision-support methods so that infrastructure owners can move from static records towards more intelligent and data-informed asset management.
Q: Could you describe your company’s role on the project?
A: UCL is one of the university partners in D-HYDROFLEX and leads the work on the dam digital twin architecture. In the project, UCL focuses on the operation and maintenance part of the dam digital twin system. The main contribution is to define how a dam digital platform should be structured so that geometric, non-geometric, and management information can be integrated into an asset management platform.
More specifically, UCL’s work addresses information interoperability, practical specifications, information integration, and platform design. This includes defining the main building blocks of the platform, the interfaces between different parts of the system, information transmission across layers, the software and system logic for implementation, BPMN process models for operational workflows, and machine-readable process chains using UML representations. The aim is to provide a clear architecture that can support predictive maintenance, digital dam management, and integration with other D-HYDROFLEX tools.
Q: Would like to explain us how the dam digital twin works?
A: A digital twin can be understood as a living digital representation of a physical asset. For a dam, this means more than creating a 3D model. It means connecting the physical dam, its components, its inspection records, operational data, and maintenance needs into one structured digital environment.
We need to think beyond traditional engineering drawings because many existing hydropower assets were built long before current digital technologies became common. Their information is often stored in separate formats, such as drawings, reports, sensor records, inspection notes, and operational databases. These sources are useful, but they are not always connected in a way that supports timely decisions.
A dam digital twin helps bridge this gap. It can describe what the asset is, where its components are, how they relate to each other, what condition they are in, and what actions are needed when an operational or maintenance issue appears. In D-HYDROFLEX, this is especially important because hydropower plants need to operate more flexibly while remaining reliable and sustainable. The digital twin architecture provides a foundation for turning fragmented information into a usable decision-support environment.
Q: What are the main challenges of your work on the project, and how do you tackle them?
A: One main challenge is the complexity of dam infrastructure. A dam is not a single object. It includes civil, hydraulic, mechanical, electrical, and monitoring components, and these components have spatial, functional, and operational relationships. Capturing these relationships in a structured digital form is technically demanding.
A second challenge is information integration. Useful data can come from drawings, point clouds, images, asset records, sensors, SCADA systems, maintenance records, and partner-developed tools. These data sources have different formats, levels of detail, and update frequencies. To address this, UCL is developing a layered architecture and data model logic that clarify how information moves between the physical asset, databases, digital models, functional modules, and user interfaces.
A third challenge is making the architecture usable for real operation and maintenance workflows. A digital twin should not remain a conceptual model. It needs to support practical tasks such as alert handling, maintenance planning, inspection workflows and decision support. For this reason, the work uses BPMN to describe business processes and workflows, and UML to represent machine-readable process chains and asset relationships. These methods help translate the digital twin concept into an operational structure that can be implemented with project partners.
Q: What are your expectations from the project? What impact will the project have on the energy ecosystem?
A: My expectation is that D-HYDROFLEX will show how digital technologies can improve the operation, maintenance, and long-term management of existing hydropower assets. For UCL’s part, the expected outcome is a robust dam digital twin architecture that can help operators organise asset information, support predictive maintenance, and improve the readiness of dams for digital management.
At the energy ecosystem level, the project can help hydropower plants become more reliable, flexible, and sustainable. This matters because hydropower plays an important role in supporting electricity systems with high shares of renewable energy. When hydropower assets are better monitored and better maintained, they can reduce unplanned downtime, support safer operation, and provide more dependable flexibility to the grid. In the longer term, the project can also contribute to common digital practices for hydropower asset management, making it easier to replicate digital twin solutions across different sites and countries.
Thank you for being with us today!
Another # meettheD-HYDROFLEX team blog story is completed. Stay tuned to learn more on our workforce team!
Learn more about the DAM digital twin project’s related publications below:
Su, Y., Chen, W., Ling, J. and Yu, D. (2025). Zero-shot point cloud segmentation for hydro power plant components. Computer-Aided Civil and Infrastructure Engineering. https://doi.org/10.1111/mice.70150
Chen, W., Su, Y. Mathew, A., Brilakis, I. (2025, January). Optimizing Hydropower Operations: A Tailored Digital Twin Framework For Hydropower Plant. Hong Kong University of Science and Technology. https://discovery.ucl.ac.uk/id/eprint/10205599/
Bouzinis, P., Dalamagkas, C., Drivakou, K., Hernampérez-Manso, P., Martín-Crespo, A., Rodríguez-Carro, S., … & Tsironi, E. (2025, June). D-HYDROFLEX: An Architectural Framework for Digitalization, Flexibility and Sustainability on Hydro Power Plants. In 2025 21st International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) (pp. 413-419). IEEE. https://ieeexplore.ieee.org/document/11096244/authors#authors
Learn more about the D-HYDROFLEX project here.
Please subscribe to our newsletter to stay updated on our activities.
