Name: Dr Mengtian Yin
Academic Division: Civil Engineering
Research Group: Digital Roads for Future
Fellowship period: 15 June 2023 – 14 June 2026
Email: my424@cam.ac.uk
Research Interests
Dr Mengtian Yin's key research interests lie in the areas of construction automation, building informatics, and digital infrastructure management. Specifically, he likes to explore (a) conceptualization and knowledge modelling of digital twins for road infrastructure and (b) digital twin-enabled process automation for highway maintenance.
Strategic themes:
Design a conceptual framework of road digital twins for highway maintenance.
Architecture design and data modeling for digital twins using knowledge representation languages.
Implementation of road digital twins integrating key use cases for highway maintenance.
Deployment of graph databases, clouds, and APIs to enable future-proofing digital twin systems for highway operation and maintenance.
Research Project
Title: Exploring the minimum viable product (MVP) of a digital twin for road inspection and maintenance
Theme: Digital Twins
Abstract:
Highway agencies face challenges managing scattered asset data across maintenance processes and information systems, obstructing efficient retrieval of dynamic cross-system road information for timely interventions. This research project investigate a Digital Twin (DT)-based data federation framework to effectively manage fragmented systems and dispersed data for highway infrastructure operation and maintenance. The DT-based framework provides a federation middleware that can decompose users’ queries and request data from different subsystems based on a metadata model and a distributed system architecture. The connected data ecosystem enables dynamic communication between different asset systems, ensuring the data synchronisation, discovery, retrieval, and process coordination for different users and teams. The objectives of this research include (a) develop foundation data models (FDM) and reference data libraries (RDL) to represent a common ontology and metadata models in the federation middleware; (b) design an integration architecture (IA) that supports data sharing and retrieval between different subsystems; (c) implement a prototype of digital twin systems and evaluate the performance based on real-world use cases. The presented framework will be demonstrated based on datasets and synthesised systems conforming to asset management practices adopted by United Kingdom (UK) National Highways.
Alignment with SDG:
-
SDG 9 Industry, Innovation, and Infrastructure,
-
SDG 11 Sustainable Cities and Communities, and
-
SDG 12 Responsible Consumption and Production.
Project TRL: the starting TRL (technology readiness level) of federated DT system is ‘1 Basic Principles Observed’, and the expected end TRL is ‘5 Technology Validated In Relevant Environment’.
Industry secondment needs: I need to do an industry secondment in National Highways or Costain to learn the real practice of road inspection and maintenance, in order to understand the use cases and information requirements for devising a federated highway twin system. I would also like to do a secondment in Trimble to learn more about digital twin software development and applications.
Datasets: This project has received two datasets: (a) 3D road models in IFC4 from Costain; and (b) 3D road models in IFC4.3 from Trimble. This project has also received asset management (P-AMS) data from National Highways.
The initial test shows that the proposed digital twin framework and system prototype can be effectively used to query asset data distributed in different subsystems. IFC models are used as metadata models for connecting with the asset management system.
Bio:
Dr. Mengtian Yin is a Marie Skłodowska-Curie Future Roads Fellow at the Department of Engineering, University of Cambridge. His research project focuses on the conceptualization and implementation of the minimum viable products (MVP) of highway digital twins, with product models and process models created and validated. He recently obtained his PhD in Real Estate and Construction at the University of Hong Kong. His PhD research was centered on the development of AI-driven Natural Language Interfaces (NLIs) for efficient data retrieval from Building Information Models (BIMs). This involved the creation of ontology learning and semantic parsing models based on language models and graph networks. He has experience transferring research innovations into industry applications. Dr. Yin was the technical director of the AutoBIM project at Hong Kong MTR Corporation, where he developed novel solutions for automatically transforming 2D mechanical, electricity, and plumbing (MEP) drawings and textual documents into BIM models with rich asset information. Currently, his research work has been published in several top peer-reviewed journals (Google scholar: https://scholar.google.com/citations?user=H2jn02YAAAAJ&hl=en&oi=ao) and has been awarded three Chinese invention patents.