A Group of Researchers from University of Edinburgh , Strathclyde and Napier aims to develop novel and impactful solutions for engineers and manufacturers
Why can’t CAD systems be more like mobile phones? On mobile phones ‘Predictive text’ systems complete words, or phrases, by matching fragments against language dictionaries or common phrases used in previous messages. Similarly a ‘predictive CAD’ system would complete 3D models using ‘shape search’ technology to interactively match partial CAD features against component databases. In this way the system would prompt the users with fragments of 3D components that complete, or extend, geometry defined by the user. Such a system could potentially increase design productivity by making the reuse of established designs a natural and effortless part of the engineering design process.
Although feature based retrieval of components from databases of 3D components has been previously reported the systems could not be embedded in the design process because of their relatively slow response time. However recent breakthroughs in sub-graph matching algorithms have enabled researchers at Strathclyde to demonstrate the feasibility of feature driven shape retrieval algorithms that run fast enough to make interactive, predictive design interfaces feasible for the first time. This project aims to investigate how such a system should be implemented to enable designers to more effectively find and re-use fragments of geometry from previous designs in new components.
The rapid advance of digital sensing technologies, is making the real time recording of activities in a manufacturing environment both practical and affordable. However, the availability of diverse, real time data about movement and activity does not automatically help engineers manage the complex, dynamic environments typical of modern industrial operations. To do this they need tools that support their interpretation of constantly changing data in ways that enhance productivity and sustainability. In other words, the research challenge posed by digital manufacturing is not the capture of data, but rather the lack of computational methods to analyse large flows of diverse (i.e. multimodal) sensor data and recognise the patterns that allow engineers to assess the current state of the shop floor, understand the impact of past events and predict the consequences of incidents on a range measures.
Motivated by this need, this project investigates if the forms of probabilistic networks that have been employed to generate computational models from location tracking data in other contexts (e.g. vehicles movements in traffic models and the daily routines of individuals in domestic environments) can be extended to work with multiple forms of industrial activity data recorded on a factory floor. Such a model would allow diverse signals of manufacturing activity (e.g. material transport, staff movement, vibration, electrical current and air quality etc.) to be used to infer the behaviour of an industrial workplace and generate quantitative measures that support decisions which impact on a sites' production and sustainability performance.
Team Members
Professor Jonathan Corney, University of Edinburgh
Professor John Quigley, University of Strathclyde
Professor Andrew Sherlock, National Manufacturing Institute of Scotland
Associate Professor Gokula Vasantha, Edinburgh Napier University
Lecturer Dr. Hanane El-Raoui, University of Strathclyde
Dr Shuang Li, University of Edinburgh
Dr Jack Hanson, University of Edinburgh
Dr Rachel Sales, University of Strathclyde
Dr Hariketan Patel, Edinburgh Napier University
Mr Saravan Kumar, National Manufacturing Institute of Scotland
Past Members
Dr Ayse Aslan, ENODA Ltd
Mr Nathan Thompson, National Nuclear Laboratory
Mr David Purves
This video demonstrates a predictive interface that interactively suggests features and associated values based on the current state of CAD design and engineer search intent.
This video demonstrates the interactive component and feature reuse based on the current state of CAD design and engineer search intent.
Publications
Engineering Design and CAD
Quigley, J., Vasantha, G., Corney, J., Purves, D., & Sherlock, A. (2022). Design as a marked point process. Journal of Mechanical Design, 144(2), 021713.
Li, S., & Corney, J. (2023). Multi-view expressive graph neural networks for 3D CAD model classification. Computers in Industry, 151, 103993.
Vasantha, G., Purves, D., Quigley, J., Corney, J., Sherlock, A., & Randika, G. (2021). Common design structures and substitutable feature discovery in CAD databases. Advanced Engineering Informatics, 48, 101261.
Vasantha, G., Purves, D., Quigley, J., Corney, J., Sherlock, A., & Randika, G. (2022). Assessment of predictive probability models for effective mechanical design feature reuse. AI EDAM, 36, e17.
Vasantha, G., Corney, J., Stuart, S., Sherlock, A., Quigley, J., & Purves, D. (2020). A probabilistic design reuse index for engineering designs. Journal of Mechanical Design, 142(10), 101401.
Vasantha, G., Purves, D., Corney, J., Canavan, M., Quigley, J., & Sherlock, A. (2022, November). Towards predictive design: tracking a CNC fixture design process to identify the requirements. In Advances in Manufacturing Technology XXXV: Proceedings of the 19th International Conference on Manufacturing Research, Incorporating the 36th National Conference on Manufacturing Research, 6–8 September 2022, University of Derby, Derby, UK (Vol. 25, p. 187). IOS Press.
Vasantha, G., Corney, J., Quigley, J., & Sherlock, A. (2023). Predictive CAD System Suggestion for Efficient Engineering Design Reuse. Institution of Engineering and Technology (IET).
Vasantha, G., Sherlock, A., Corney, J., & Quigley, J. (2018, August). A probabilistic design reuse index. In International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (Vol. 51760, p. V02BT03A047). American Society of Mechanical Engineers.
Responsive Manufacturing
Patel, H., Vasantha, G., Corney, J., Quigley, J., Raoui, H. E., Sales, R., Cusack, M., Burns, A., & Rough, A. (2025, in press). A Decision Support Model for Efficient Garment Reprocessing for a Sustainable Circular Business Model. International Journal of Advanced Manufacturing Technology.
Aslan, A., Vasantha, G., El-Raoui, H., Quigley, J., Hanson, J., Corney, J., & Sherlock, A. (2024). Smarter facility layout design: leveraging worker localisation data to minimise travel time and alleviate congestion. International Journal of Production Research, 1-28.
Aslan, A., Vasantha, G., El-Raoui, H., Quigley, J., Hanson, J., Corney, J., & Sherlock, A. (2023). Hierarchical ensemble deep learning for data-driven lead time prediction. The International Journal of Advanced Manufacturing Technology, 128 (9-10), 4169-4188.
Aslan, A., El-Raoui, H., Hanson, J., Vasantha, G., Quigley, J., Corney, J., & Sherlock, A. (2023). Using worker position data for human-driven decision support in labour-intensive manufacturing. Sensors, 23 (10), 4928.
Vasantha, G., Patel, H., Hanson, J., Corney, J., El-Raoui, H., Sales, R., Quigley, J., Kasarapu, S. S., & Sherlock, A. (2025, June). Analysing Spatio-Temporal Worker Movement Patterns: Implications for Safety and Productivity in Smart Factories. 11th IFAC Conference on Manufacturing Modelling, Management and Control – IFAC MIM2025, Norway.
Patel, H., Vasantha, G., Corney, J., Quigley, J., Raoui, H.-E., Sales, R., & Smith, S. (2025, June). A scheduling decision-making framework using machine learning algorithms for energy efficient integrated factory. FAIM 2025: The International Conference on Flexible Automation and Intelligent Manufacturing, New York.
Kasarapu, S. S. K., Vasantha, G., Marzano, A., Corney, J., Hanson, J., Quigley, J., El-Raoui, H., Thomson N. & Sherlock, A. (2024). Safer and efficient assemblies: Harnessing real time worker movements with digital twins. In the 21st International Conference on Manufacturing Research. Glasgow. (Received Best Paper Award).
Kasarapu, S. S. K., Vasantha, G., Corney, J., Hanson, J., Quigley, J., El-Raoui, H., Thomson N. & Sherlock, A. (2024, August). Safer and Efficient Factory by Predicting Worker Trajectories Using Spatio-Temporal Graph Attention Networks. In International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (Vol. 88353, p. V02BT02A022). American Society of Mechanical Engineers.
El-Raoui, H., Quigley, J., Aslan, A., Vasantha, G., Hanson, J., Corney, J., & Sherlock, A. (2023, April). Agent based simulation of workers' behaviours around hazard areas in manufacturing sites. In The OR Society 11th Simulation Sorkshop (pp. 86-95). The Operational Research Society. Chicago
Aslan, A., El-Raoui, H., Hanson, J., Vasantha, G., Quigley, J., & Corney, J. (2023, June). Data-driven discovery of manufacturing processes and performance from worker localisation. In International Conference on Flexible Automation and Intelligent Manufacturing (pp. 592-602). Cham: Springer Nature Switzerland.
El Raoui, H., Quigley, J., Aslan, A., Vasantha, G., Hanson, J., Corney, J., & Sherlock, A. (2023, December). Design of a serious game for safety in manufacturing industry using hybrid simulation modelling: towards eliciting risk preferences. In 2023 Winter Simulation Conference (WSC) (pp. 1304-1315). IEEE.
Vasantha, G., Aslan, A., Hanson, J., El-Raoui, H., Corney, J., & Quigley, J. (2023, June). A knowledge graph approach for state-of-the-art implementation of industrial factory movement tracking system. In International Conference on Flexible Automation and Intelligent Manufacturing (pp. 1194-1204). Cham: Springer Nature Switzerland.
EPSRC Funding Grants
Industry Collaborators
Contact Professor Jonathan Corney <J.R.Corney@ed.ac.uk> to get more information on the projects