About the Project
Classical automation is based on physical models. However, it is not always possible to have an accurate physical model of the system that will be automated. Machine learning can be used to learn a model of the system from experimental data. Machine learning methods are very powerful but have also some drawbacks. They require large computations and do not always generate reliable result. Can we combine the best of both worlds?
This project will aim at merging well understood physical principles and ML methods so that ML can focus on learning only what is necessary. This new research trend will push the boundaries of the performance limitations in numerous applications with complex dynamics, e.g., robotic manipulators (e.g., to perform repetitive tasks at high speeds and accuracies) mechatronic systems (e.g., automated guided vehicles), cyber-physical systems, etc.
This project aims at studying how physical model-based methods can be supplemented by data-based techniques. He/ she will be expected to conduct outstanding research on high-performance automation of complex systems via combining physical modelling and machine learning.
Funding
This research project is fully funded.
Home/EU Applicants
This project is eligible for a fully funded College of Science and Engineering studentship which includes:
• A full UK/EU fee waiver for 3.5 years
• An annual tax free stipend of £15,009 (2019/20)
• Research Training Support Grant (RTSG)
International Applicants
This project is eligible for a partially funded College of Science and Engineering studentship which includes:
• A full UK/EU fee waiver for 3.5 years (applicants will need to provide evidence they can fund the difference between the UK/EU fee and International fee)
• An annual tax free stipend of £15,009 (2019/20)
• Research Training Support Grant (RTSG)
Entry requirements
UK Bachelor Degree with at least 2:1 in a relevant subject or overseas equivalent.
Enquiries
Project Specific : [Email Address Removed]
Application Specific : [Email Address Removed]
References
Hou, Zhong-Sheng, and Zhuo Wang. "From model-based control to data-driven control: Survey, classification and perspective." Information Sciences 235 (2013): 3-35.
Brunton, Steven L., and J. Nathan Kutz. Data-driven science and engineering: Machine learning, dynamical systems, and control. Cambridge University Press, 2019.
Hou, Zhongsheng, Huijun Gao, and Frank L. Lewis. "Data-driven control and learning systems." IEEE Transactions on Industrial Electronics 64.5 (2017): 4070-4075.
Bristow, Douglas A., Marina Tharayil, and Andrew G. Alleyne. "A survey of iterative learning control." IEEE control systems magazine 26.3 (2006): 96-114.
Hou, Zhong-Sheng, and Zhuo Wang. "From model-based control to data-driven control: Survey, classification and perspective." Information Sciences 235 (2013): 3-35.
Brunton, Steven L., and J. Nathan Kutz. Data-driven science and engineering: Machine learning, dynamical systems, and control. Cambridge University Press, 2019.
Hou, Zhongsheng, Huijun Gao, and Frank L. Lewis. "Data-driven control and learning systems." IEEE Transactions on Industrial Electronics 64.5 (2017): 4070-4075.
Bristow, Douglas A., Marina Tharayil, and Andrew G. Alleyne. "A survey of iterative learning control." IEEE control systems magazine 26.3 (2006): 96-114.
Bazanella, Alexandre Sanfelice, Lucíola Campestrini, and Diego Eckhard. Data-driven controller design: the H2 approach. Springer Science & Business Media, 2011.
Continue with Facebook
