applied mechanics
This exciting project will focus on addressing two fundamental challenges in physics-enhanced machine learning strategies in applied mechanics: (i) Overcoming poor generalisation performance and physically inconsistent or implausible predictions of machine learning models in applied mechanics by developing approaches integrating physics (first principles) knowledge through biases within Machine Learning (ML) algorithms to inform physics (e,g. identification of unknown constitutive laws and nonlinearities from measurements and physics-knowledge). (ii) Identification of incorrect prior physics assumption (e.g. wrong constitutive model) in the physics-enhanced machine learning algorithm.
During this project you will carry out dynamic tests on a laboratory setup, process data and develop advanced physics-enhanced machine learning techniques to identify nonlinearity under sparse noisy data and wrong physics-biases. You will present the outcomes of your work at international conference, and will be part of the Data, Vibration and Uncertainty group (https: // sites.google.com/view/dvugroup).The DVU group is a creative, positive and stimulating research group. We nurture your talent with 1-2-1 weekly or fortnightly meetings, regular fortnightly group meetings, quarterly review group meetings and dedicated technical and soft skills training opportunities. We celebrate diversity, success, and most importantly, we openly chat about setbacks and learn from things that inevitably do not go as planned. We provide flexible working patterns and direct access to a network of international collaborators. We value your time off, your personal space, and your technical contribution.
EPSRC DTP studentships are fully-funded (fees and maintenance) for eligible UK students. EU and international students may be considered for a small number of awards at the UK rate. Full eligibility criteria can be found via the following link; https: // www. postgraduate.study.cam.ac.uk/finance/fees/what-my-fee-status
Applicants should have (or expect to obtain by the start date) at least a good 2.1 degree in an Engineering or related subject. Preferably a 1st class honours degree in Engineering or Physics or Mathematics. A good knowledge or experience of: experimental dynamic testing and signal processing and/or of machine learning strategies. Experience with Physics-enhanced machine learning strategies would be an advantage.
Applications should be submitted via the University of Cambridge Applicant Portal https: // www. postgraduate.study.cam.ac.uk/courses/directory/egegpdpeg, with Alice Cicirello identified as the potential supervisor. Applications may close early if the position is filled before the advertised date.
Please include a cover letter describing how your research experience and interest would make you a strong candidate for this position.
The University actively supports equality, diversity and inclusion and encourages applications from all sections of society.
Department/LocationDepartment of Engineering, Cambridge
ReferenceNM40063
CategoryStudentships
Published10 January 2024
Closing date29 February 2024