Rob Hewson

[Full coverage of tuition fees and an annual tax-free stipend of £23,805 for Home, EU and International students.] This PhD project in the Department of Aeronautics at Imperial College London explores how generative design can be combined with neural-operator surrogates to support real-time, closed-loop multiphysics design. The work targets a major engineering bottleneck: geometry generation is fast, but evaluating thermal and electromagnetic performance usually requires slow simulation cycles. You will develop neural-operator models, including Fourier Neural Operator and DeepONet-style architectures, to learn thermal and electromagnetic performance from training data such as multifunctional metastructures. These surrogate models will then be embedded directly into a conditional generative system, such as a diffusion or transformer-based architecture, so that physics feedback can shape new designs during generation rather than after the fact. The project focuses on coupling physical prediction with design synthesis. You will build physics constraints into the generative process, create conditioning methods that allow target performance to be specified directly, and benchmark the trade-off between surrogate fidelity and design quality. A further research question is whether one joint multiphysics operator can represent both thermal and electromagnetic behaviour more efficiently than two separate models. Alongside computational validation, you will also work toward experimental testing where feasible, using 3D-printed prototypes to keep the research grounded in physically realisable structures. The project aims to move toward an interactive design-exploration tool with sub-second feedback, comparing the closed-loop approach against conventional solver-in-the-loop pipelines. You will be supervised by Dr. Ajit Panesar and Prof. Rob Hewson, whose expertise includes generative design, engineering optimisation, structural metamaterials and scientific machine learning. The student will join a dynamic research environment and work with a group of researchers on this interdisciplinary computational and experimental design problem.

[Full coverage of tuition fees, a generous travel budget, and an annual tax-free stipend of £23,805.] This PhD studentship is based in The Brahmal Institute at Imperial College London as part of the October 2027 Doctoral Programme in Sustainable Aviation (DPSA) . The cohort is framed around a systems view of aviation sustainability, with students working across themes that connect airports, airlines, air traffic management, aircraft and passengers through shared training, networking and outreach. The project focuses on fast topology-optimised heat exchangers for circular aircraft MRO . The student will develop automated topology optimisation methods that adapt spare parts to available materials and additive manufacturing equipment while preserving performance. The research is positioned for future airport hydrogen infrastructure and circular maintenance practices, linking design adaptability with reliable aircraft maintenance and airport ground support. Research activity will combine physics-based modelling , gradient-based optimisation and scientific machine learning to assess heat transfer, pressure loss and structural performance. The project also integrates phase-change thermal-fluid modelling with component durability analysis, inventory reduction and sustainability evaluation. Life-cycle assessment and inventory modelling will be used to study whether on-demand production can reduce waste, transport and environmental impacts while maintaining reliable operations. The supervisors are Professor Rob Hewson and Dr Ajit Panesar . The studentship sits within an interdisciplinary doctoral environment focused on sustainable aviation research, with specialist training and collaboration across the programme.

[Full coverage of tuition fees, a generous travel budget, and an annual tax-free stipend of £23,805.] This PhD sits within Imperial College London’s Brahmal Institute and its October 2027 Doctoral Programme in Sustainable Aviation (DPSA). The programme brings together an interdisciplinary cohort working on aviation sustainability from a systems perspective, with shared learning, specialist training, networking, and outreach as part of a wider effort to support system-wide change in aviation. The project focuses on aircraft design as a lever for sustainability and production resilience. It develops agent-based, multi-fidelity optimisation methods that treat manufacturing flexibility as a design variable. By combining multi-agent simulation, machine learning, and structural optimisation, the research aims to reduce ramp-up delays, aircraft-on-ground risk, and redesign cost at scale. The successful student will work with expertise spanning structural optimisation, aircraft design, machine learning, and design for manufacturing. The project is framed around more resilient and sustainable aircraft production, linking computational methods with the realities of how aircraft are designed and built. The supervisory team comprises Dr Thulasi Mylvganam, Dr Ajit Panesar, Professor Rob Hewson, and Dr Rhea Liem. The PhD is based at Imperial College London within a research environment centred on sustainable aviation and interdisciplinary collaboration.

[Full coverage of tuition fees and an annual tax-free stipend of £22,780 for Home, EU and International students.] This fully funded PhD studentship at Imperial College London offers an exciting opportunity to work at the intersection of aeronautics, materials science, and machine learning. The project focuses on developing architected materials and metamaterials for non-linear thermo-mechanical applications, with a particular emphasis on aerospace and other demanding environments. You will join the IDEA Lab and Structural Metamaterials Group, collaborating in a world-leading research environment that values inclusivity and professional development. The research aims to fuse machine learning-based inverse design approaches with topology optimisation to create multiscale materials capable of targeted non-linear responses. You will develop computational frameworks that address variability and uncertainty in material properties, fabrication processes, and boundary conditions. The project leverages advanced techniques such as tandem neural networks, video diffusion models, and reinforcement learning to efficiently explore high-dimensional design spaces. Mixture density networks will be used to enable robust property-to-design mapping, overcoming limitations of deterministic ML methods and providing insights into reliability and diversity of inverse designs. Applicants should hold or expect to obtain a First class honours MEng/MSci or higher degree (or international equivalent) in Aeronautics, Mechanical Engineering, or Computer Science. Experience in machine learning, optimisation, Python programming, and finite element analysis is highly desirable. The studentship provides full coverage of tuition fees and a generous annual tax-free stipend of £22,780 for Home, EU, and International students, supporting you for 3.5 years of doctoral research. The application process involves submitting a CV, transcripts, and a motivation statement via the Supervisor Review Form by 8 January 2026. Supervisors will review applications and invite long-listed candidates to formally apply. For project-specific questions, contact Dr Ajit Panesar. Imperial College London is committed to equality, diversity, and inclusion, and offers a supportive environment for all researchers.