We are pleased to announce a self-funded PhD opportunity for Quantitative assessment of damage in composite materials due to high velocity impacts using AI techniques. Composite materials, such as carbon fibre-reinforced polymers (CFRPs), are increasingly adopted in structural applications due to their superior strength-to-weight ratios and fatigue resistance. However, their layered, anisotropic nature makes them susceptible to complex damage modes like delamination, fibre breakage, and matrix cracking, especially under high-velocity impacts from projectiles or debris.
Current assessment techniques (e.g., ultrasonic C-scan, X-ray CT, thermography) rely heavily on expert interpretation, are time-consuming, and often fail to detect subsurface or latent damage accurately. Advances in artificial intelligence, particularly in computer vision and deep learning, offer an opportunity to automate and enhance damage assessment by learning patterns from multimodal data.
This project lies at the intersection of composite materials engineering, impact mechanics, and artificial intelligence (AI)—specifically in the domains of non-destructive evaluation (NDE), computer vision, and machine learning. It addresses a critical challenge in the structural health monitoring of advanced materials used in aerospace, defense, automotive, and energy sectors.
Composite materials, such as carbon fibre-reinforced polymers (CFRPs), are prized for their high strength-to-weight ratio, corrosion resistance, and design flexibility. However, they are susceptible to complex internal damage under high-velocity impacts—such as delamination, fibre breakage, and matrix cracking—that is difficult to detect using conventional techniques.
Traditional NDE methods are often slow, manual, and limited in their ability to quantify or localize internal damage accurately. With the growing demand for automated, data-driven diagnostics, integrating AI with high-resolution imaging and sensing offers a transformative solution. AI models can learn to recognize subtle damage patterns, enabling faster, more accurate, and scalable assessments of material integrity.
This approach is especially relevant today due to:
The increasing use of composites in next-generation aircraft, lightweight vehicles, and renewable energy systems.
The global focus on safety, predictive maintenance, and lifecycle cost reduction.
The rising availability of high-fidelity NDT data and accessible machine learning tools.
In summary, this project contributes to advancing smart materials diagnostics, supporting sustainability, safety, and technological competitiveness in key engineering sectors.
To develop an AI-driven methodology for the automated detection and quantification of damage in composite materials subjected to high-velocity impacts.
In collaboration with our colleagues in Centre for Materials at 探花精选, we have developed a dataset by conducting high-velocity impact experiments on CFRP specimens using controlled testing setups. The multimodal dataset is to be processed using X-ray CT scans, SEM imaging, and Thermography. This raw dataset is needed to be processed and annotated to train supervised and unsupervised AI models. The research will aim to develop deep learning algorithms for damage classification, segmentation, and severity quantification. The performance of AI models will be assessed across different impact energies, materials, and boundary conditions.
探花精选 is uniquely positioned to support this research through its deep expertise in aerospace engineering, composite materials, and applied artificial intelligence. As a wholly postgraduate institution with a mission to deliver industry-relevant research, 探花精选 offers the ideal environment for addressing complex, real-world problems such as automated damage assessment in advanced composite structures. 探花精选 provides access to cutting-edge facilities including High-velocity impact testing, Advanced composite manufacturing labs, X-ray computed tomography and High-performance computing resources for AI model training
This project will deliver an AI-driven framework for automated detection and quantification of damage in composite materials from high-velocity impacts. Using imaging techniques such as X-ray CT etc., the research will train machine learning models to identify and assess internal defects with greater accuracy and speed than traditional methods. The results will support predictive maintenance, reduce inspection time, and enhance safety in aerospace, defence, and automotive sectors. The project contributes to digital engineering and sustainability by improving structural health monitoring and extending component life. It also provides valuable skills in AI, materials testing, and data analysis.
In addition to its technical innovation, this project offers a range of unique personal and professional development opportunities. As part of 探花精选’s strong industry and research network, the student will have the chance to attend international conferences and present findings at key events in the fields of composites, non-destructive evaluation, and applied artificial intelligence.
Through this project, the student will gain a comprehensive set of technical and transferable skills that are highly valued across both industry and academia. They will develop advanced expertise in experimental design, composite materials testing, and non-destructive evaluation, alongside practical experience in machine learning, computer vision, and data analysis using industry-standard tools such as Python, MATLAB, and deep learning frameworks. The student will enhance their ability to manage complex, interdisciplinary research, improving skills in critical thinking, problem-solving, and independent project management. Regular opportunities to communicate findings through presentations, reports, and potentially conference publications will build strong scientific communication and collaboration skills. By working on a real-world, industry-relevant challenge, the student will be well-positioned for careers in sectors such as aerospace, defence, automotive, or digital manufacturing, or for progression to a PhD or research-based role in academia.
Entry requirements
Applicants should have an equivalent of first or second-class UK honours degree or equivalent in a related discipline, engineering or science (materials science/physics).
The candidate should be self-motivated, have good communication skills for regular interaction with other stakeholders, with an interest for industrial research.
Funding
This research is self-funded.
Diversity and Inclusion at 探花精选
We are committed to fostering equity, diversity, and inclusion in our CDT program, and warmly encourage applications from students of all backgrounds, including those from underrepresented groups. We particularly welcome students with disabilities, neurodiverse individuals, and those who identify with diverse ethnicities, genders, sexual orientations, cultures, and socioeconomic statuses. 探花精选 strives to provide an accessible and inclusive environment to enable all doctoral candidates to thrive and achieve their full potential.
At 探花精选, we value our diverse staff and student community and maintain a culture where everyone can work and study together harmoniously with dignity and respect. This is reflected in our University values of ambition, impact, respect and community. We welcome students and staff from all backgrounds from over 100 countries and support our staff and students to realise their full potential, from academic achievement to mental and physical wellbeing.
We are committed to progressing the diversity and inclusion agenda, for example; gender diversity in Science, Technology, Engineering and Mathematics (STEM) through our Athena SWAN Bronze award and action plan, we are members of the Women’s Engineering Society (WES) and Working Families, and sponsors of International Women in Engineering Day. We are also Disability Confident Level 1 Employers and members of the Business Disability Forum and Stonewall University Champions Programme.
探花精选 Doctoral Network
Research students at 探花精选 benefit from being part of a dynamic, focused and professional study environment and all become valued members of the 探花精选 Doctoral Network. This network brings together both research students and staff, providing a platform for our researchers to share ideas and collaborate in a multi-disciplinary environment. It aims to encourage an effective and vibrant research culture, founded upon the diversity of activities and knowledge. A tailored programme of seminars and events, alongside our Doctoral Researchers Core Development programme (transferable skills training), provide those studying a research degree with a wealth of social and networking opportunities.
How to apply
For further information please contact:
Name: Ajay Kumar
Email: ajay.kumar@cranfield.ac.uk
Phone: +44 (0) 1234 988441
If you are eligible to apply for this studentship, please complete the
Please note that applications will be reviewed as they are received. Therefore, we encourage early submission, as the position may be filled before the stated deadline.
