De-mixing is one of the most ubiquitous examples of self-assembly, occurring frequently in complex fluids and living systems. It has enabled the development of multi-phase polymer alloys and composites for use in sophisticated applications including structural aerospace components, flexible solar cells and filtration membranes. In each case, superior functionality is derived from the microstructure, the prediction of which has failed to maintain pace with synthetic and formulation advances. The interplay of non-equilibrium statistical physics, diffusion and rheology causes multiple processes with overlapping time and length scales, which has stalled the discovery of an overarching theoretical framework. Consequently, we continue to rely heavily on trial and error in the search for new materials. Our aim is to introduce a powerful new approach to modelling non-equilibrium soft matter, combining the observation based empiricism of machine learning with the fundamental based conceptualism of physics. We will develop new methods in machine learning by addressing the broader challenge of incorporating prior knowledge of physical systems into probabilistic learning rules, transforming our capacity to control and tailor microstructure through the use of predictive tools. Our goal is to create empirical learning engines, constrained by the laws of physics, that will be trained using microscopy, tomography and scattering data. In this feasibility study, we will focus on proof-of-concept, exploring the temperature / composition parameter space for a model blend, building the foundations for our ambition of using physics informed machine learning to automate and accelerate experimental materials discovery for next generation applications.

Continuous carbon fibre composites are capable of competing directly with advanced metals in terms of structural performance. The advantages of composites come from the ability to manufacture complex shapes, generally in relatively low volume production, in weight saving and corrosion resistance. However, continuous fibre composites are difficulties to manufacture, leading to both high costs and to the potential for generation of a range of defects impacting strongly on performance. In addition, continuous fibre composites cannot be directly recycled as there is no way of reusing the fibres that can be extracted in long, but not continuous and topologically ordered form. From an examination of the current status of the composites industry two big challenges can be identified. The first is to increase defect-free production volumes by at least an order of magnitude - leading directly to the need to simplify and automate the manufacturing processes [12]. The second is the requirement to generate more sustainable composites solutions by moving towards a circular economy based model [13] via the development of recycling processes able to retain the material's mechanical properties and economic value. In principle, there is nothing new in this analysis of the challenges, however, a great deal of research activity has been expended in these areas in the last two decades without achieving a step-change in capability. The central thesis of this proposal is that the principal difficulties in both achieving low cost, reliable, high volume production and readily recyclable advanced composites arise from a single source: the fact that the fibres are continuous and that both problem areas can be directly tackled by adopting highly Aligned Discontinuous Fibre Reinforced Composites (ADFRCs). Our vision is to generate a fundamental step-change in the composite industry by further developing and applying the HiPerDiF (High Performance Discontinuous Fibre) technology to produce high performance ADFRCs. This new, high volume manufacturing method was invented at the University of Bristol in the EPSRC funded HiPerDuCT (High Performance Ductile Composite Technology) programme (EP/I02946X/1). The basic concept is that if discontinuous fibres are accurately aligned and their length is significantly longer than the critical fibre length, the tensile modulus, strength and failure strain of the obtained composites are comparable to those of continuous fibre composites. This technique, developed in the HiPerDuCT programme has also shown the potential to tailor mechanical behaviour of composite materials, delivering pseudo-ductility via hybridisation and fibre pull-out mechanisms. The HiPerDiF technology offers the opportunity to realise the potential of aligned discontinuous fibre composites and produce a significant industrial and societal impact. Changing the fibre reinforcement geometry from continuous to discontinuous, without compromising the mechanical properties, will have a wide impact on the composite industry. The fibre discontinuity will allow an increase in the productivity of automated manufacturing processes and the formability of complex geometries, reducing the manufacturing generated defects. The use of ADFRC will increase the tailorability of composite materials by leading to truly multifunctional composite materials, able to respond to multiple design requirements. ADFRC will open the way for the adoption of a circular economy model in the composite sector by allowing the remanufacturing of reclaimed carbon fibres in high performance and high value feedstock and by producing more readily recyclable materials.

High performance fibre-reinforced polymer composites are the current state-of-the-art for lightweight structures and their use is rising exponentially in a wide range of applications from aerospace to sporting goods. They offer outstanding mechanical properties: high strength and stiffness, low weight, and low susceptibility to fatigue and corrosion. The use of high strength, high stiffness materials in fibre form mitigates the tendency for premature brittle failure, enables components to be formed at low or moderate temperatures, and enables anisotropic designs to target the primary load-carrying demands. Fibres are particularly efficient in uniaxial tension but, under compression, composites suffer a range of failures typically associated with fibre micro-buckling or kinking, linked to matrix or interfacial issues; these mechanisms couple in a complicated way at a variety of physical lengthscales. Often, these types of failure determine the practical usage of composites and set design limits well below the expected intrinsic performance of the constituent fibres. On the other hand, new constituents and processes are becoming available that enable the directed assembly of composite structures, controlled across a much wider range of lengthscales than previously possible. In principle, then, composite materials should be redesigned to take advantage of these opportunities to supress or redirect the failure process in compression. Natural materials, such as wood and bone, are fully hierarchical, with precise structural features resolved at every possible magnification. Artificial composites lack this dexterity but can exploit intrinsically superior constituents. The increasing ability to visualise, calculate, and control structures, including with quantitative precision, will allow a new generation of composite materials to be developed. The ambition is to realise the full intrinsic potential of the fibres by designing such hierarchical systems for compression, from first principles, exploiting the latest developments in materials, processing, characterisation, and modelling of mechanistic processes. This programme focusses on the challenge of improving the absolute performance of composites in compression, both to address practical limitations of current materials, and as a demonstration of the value of quantitative hierarchical materials design. Tools and materials developed during this programme will be useful in a range of other contexts. The work will develop and embed structure at every lengthscale from the molecules of the matrix, to the lay-up of final components, using new constituents and new architectures, designed with a new analytical framework. The programme will benefit from a highly creative and interdisciplinary approach amongst the core project term, amplified by contributions from leading international advisors and collaborators. An extensive group of industrial partners will contribute to the project, and help to develop the outputs, building on concept demonstrators designed during the programme. The scientific and technical results will be widely disseminated nationally and internationally, helping to ensure UK leadership in this key field.

We will train a cohort of students at the interface between the physical and computer sciences to drive the critically needed implementation of digital and automated methods in chemistry and materials. Through such training, each student will develop a common language across the areas of automation, AI, synthesis, characterization and modelling, preparing them to become both leader and team player in this evolving and multifaceted research landscape. The lack of skilled individuals is one of the main obstacles to unlocking the potential of digital materials research. This is demonstrated by the enthusiastic response toward this proposal from our industrial partners, who span sectors and sizes: already 35 are involved and we have already received cash support corresponding to over 27 full studentships. This proposal will deliver the EPRSC strategic priority "Physical and Mathematical Sciences Powerhouse" by training in "discovery research in areas of potential high reward, connecting with industry and other partners to accelerate translation in areas such as catalysis, digital chemistry and materials discovery." The CDT training programme is based on a unique physical and intellectual infrastructure at the University of Liverpool. The Materials Innovation Factory (MIF) was established to deliver the vision of digital materials research in partnership with industry: it now co-locates over 100 industrial scientists from more than 15 companies with over 200 academic researchers. Since 2017, academics and industrial researchers from physical sciences, engineering and computer sciences have co-developed the intellectual environment, infrastructure and expertise to train scientists across these areas. To date, more than 40 PhD projects have been co-designed with and sponsored by our core industrial partners in the areas of organic, inorganic, hybrid, composite and formulated materials. Through this process, we have developed bespoke training in data science, AI, robotics, leadership, and computational methods. Now, this activity must be grown scalably and sustainably to match the rapidly increasing demand from our core partners and beyond. This CDT proposal, developed from our previous experience, allows us to significantly extend into new sectors and to a much larger number of partners, including late adopters of digital technologies. In particular, we can now reach SMEs, which currently have limited options to explore digitalization pathways without substantial initial investment. A distinctive and exciting training environment will be built exploiting the diverse background of the students. Peer learning and group activities within a cross-disciplinary team will accelerate the development of a common language. The ability to use a combination of skills from different individuals with distinct domain expertise to solve complex problems will build the teams capable of driving the necessary change in industry and academia. The professional training will reflect the diversity of career opportunities available to this cohort in industry, academia and non-commercial research organizations. Each component will be bespoke for scientists in the domain of materials research (Entrepreneurship, Chemical Supply Chain, Science Policy, Regulatory Framework). External partners of training will bring different and novel perspectives (corporate, SMEs, start-ups, international academics but also charities, local authorities, consultancy firms). Cohort activities span the entire duration of the training, without formal division between "training" and "research" periods, exploiting the physical infrastructure of MIF and its open access area to foster a strong and vital sense of community. We will embed EDI principles in all aspects of the CDT (e.g. recruitment, student well-being, composition of management, supervisory and advisory teams) to make it a pervasive component of the student experience and professional training.

We will launch a new CDT, focused on composite materials and manufacturing, to deliver the next generation of composites research and technology leaders equipped with the skills to make an impact on society. In recent times, composites have been replacing traditional materials, e.g. metals, at an unprecedented rate. Global growth in their use is expected to be rapid (5-10% annually). This growth is being driven by the need to lightweight structures for which 'lighter is better', e.g. aircraft, automotive car bodywork and wind blades; and by the benefits that composites offer to functionalise both materials and structures. The drivers for lightweighting are mainly material cost, fuel efficiency, reducing emissions contributing to climate change, but also for more purely engineering reasons such as improved operational performance and functionality. For example, the UK composites sector has contributed significantly to the Airbus A400M and A350 airframes, which exhibit markedly better performance over their metallic counterparts. Similarly, in the wind energy field, typically, over 90% of a wind turbine blade comprises composites. However, given the trend towards larger rotors, weight and stiffness have become limiting factors, necessitating a greater use of carbon fibre. Advanced composites, and the possibility that they offer to add extra functionality such as shape adaptation, are enablers for lighter, smarter blades, and cheaper more abundant energy. In the automotive sector, given the push for greener cars, the need for high speed, production line-scale, manufacturing approaches will necessitate more understanding of how different materials perform. Given these developments, the UK has invested heavily in supporting the science and technology of composite materials, for instance, through the establishment of the National Composites Centre at the University of Bristol. Further investments are now required to support the skills element of the UK provision towards the composites industry and the challenges it presents. Currently, there is a recognised skills shortage in the UK's technical workforce for composites; the shortage being particularly acute for doctoral skills (30-150/year are needed). New developments within industry, such as robotic manufacture, additive manufacture, sustainability and recycling, and digital manufacturing require training that encompasses engineering as well as the physical sciences. Our CDT will supply a highly skilled workforce and technical leadership to support the industry; specifically, the leadership to bring forth new radical thinking and the innovative mind-set required to future-proof the UK's global competitiveness. The development of future composites, competing with the present resins, fibres and functional properties, as well as alternative materials, will require doctoral students to acquire underpinning knowledge of advanced materials science and engineering, and practical experience of the ensuing composites and structures. These highly skilled doctoral students will not only need to understand technical subjects but should also be able to place acquired knowledge within the context of the modern world. Our CDT will deliver this training, providing core engineering competencies, including the experimental and theoretical elements of composites engineering and science. Core engineering modules will seek to develop the students' understanding of the performance of composite materials, and how that performance might be improved. Alongside core materials, manufacturing and computational analysis training, the CDT will deliver a transferable skills training programme, e.g. communication, leadership, and translational research skills. Collaborating with industrial partners (e.g. Rolls Royce) and world-leading international expertise (e.g. University of Limerick), we will produce an exciting integrated programme enabling our students to become future leaders.