Batch processes are gaining ever increasing importance in manufacturing industries. They are particularly prevalent in the polymer, pharmaceutical and specialty chemical industries where the focus is on the production of low-volume, high-value added products. Yet, while advanced control of continuous processes has progressed significantly over the last few decades, the characteristics associated with batch processes make them particularly challenging to control. These include presence of nonlinear and time-varying dynamics, lack of on-line sensors for product quality variables, frequent operation close to process constraints and an abundance of unmeasured disturbances.In batch processing the objective for the control system can be divided into Batch End /Point Control and Trajectory Tracking Control problems. The fundamental difference between these two types of control problems is that an end-point controller is concerned with ensuring that the quality of the product at the end of a batch meets target specifications, whilst trajectory tracking involves the regulation of product quality to a, typically, time-varying set-point as a batch progresses. Another highly relevant control problem that has not yet been effectively addressed by the academic community is the reduction of batch run length. In fact, the ability to reduce batch run length, while also ensuring that the final product conforms to stringent quality specifications, is arguably the most critical business driver in batch processing industries. The aim of the proposed project is to develop a novel Model Predictive Controller that is capable of addressing a critical operational objective in industrial batch processing, which is real-time reduction of the batch run length. The MPC controller will employ a multivariate statistical data-driven prediction model and will also be applicable to both trajectory tracking and batch end-point control problems for processes that exhibit variable batch run lengths and contain irregular measurements of the controlled variables.The novelty of the proposed project stems from the fact that none of the existing advanced control techniques provide solutions to both the trajectory tracking and batch end-point control while dealing with variable batch run lengths and irregular measurements of the controlled variables. Also, none of the existing controllers address the critical control problem of batch run length minimisation. In contrast, the controllers developed in the proposed project will address all three control problems (trajectory tracking, batch end-point control and batch run length control) while also tolerating the presence of variable batch run lengths and irregular measurements of the controlled variables.

GSK is a global healthcare company that discovers, develops and manufactures medicines to treat a range of conditions including: respiratory diseases, cancer, heart disease, epilepsy, bacterial and viral infections (such as HIV and lupus), and skin conditions like psoriasis. GSK makes over 4 billion packs of medicines each year, with the goal of playing its part in meeting some of society's biggest healthcare challenges. Alongside a mission to provide transformative medicines to patients, GSK continually seeks to improve the efficiency and sustainability of our processes across the discovery, manufacturing, and delivery components of our supply chain. Indeed, GSK are committed to ambitious sustainability goals by 2050 that can only be achieved by making existing and future medicines via better routes, driving innovation all the way from the first design of the molecule through to patients in the clinic. This Prosperity Partnership aims to build on existing vibrant collaborations between GSK and the Universities of Nottingham and Strathclyde. The strengths of each partner will be leveraged to deliver a new suite of methods and approaches to tackle some of the major challenges in the discovery, development, and manufacture of medicines. Our vision is to increase efficiency in terms of atoms, energy, and time; resulting in transformative medicines at lower costs, reduced waste production, and shorter manufacturing routes. Key challenge areas, or themes, covered in our partnership include: 1. The development and application of Artificial Intelligence (AI) and Machine Learning to the efficient identification of next generation medicines: in Drug Discovery, many hundreds of candidate structures are designed, prepared, and tested to find the molecule with the right profile to take into the clinic. The development of AI informed decision making has the potential to deliver huge savings by minimising the number of compounds that need to be made at this stage. The software developed will incorporate green chemistry principles with the goal that the chemical methods employed are as efficient and sustainable as possible. 2. Next generation catalysis and synthesis: Chemists seeking to discover new medicines need new reactions that will allow them to make and investigate structures that are currently difficult, or even impossible, to make. A key objective of this proposal will be to develop new reagents, catalysts, and reactions to facilitate the more efficient preparation of drug-like molecules to accelerate drug discovery. Similarly, we will develop new ways of performing some of the most common chemical transformations in the synthesis of medicines whilst avoiding the use of carcinogenic reagents. 3. Sustainable processes that deliver efficiency and transition to scale-up from grammes to kilogrammes. Currently under-utilised approaches, such as electrochemistry, will be explored for their ability to catalyse reactions with cheaper and less environmentally impactful metals, such as replacing palladium with nickel. 4. A new Digital Design toolset for equipment will enable Digital Manufacturing of novel pharmaceutical processing equipment. Current development relies on existing traditional vessels and flow reactors that compromise our ability to deliver processes that operate at optimal performance. The research will couple advanced process models, state-of-the-art experimentation, and 3-D printing/additive manufacturing technologies to revolutionise how we develop, scale up, and operate chemical processes to supply new medicines. Integration of the projects and the expertise from the three partner institutions, and the successful prosecution of our research objectives, will make a major contribution to the wider pharmaceutical sector and, indeed, GSK's mission of discovering and developing transformative medicines faster to help people do more, feel better, and live longer.

There are considerable challenges around digitalisation in science, engineering and manufacturing in part due to the inherent complexity in the data generated and the challenges in creating useful data sets with the scale required to allow big data approaches to identify patterns, trends and useful knowledge. Whilst other sectors are now realising the power of predictive data analytics; social media platforms, online retailers and advertisers, for example; much of the pharmaceutical manufacturing R&D community struggle with modest, poorly interconnected datasets, which ultimately tend to have short useful lifespans. A result of poor, under-utilised datasets, is that it is largely impossible to avoid "starting at the beginning" for every new drug that needs to be manufactured, which is very costly with new medicines currently doubling in cost every nine years; $1 billion US Dollars currently "buys" only half a new drug so addressing this issue is key for sustainability of the industry and future medicines supply. This project, ARTICULAR, will seek to develop novel machine learning approaches, a branch of artificial intelligence research, to learn from past and present manufacturing data and create new knowledge that aids in crucial manufacturing decisions. Machine learning approaches have been successfully applied to inform aspects of drug discovery, upstream of pharmaceutical manufacturing, where large genomic and molecule screening datasets provide rich information sources for analysis and training artificial intelligences (AI). They have also shown promise in classifying and predicting outcomes from individual unit operations used in medicines manufacturing, such as crystallisation. For the first time, there is an opportunity to use AI approaches to learn from the data and models from across multiple previous development and manufacturing efforts and then address the most commonly encountered problems when manufacturing new pharmaceutical products, which are knowing: (1) the processes and operations to employ; (2) the sensors and measurements to deploy to optimally deliver the product; and (3) the potential process upsets and their future impact on the quality of the medicine manufactured. All of these data and the AI "learning" will be made available via bespoke, personalisable AR and VR interfaces incorporating gesture and voice inputs alongside more traditional approaches such as dashboards. These immersive interfaces will facilitate pharmaceutical manufacturing process design, and visualisation of the complex data being captured and analysed in real-time. Detailed, interactive 3D visualisations of drug forms, products, equipment and manufacturing processes and their associated data will be created which provide intuitive access across the length scales of transformations involved from the drug molecule to final drug product. This will be unique tool, allowing the user to see their work and engage with their data in the context of upstream and downstream processes and performance data. Virtual and Augmented Reality technologies will be used in the lab/plant environment to visualise live data streams for process equipment as the next step in digitalisation. These advanced visualisation tools will add data rich, interactive visualisation to aid researchers in their work, allowing them to focus on the meaning of results and freeing them from menial manual data curation steps.

Although continuous crystallisation provides significant benefits to innovative manufacture, the key challenge of real time, robust monitoring of quantitative attributes (form, shape, size) of particulate products still remains a massive challenge. While particle attributes are crucial for downstream processing of products, no current solution allows the processing of data from in-line sensors to reliably extract these attributes in real time across multiple manufacturing steps and the subsequent use of this knowledge for IDS and control of processes. The development of solutions for the sector requires expertise across many technologies driven by end user requirements. Industrial co-creators will provide the requirements, the range of expertise within the applicants ensuring that the goals of the programme are met. The grant will enable the establishment of a process test-bed which as the project matures, will be made available to a range of national and international user and application communities. This activity will support the creation of a requirement and technology roadmap, in so doing informing both the research and commercial communities on future opportunities. The project will also yield the following added value to the community: - the cross-disciplinary nature of the project and participating teams will stimulate new solutions and promote creativity through sharing best practice in executing research from different perspectives - the PDRAs will be applying their know-how to joint development tasks, allowing them to gain comprehensive knowledge and expertise across a range of field and in so doing provide trained, talented engineers that will fuel the deployment of these innovative solutions - the project addresses the integration of a number of distinct architectural layers to transform a physical infrastructure into a flexible platform which supports a range of applications whilst accessible to users

Lancaster University (LU) proposes a Centre for Doctoral Training (CDT) whose goal is the development of international research leaders in statistics and operational research (STOR) through a programme in which industrial challenge is the catalyst for methodological advance. The proposal brings together LU's considerable academic strength in STOR with a formidable array of external partners, both academic and industrial. All are committed to the development of graduates capable of either leadership roles in industry or of taking their experience of and commitment to industrial engagement into academic leadership in STOR. The proposal develops an existing EPSRC-funded CDT (STOR-i) by a significant evolution of its mission which takes its degree of industrial engagement to a new level. This considerably enhanced engagement will further strengthen STOR-i's cohort-based training and will result in a minimum of 80% of students undertaking doctoral projects joint with industry, up from 50% in the current Centre. Industrial internships will be provided for those not following a PhD with industry. Industry will (i) play a role in steering the Centre, (ii) has co-designed the training programme, (iii) will co-fund and co-supervise industrial doctoral projects, (iv) will lead a programme of industrial problem-solving days and (v) will play a major role in the Centre's programme of leadership development. Industry's financial backing is providing for stipend enhancement and a range of infrastructure and training support as well as helping to bring STOR-i benefits to a wide audience. The total pledged support for STOR-i is over £5M (including £1.1M cash). The proposal addresses the priority area 'Industrially-Focussed Mathematical Modelling'. Within this theme we specifically target 'Statistics' (itself a priority area) and Operational Research (OR). This choice is motivated first by the pervasive need for STOR solutions within modern industrial problems and second by the widely acknowledged and long standing skills-shortage at doctoral level in these areas. Our partners' statements of support attest that the substantial recent growth in data acquisition and data-driven business and industrial decision-making have signalled a step change in the demand for high level STOR expertise and have opened the skills gap still wider. The current Centre has demonstrated that a high quality, industrially engaged programme of research training can create a high demand for places among the very ablest mathematically trained students, including many who would otherwise not have considered doctoral study in STOR. We believe that the new Centre will play a yet more strategic role than its predecessor in meeting the persistent skills gap. Our training programme is designed to do more than solve a numbers problem. There is an issue of quality of graduating doctoral students in STOR as much as there is one of quantity. Our goal is to develop research leaders who are able to secure impact for their work across academic, scientific and industrial boundaries; who can work alongside others who are differently skilled and who can communicate widely. Our external partners are strongly motivated to join us in achieving this through STOR-i's cohort-based training programme. We have little doubt that our graduates will be in great demand across a wide range of sectors, both industral and academic. The need for a Centre to deliver the training resides primarily in its guarantee of a critical mass of outstanding students. This firstly enables us to design a training programme around student cohorts in which peer to peer learning is a major feature. Second, we are able to attract and integrate the high quality contributions (both internal and external to LU) we need to create a programme of quality, scope and ambition.