Smart Continuous Nanoparticle Manufacturing.

目标：该项目旨在通过开发用于纳米颗粒生产的模块化平台技术，实现智能连续纳米颗粒制造。开发实时表征颗粒大小、成分和形态的方法，再加上计算机化的反应堆控制该项目将有助于纳米颗粒形成和生产的算法驱动的自我优化。关键技术成果包括实时颗粒分析方法、强大的纳米颗粒过程和控制环境，以及用于强化数据驱动开发的使能技术。方法：通过文献检索和与行业合作伙伴的合作，这项工作的最初重点将是识别与生物制药行业相关的聚合物纳米颗粒和兼容包封剂靶标。该项目将开发认知化工制造EPSRC项目控制平台，并进一步开发集成纳米颗粒混合合成、分离和提纯的自动化控制系统，配备在线分析，用于监测颗粒特性。该平台的性能是提供有针对性的纳米颗粒，并加深对各种纳米颗粒类型的基本了解。该项目的潜在影响：该项目旨在提供一种自主和快速生成目标纳米颗粒的方法。这些材料具有重大的社会和经济影响(例如，在疫苗和定向释放药物的开发方面)。这种材料的加速开发将使患者能够更快地接受治疗，因此可能会挽救生命，同时还会带来经济回报。更广泛地说，机器学习在工业工作流程中的集成为整个项目团队(工业和学术)提供了经验，这可能会在阿斯利康和利兹大学产生更广泛的影响，因为工业4.0实践被纳入正常工作。预期交付成果：4个月-聚合物纳米颗粒生成路线的文献综述9个月-使用所选纳米颗粒系统的SAXS、DLS、UV-VIS进行在线测量18个月-建立集成控制、在线分析和反馈优化的平台30-2个月使用机器学习方法优化聚合物纳米颗粒的案例研究36个月-自主方法与手动优化的基准

Aims: The project is envisioned to enable smart continuous nanoparticles manufacturing by developing a modular platform technology for nanoparticle production. Development of methods for real time characterisation of particle size, composition and morphology coupled with computerised reactor control the project will contribute towards algorithmic driven self-optimisation of nanoparticle formation and production. Key technology output includes real-time particle analysis methods, a robust nanoparticle process and control environment and an enabling technology for intensified data driven development. Methodology:The initial focus of the work will be identification of polymeric nanoparticles and compatible encapsulant targets relevant to biopharmaceutical industries by literature searching and collaboration with the industrial partners. The project will exploit the Cognitive Chemical Manufacturing EPSRC project control platform and further develop an automated control system integrating mixing and synthesis, separation and purification of nanoparticles equipped with online analytics for monitoring of particle characteristics. The platform's performance to deliver targeted nanoparticles and develop fundamental understanding of various nanoparticle types. Potential Impact of Project:This project aims to deliver an autonomous and rapid method for rapidly generating targeted nanoparticles. These materials have significant societal and economic impact (for example in the development of vaccines and targeted release medicines). Accelerated development of such materials will enable a faster route to patients and may therefore save lives whilst also providing economic returns. More generally the integration of machine learning within an industrial workflow provides experience to the whole project team (both industrial and academic) which may result in wider impact at AstraZeneca and the University of Leeds as Industry 4.0 practices are incorporated within normal working. Expected Deliverables:Month 4 - Literature review of polymeric nanoparticle generation routes Month 9 - Online measurements with SAXS, DLS, UV-Vis of chosen nanoparticle System Month 18 - Established platform integrating control, online analysis and feedback optimisation Month 30 - 2 Case study optimisations of polymeric nanoparticles using machine learning methods Month 36 - Benchmarking of autonomous method vs manual optimisation