Real-time optimisation control of batch processes

Batch processes are widely used in the pharmaceutical, specialty chemical, and food industry for the responsive agile manufacturing of high value added products. Some notable difficulties in the optimisation and control of batch processes include nonlinearity, expensive nature of first principle modelling, and batch to batch variations. An integrated approach to the real-time optimisation control and model parameter estimation will be investigated in this project. In order to overcome the difficulties in developing detailed mechanistic models, data-driven models will be developed using machine learning techniques such as neural networks. Real-time optimisation incorporating model adaptation and model prediction reliability will be investigated. Reinforcement learning techniques will be investigated for batch to batch control. Simulated benchmark batch processes, as well as real industrial processes from potential industrial collaborators, will be used as case studies. 

Newcastle University is committed to being a fully inclusive Global University which actively recruits, supports and retains colleagues from all sectors of society.  We value diversity as well as celebrate, support and thrive on the contributions of all our employees and the communities they represent.  We are proud to be an equal opportunities employer and encourage applications from everybody, regardless of race, sex, ethnicity, religion, nationality, sexual orientation, age, disability, gender identity, marital status/civil partnership, pregnancy and maternity, as well as being open to flexible working practices.