A5000673024- Innovative Microfluidic and Catalytic Techniques Innovation
- Machine Learning in Materials Science
- Advanced Multi-Objective Optimization Algorithms
- Process Optimization and Integration
- Analytical Chemistry and Chromatography
- Electrocatalysts for Energy Conversion
- Gaussian Processes and Bayesian Inference
- CO2 Reduction Techniques and Catalysts
- Machine Learning and Algorithms
- Microfluidic and Capillary Electrophoresis Applications
- Chemical Synthesis and Analysis
- Ionic liquids properties and applications
- Advanced Control Systems Optimization
- Chemical Synthesis and Reactions
- Catalytic Processes in Materials Science
University of Leeds
2019-2023
Self-optimising chemical systems have experienced a growing momentum in recent years. Herein, we review algorithms used for the self-optimisation of reactions an accessible way general chemist.
There has been an increasing interest in the use of automated self-optimising continuous flow platforms for development and manufacture synthesis recent years. Such processes include multiple reactive work-up steps, which need to be efficiently optimised. Here, we report combination multi-objective optimisation based on machine learning methods (TSEMO algorithm) with multi-step reaction processes. This is demonstrated a pharmaceutically relevant Sonogashira reaction. We demonstrate how...
The consideration of discrete variables (e.g. catalyst, ligand, solvent) in experimental self-optimization approaches remains a significant challenge. Herein we report the application new mixed variable multi-objective optimization (MVMOO) algorithm for chemical reactions. Coupling MVMOO with an automated continuous flow platform enabled identification trade-off curves different performance criteria by optimizing and concurrently. This approach utilizes Bayesian methodology to provide high...
We herein report a novel kinetic modelling methodology whereby identification of the correct reaction model and parameters is conducted by an autonomous framework combined with transient flow measurements to enable comprehensive process understanding minimal user input. An automated chemistry platform was employed initially conduct linear flow-ramp experiments rapidly map profile three processes using data. Following experimental data acquisition, computational approach utilised discriminate...
An open-source reaction simulator was designed to benchmark the performance of multi-objective optimisation algorithms using chemistry-inspired test problems, which validated an experimental self-optimisation platform.
Although kinetic analysis has traditionally been conducted in a batch vessel, continuous-flow aided continues to swell popularity.
Abstract In many real-world problems there is often the requirement to optimise multiple conflicting objectives in an efficient manner. such can be a mixture of continuous and discrete variables. Herein, we propose new multi-objective algorithm capable optimising both bounded variables The utilises Gaussian processes as surrogates combination with novel distance metric based upon Gower similarity. MVMOO was compared existing mixed variable implementation NSGA-II random sampling for three...
A novel adaptive latent Bayesian optimisation (ALaBO) algorithm accelerates the development of mixed variable catalytic reactions.
A new hybridized algorithm that combines process optimisation with response surface mapping was developed and applied in an automated continuous flow reaction. Moreover, a photochemical cascade CSTR characterised by chemical actinometry, showing photon flux density of ten times greater than previously reported batch. The success the then evaluated aerobic oxidation sp³ C-H bonds using benzophenone as photosensitizer newly photo reactor.
An integrated flow platform enables the electrochemical synthesis of base-metal catalysts with high-throughput screening and rapid data generation.