English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Chemical plant design and optimisation have proven challenging due to thecomplexity of these real-world systems. The resulting complexity translatesinto high computational costs for these systems' mathematical formulations andsimulation models. Research has illustrated the benefits of using machinelearning surrogate models as substitutes for computationally expensive modelsduring optimisation. This paper extends recent research into optimisingchemical plant design and operation. The study further explores SurrogateAssisted Genetic Algorithms (SA-GA) in more complex variants of the originalplant design and optimisation problems, such as the inclusion of parallel andfeedback components. The novel extension to the original algorithm proposed inthis study, Surrogate Assisted NSGA-\Romannum{2} (SA-NSGA), was tested on apopular literature case, the Pressure Swing Adsorption (PSA) system. We furtherprovide extensive experimentation, comparing various meta-heuristicoptimisation techniques and numerous machine learning models as surrogates. Theresults for both sets of systems illustrate the benefits of using GeneticAlgorithms as an optimisation framework for complex chemical plant systemdesign and optimisation for both single and multi-objective scenarios. Weconfirm that Random Forest surrogate assisted Evolutionary Algorithms can bescaled to increasingly complex chemical systems with parallel and feedbackcomponents. We further find that combining a Genetic Algorithm framework withMachine Learning Surrogate models as a substitute for long-running simulationmodels yields significant computational efficiency improvements, 1.7 - 1.84times speedup for the increased complexity examples and a 2.7 times speedup forthe Pressure Swing Adsorption system.

Surrogate Assisted Evolutionary Multi-objective Optimisation applied to a Pressure Swing Adsorption system