||Integration of ontology and knowledge-based optimization in process synthesis applications
|| Cecelja, D.F., Kokossis, P.A., Du, D.D.
||Computer Aided Chemical Engineering, vol.29, p.427-431
||High throughput; Knowledge models; Ontology; Process synthesis; Stochastic optimization
||Previous research has shown that knowledge-based optimization models in process synthesis applications are more robust in both providing final outputs and improving computational performance. This expands this approach by implementing a general knowledge models which in turn enables interpretation of solutions so that non-experts understand detailed procedures of optimization. To this end, an automatic ontology based optimization system that links rule-based optimization model and ontology has been introduced for the purpose to both improve optimization performance and to present new extracted knowledge at optimization run-time. A benchmark reactor network design synthesis case is studied for comparison of performance. The concomitant results show that not only can ontology-based optimization system improve robustness of solutions and computational performance, but also it enables a more accurate understanding of the process synthesis procedures and presents extracted knowledge in a decent format. © 2011 Elsevier B.V.
© Copyright 2020. All rights reserved. | Powered by Nevma