A new formulation for symbolic regression to identify physico-chemical laws from experimental data

•Automated identification of physical laws from noisy experimental data demonstrated.•Symbolic regression problem is formulated using directed acyclic graphs.•Demonstration of physical knowledge generated from the robotically collected data. A modification to the mixed-integer nonlinear programming...

Celý popis

Podrobná bibliografie

Vydáno v:	Chemical engineering journal (Lausanne, Switzerland : 1996) Ročník 387; s. 123412
Hlavní autoři:	Neumann, Pascal, Cao, Liwei, Russo, Danilo, Vassiliadis, Vassilios S., Lapkin, Alexei A.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier B.V 01.05.2020
Témata:	Automated model construction Chemical process development Global optimization Mixed-integer nonlinear programming (MINLP) Model identification Symbolic regression Symbolic regression Mixed-integer nonlinear programming (MINLP) Global optimization Chemical process development Automated model construction Model identification
ISSN:	1385-8947, 1873-3212
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!