Search results for "Dynamical models"

showing 3 items of 3 documents

Insights into the compositional evolution of crustal magmatic systems from coupled petrological-geodynamical models

2020

Funding was provided by the VAMOS Research Center, University of Mainz (Germany) and by the ERC Consolidator Grant MAGMA (project #771143). The evolution of crustal magmatic systems is incompletely understood, as most studies are limited either by their temporal or spatial resolution. Exposed plutonic rocks represent the final stage of a long-term evolution punctuated by several magmatic events with different chemistry and generated under different mechanical conditions. Although the final state can be easily described, the nature of each magmatic pulse is more difficult to retrieve. This study presents a new method to investigate the compositional evolution of plutonic systems while consid…

Dike010504 meteorology & atmospheric sciencesHighly evolved rocksCoupled petrological-geodynamical models010502 geochemistry & geophysics01 natural sciencesLong-lived mush chambersSillGeochemistry and PetrologyPetrology0105 earth and related environmental sciencesgeographygeography.geographical_feature_categoryFractional crystallization (geology)GELarge phase diagram databaseContinental crustPartial meltingDASDepletion of rocks through dikingGeophysics13. Climate actionMagmaMagmatismIgneous differentiationGeologyGE Environmental SciencesJournal of Petrology
researchProduct

RNN- and LSTM-Based Soft Sensors Transferability for an Industrial Process

2021

The design and application of Soft Sensors (SSs) in the process industry is a growing research field, which needs to mediate problems of model accuracy with data availability and computational complexity. Black-box machine learning (ML) methods are often used as an efficient tool to implement SSs. Many efforts are, however, required to properly select input variables, model class, model order and the needed hyperparameters. The aim of this work was to investigate the possibility to transfer the knowledge acquired in the design of a SS for a given process to a similar one. This has been approached as a transfer learning problem from a source to a target domain. The implementation of a transf…

Computational complexity theoryProcess (engineering)Computer sciencesulfur recovery unit02 engineering and technologytransfer learningMachine learningcomputer.software_genrelcsh:Chemical technologyBiochemistryRNNField (computer science)ArticleAnalytical ChemistryDomain (software engineering)0202 electrical engineering electronic engineering information engineeringlcsh:TP1-1185Electrical and Electronic EngineeringInstrumentationsystem identificationHyperparameterbusiness.industry020208 electrical & electronic engineeringdynamical modelsSystem identificationAtomic and Molecular Physics and OpticsNonlinear systemRecurrent neural networksoft sensors020201 artificial intelligence & image processingArtificial intelligenceTransfer of learningbusinessLSTMcomputerDynamical models; LSTM; RNN; Soft sensors; Sulfur recovery unit; System identification; Transfer learningSensors
researchProduct

Validation of models for sprays

2016

We consider complex fluids consisting of a dispersed phase (solid particles or liquid droplets) immersed in a gas. A class of models describing the dynamics of such a kind of systems is given by a system of partial differential equations where a kinetic equation, describing the dispersed phase, is coupled to a fluid equation for the background gas. The coupling is given by the drag force exerted by the gas on the dispersed phase. Within this class, we shall analyse the case where the kinetic equation is a Vlasov-type equation and the fluid equation are of Stokes or Navier-Stokes type. We shall discuss the validation problem for this class of models, i.e. the derivation of the equations of t…

Modelling spray validation of hydrodynamical modelsSettore MAT/07 - Fisica Matematica
researchProduct