arXiv subjects

Marco Baldan

Publications and source records attributed to Marco Baldan.

4 recordsLinked to original sources

arXiv2026

Deep Learning for Model Calibration in Simulation of Itaconic Acid Production

In this study, deep learning is used to estimate kinetic parameters for modeling itaconic acid production based on real batch experiments conducted at different agitation speeds and reactor scales. Two deep learning strategies, namely direct deep learning (DDL) and generative conditional flow matching (CFM) are compared and benchmarked against nonlinear regression as a reference method. Compared with DDL, CFM consistently yields more accurate results. The concentration profiles predicted by CFM closely match those obtained from nonlinear regression, whereas DDL results in larger deviations. Similar behavior is observed in the scale-up experiments, where the CFM model again generalizes better and is more robust than the direct approach. These findings demonstrate that CFM can reliably predict system behavior across different operating conditions and scales, offering a flexible and data-efficient framework for parameter estimation in dynamic bioprocess models.

cs.LG↗

arXiv2024

Energy-based PINNs for solving coupled field problems: concepts and application to the multi-objective optimal design of an induction heater

Physics-informed neural networks (PINNs) are neural networks (NNs) that directly encode model equations, like Partial Differential Equations (PDEs), in the network itself. While most of the PINN algorithms in the literature minimize the local residual of the governing equations, there are energy-based approaches that take a different path by minimizing the variational energy of the model. We show that in the case of the steady thermal equation weakly coupled to magnetic equation, the energy-based approach displays multiple advantages compared to the standard residual-based PINN: it is more computationally efficient, it requires a lower order of derivatives to compute, and it involves less hyperparameters. The analyzed benchmark problems are the single- and multi-objective optimal design of an inductor for the controlled heating of a graphite plate. The optimized device is designed involving a multi-physics problem: a time-harmonic magnetic problem and a steady thermal problem. For the former, a deep neural network solving the direct problem is supervisedly trained on Finite Element Analysis (FEA) data. In turn, the solution of the latter relies on a hypernetwork that takes as input the inductor geometry parameters and outputs the model weights of an energy-based PINN (or ePINN). Eventually, the ePINN predicts the temperature field within the graphite plate.

cs.CE↗

arXiv2023

Continuous Synthesis of Diazo Acetonitrile: From Experiments to Physical and Grey-Box Modeling

Diazo compounds are gathering interest for their potential in promoting greener synthesis routes. We investigate, at a lab-scale, the continuous synthesis of diazo acetonitrile (DAN) using a micro-structured flow reactor and a flow reaction calorimeter. Data concerning DAN formation in the former, and relative to reaction heat and gas flow rate in the latter, are collected. We present both a physical and a grey-box simulation model, both of which are calibrated to our measurements. Both models provide valuable insights into the DAN synthesis. The grey-box approach is useful to incorporate the complex chemical reaction pathways for DAN synthesis and decomposition that are currently hard to address with the physical model.

math.OC↗

arXiv2023

Multi-Criteria Shape Optimization of Flow Fields for Electrochemical Cells

We consider the shape optimization of flow fields for electrochemical cells. Our goal is to improve the cell by modifying the shape of its flow field. To do so, we introduce simulation models of the flow field with and without the porous transport layer. The latter is less detailed and used for shape optimization, whereas the former is used to validate our obtained results. We propose three objective functions based on the uniformity of the flow and residence time as well as the wall shear stress. After considering the respective optimization problems separately, we use techniques from multi-criteria optimization to treat the conflicting objective functions systematically. Our results highlight the potential of our approach for generating novel flow field designs for electrochemical cells.

math.OC↗