Marco Baldan

Marco Baldan

Auto-generated profile, based on publicly available information

Marco Baldan

Fraunhofer ITWM Fraunhofer‐Platz 1 67663 Kaiserslautern Germany

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2023 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
MBMarco Baldan
Marco Baldan
Paolo Di BarbaPaolo Di Barba
Paolo Di Barba
DLDavid A. Lowther
David A. Lowther
Physics-informed neural networks (PINNs) have been successfully applied in electromagnetism for the solution of direct problems. However, since PINNs typically do not take system parameters (like geometry or material properties) as input, when embedded in inverse problems or adopted for parametrical studies, in order to output the solution of the governing equations, they require additional training for each new system parameter set. To overcome this issue, we propose a hypernetwork (HNN) that receives system parameters and outputs the network weights of a PINN, which in turn provides the solution of the direct problem. Therefore, once trained, the HNN acts as a parametrized real-time field solver that allows the fast solution of inverse problems, in which the objective(s) are defined a-posteriori (i.e., after HNN’s training). This method is adopted for a coil optimal design task in magnetostatics.

5 February 2021 in IET Science, Measurement & Technology
Verified
Journal Article
Open access
PDF file
MBMarco Baldan
Marco Baldan
GBGiacomo Baldan
Giacomo Baldan
BNBernard Nacke
Bernard Nacke
Electromagnetics (EM) can be described, together with the constitutive laws, by four PDEs, called Maxwell's equations. “Quasi‐static” approximations emerge from neglecting particular couplings of electric and magnetic field related quantities. In case of slowly time varying fields, if inductive and resistive effects have to be considered, whereas capacitive effects can be neglected, the magneto quasi‐static (MQS) approximation applies. The solution of the MQS Maxwell's equations, traditionally obtained with finite differences and elements methods, is crucial in modelling EM devices. In this paper, the applicability of an unsupervised deep learning model is studied in order to solve MQS Maxwell's equations, in both frequency and time domain. In this framework, a straightforward way to model hysteretic and anhysteretic non‐linearity is shown. The introduced technique is used for the field analysis in the place of the classical finite elements in two applications: on the one hand, the B – H curve inverse determination of AISI 4140, on the other, the simulation of an induction heating process. Finally, since many of the commercial FEM packages do not allow modelling hysteresis, it is shown how the present approach could be further adopted for the inverse magnetic properties identification of new magnetic flux concentrators for induction applications.

9 May 2022 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
MBMarco Baldan
Marco Baldan
Paolo Di BarbaPaolo Di Barba
Paolo Di Barba
In the framework of induction hardening, the coil design task is particularly suitable to be formulated as multi-objective optimization problem. In fact, the Pareto front estimation raises the issue of guaranteeing a satisfactory diversity and number of non-dominated solutions to be provided to the decision maker (DM). In this paper, a generative adversarial network (GAN) and a forward neural network (FNN), which is cascade connected to the GAN generator, produce additional Pareto optimal solutions starting from the results of a genetic algorithm (NSGA-II) used as training set. The FNN ensures an accurate prediction of the objectives of the added solutions, removing the need for further field analyses. This method is first tested against two analytical problems and subsequently validated on a 3-objective coil design task to illustrate its utility for a real-world case.

24 March 2021 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
MBMarco Baldan
Marco Baldan
Paolo Di BarbaPaolo Di Barba
Paolo Di Barba
BNBernard Nacke
Bernard Nacke
In order to identify the magnetic properties of a magnetic steel, the synergy between the data arising from the experimental activity, a FE model, and the use of a multi-fidelity surrogate could relieve the burden of the total cost. A neural network, with as many outputs as fidelity levels, is adopted in quality of metamodel to describe the forward problem (forward neural network or FNN). FNN is trained using multiple losses aiming at getting a robust surrogate that is poorly sensitive to the chosen norm. This makes it bi-objective optimal, since several error metrics are simultaneously minimized. In addition, a conjugate, inverse net (INNCJ ) is built, which is a ready-to-use tool for inverse properties identification, since no optimization runs are required. Its performances are compared to those obtained with a transfer learning based approach (INNTR) and a single-fidelity inverse neural network (INNSF ). Finally, a real B – H curve identification task has been solved, thereby validating the conjugate inverse net.

9 April 2024 in Chemie Ingenieur Technik
Verified
Journal Article
Open access
SBSebastian Blauth
Sebastian Blauth
MBMarco Baldan
Marco Baldan
SOSebastian Osterroth
Sebastian Osterroth
CLChristian Leithäuser
Christian Leithäuser
Ulf-Peter ApfelUlf-Peter Apfel
Ulf-Peter Apfel
MBMichael Bortz
Michael Bortz

7 July 2024 in IET Science, Measurement & Technology
Verified
Journal Article
Open access
MBMarco Baldan
Marco Baldan
PBPaolo Di Barba
Paolo Di Barba
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. It is shown 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 by 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.