Grid-Enabled Tabu Search for Electromagnetic Optimization Problems

Carcangiu, Sara; Fanni, Alessandra; Mereu, Anna; Montisci, Augusto

doi:10.1109/tmag.2010.2045487

Cited by 9 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, the left mold radius R 1 was also optimized. The objective function value of the this optimal solution was f = 0.012, which is comparable to the known solutions from the literature [31]. Regarding the sensitivity analysis, the optimization showed that, in order to reach very low values of the error function, the value of the R 1 parameter (the radius of the g − h curve which is the arc of circumference describing the left mold) tends to be close to the maximum allowed value (13).…”

Section: Full Fea-based Optimization and Model Validationsupporting

confidence: 71%

A Regularized Procedure to Generate a Deep Learning Model for Topology Optimization of Electromagnetic Devices

et al. 2021

View full text Add to dashboard Cite

The use of behavioral models based on deep learning (DL) to accelerate electromagnetic field computations has recently been proposed to solve complex electromagnetic problems. Such problems usually require time-consuming numerical analysis, while DL allows achieving the topologically optimized design of electromagnetic devices using desktop class computers and reasonable computation times. An unparametrized bitmap representation of the geometries to be optimized, which is a highly desirable feature needed to discover completely new solutions, is perfectly managed by DL models. On the other hand, optimization algorithms do not easily cope with high dimensional input data, particularly because it is difficult to enforce the searched solutions as feasible and make them belong to expected manifolds. In this work, we propose the use of a variational autoencoder as a data regularization/augmentation tool in the context of topology optimization. The optimization was carried out using a gradient descent algorithm, and the DL neural network was used as a surrogate model to accelerate the resolution of single trial cases in the due course of optimization. The variational autoencoder and the surrogate model were simultaneously trained in a multi-model custom training loop that minimizes total loss—which is the combination of the two models’ losses. In this paper, using the TEAM 25 problem (a benchmark problem for the assessment of electromagnetic numerical field analysis) as a test bench, we will provide a comparison between the computational times and design quality for a “classical” approach and the DL-based approach. Preliminary results show that the variational autoencoder manages regularizing the resolution process and transforms a constrained optimization into an unconstrained one, improving both the quality of the final solution and the performance of the resolution process.

show abstract

Section: Full Fea-based Optimization and Model Validationsupporting

confidence: 71%

A Regularized Procedure to Generate a Deep Learning Model for Topology Optimization of Electromagnetic Devices

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Amongst researches that have used meta-heuristic algorithms in the electromagnetic area, we can point to the research of Cau et al [1] using the neural network inversion-based designed of a high field superconducting dipole. Carcangiu et al [2] have optimized electromagnetic problems by using Tabu search. Savini and Di Barba [3] have done Loney's Solenoid optimization by means of a deterministic attitude and have presented acceptable results.…”

Section: Introductionmentioning

confidence: 99%

Modified BNMR algorithm applied to Loney's solenoid benchmark problem

Taherdangkoo¹,

Taherdangkoo

2014

International Journal of Applied Electromagnetics and Mechanics

View full text Add to dashboard Cite

We propose a new method for solving the Loney's solenoid benchmark problem based on Blind, Naked Mole-Rats (BNMR) algorithm. The key idea of the algorithm is using a β-distribution that can efficiently achieve the best solution for the position and size of two correcting coils in the famous Loney's solenoid problem. The results show the superiority of the proposed method on other previously methods for electromagnetic optimization.

show abstract

“…Carcangiu et al [2] have optimized electromagnetic problems by using Tabu search. Savini and Di Barba [3] have done Loney's Solenoid optimization by means of a deterministic attitude and have presented acceptable results.…”

Section: Introductionmentioning

confidence: 99%

Modified stem cells algorithm for Loney's solenoid benchmark problem

Taherdangkoo¹

2013

International Journal of Applied Electromagnetics and Mechanics

View full text Add to dashboard Cite

In this paper, we propose a new method for solving the Loney's solenoid benchmark problem based on stem cells algorithm (SCA). The key idea of the algorithm is using a modified version of our proposed stem cells optimization method that can efficiently achieve the best solution for the position and size of two correcting coils in the famous Loney's solenoid problem. The results show the superiority of the proposed method on other previously proposed methods for electromagnetic optimization.

show abstract

Grid-Enabled Tabu Search for Electromagnetic Optimization Problems

Cited by 9 publications

References 8 publications

A Regularized Procedure to Generate a Deep Learning Model for Topology Optimization of Electromagnetic Devices

A Regularized Procedure to Generate a Deep Learning Model for Topology Optimization of Electromagnetic Devices

Modified BNMR algorithm applied to Loney's solenoid benchmark problem

Modified stem cells algorithm for Loney's solenoid benchmark problem

Contact Info

Product

Resources

About