A Novel Surrogate-Assisted Multi-Objective Optimization Algorithm for an Electromagnetic Machine Design

Lim, Dong-Kuk; Woo, Dong-Kyun; Yeo, Han-Kyeol; Jung, Sang-Yong; Ro, Jong‐Suk; Jung, Hyun–Kyo

doi:10.1109/tmag.2014.2359452

Cited by 38 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, the metric of choice will be the maximum input tolerance levels that ensure meeting the performance specifications (cf. tolerance hypervolume 39 ). In practice, the parameter deviations are often modelled using independent normal distributions N (0, σ ) (i.e., with mean equal to zero and variance σ common for all variables).…”

Section: Mo With Tolerance Analysis: Problem Formulationmentioning

confidence: 99%

“…These levels are expressed as probability distributions pertinent to the manufacturing process but also possible correlations between the system variables. Robust design problem can also be formulated in terms of finding the maximum parameter deviations for which the design specifications are still satisfied (e.g., design for maximum input tolerance hypervolume, MITH 39 ). Regardless of the problem statement, uncertainty quantification (UQ) is CPU intensive when executed with the use of traditional methods such as EM-based Monte Carlo (MC) analysis.…”

Section: Introductionmentioning

confidence: 99%

“…MO of antenna structures and arrays, in which MITH is estimated by means of machine learning methods involving GPR surrogates has been proposed in Ref. 39 . In Ref.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Rapid multi-criterial design of microwave components with robustness analysis by means of knowledge-based surrogates

Kozieł

Pietrenko‐Dabrowska

2023

Sci Rep

View full text Add to dashboard Cite

Manufacturing tolerances and uncertainties concerning material parameters, e.g., operating conditions or substrate permittivity are detrimental to characteristics of microwave components. The knowledge of relations between acceptable parameter deviations (not leading to violation of design specifications) and the nominal performance (not considering uncertainties), and is therefore indispensable. This paper proposes a multi-objective optimization technique of microwave components with tolerance analysis. The goal is to identify a set of trade-off designs: nominal performance versus robustness (quantified by the maximum input tolerance values that allow for achieving 100-percent fabrication yield). Our approach exploits knowledge-driven regression predictors rendered using characteristic points (features) of the component’s response for a rapid evaluation of statistical performance figures, along with trust-region algorithm to enable low execution cost as well as convergence. The proposed methodology is verified with the use of three microstrip circuits, a broadband filter, and two branch-line couplers (a single- and a dual-band one). It is demonstrated that a Pareto set w.r.t. nominal performance and robustness objectives can be produced using only 40 to 60 EM simulations of the respective structure (per design). Reliability of the proposed algorithm is corroborated with the use of EM-based Monte Carlo simulation.

show abstract

Section: Mo With Tolerance Analysis: Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rapid multi-criterial design of microwave components with robustness analysis by means of knowledge-based surrogates

Kozieł

Pietrenko‐Dabrowska

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Some of the widely used modeling techniques include neural networks [58][59][60], kriging [61], radial basis functions [62], polynomial chaos expansion [63], support vector regression [64], etc. Datadriven surrogates are used for global [65] and multi-objective design [66] and statistical analysis [67], and they are often combined with machine learning methods [68]. Their fundamental drawback is related to the curse of dimensionality [69], which hinders their applicability in higher-dimensional parameter spaces.…”

Section: Introductionmentioning

confidence: 99%

Globalized Knowledge-Based, Simulation-Driven Antenna Miniaturization Using Domain-Confined Surrogates and Dimensionality Reduction

2023

View full text Add to dashboard Cite

The design of contemporary antenna systems encounters multifold challenges, one of which is a limited size. Compact antennas are indispensable for new fields of application such as the Internet of Things or 5G/6G mobile communication. Still, miniaturization generally undermines electrical and field performance. When attempted using numerical optimization, it turns into a constrained problem with costly constraints requiring electromagnetic (EM) simulations. At the same time, due to the parameter redundancy of compact antennas, size reduction poses a multimodal task. In particular, the achievable miniaturization rate heavily depends on the starting point, while identifying a suitable starting point is a challenge on its own. These issues indicate that miniaturization should be addressed using global optimization methods. Unfortunately, the most popular nature-inspired algorithms cannot be applied for solving size reduction tasks because of their inferior computational efficacy and difficulties in handling constraints. This work proposes a novel methodology for the globalized size reduction of antenna structures. Our methodology is a multi-stage knowledge-based procedure, initialized with the detection of the approximate location of the feasible region boundary, followed by the construction of a dimensionality-reduced metamodel and global optimization thereof; the last stage is the miniaturization-oriented local refinement of geometry parameters. For cost reduction, the first stages of the procedure are realized with the use of a low-fidelity EM antenna model. Our approach is verified using four broadband microstrip antennas and benchmarked against multi-start local search as well as nature-inspired methods. Superior size reduction rates are demonstrated for all considered cases while maintaining reasonably low computational costs.

show abstract

“…The optimization process can be speed up by combing surrogate models with optimization strategies. Popular surrogate models include response surface model (RSM), radial basis function (RBF) model and Kriging interpolation [11][12][13][14][15][16]. They can construct approximate models with less FEA samples by using different design of experiment (DoE) techniques.…”

mentioning

confidence: 99%

Ultra-High-Dimensional Multi-Level Optimization Strategies for Electrical Machines

Liu

Zhang

Lei

et al. 2023

Preprint

View full text Add to dashboard Cite

Electrical machine optimization is normally a high-dimensional nonlinear multi-objective optimization problem. To improve the efficiency, multi-level optimization strategy is currently used, where sensitivity analysis is required for dividing design parameters into different groups. However, the conventional multi-level optimization strategy cannot handle ultra-high-dimensional optimization problems. To attempt this challenge, this paper proposes a sensitivity analysis method with variable weighted intervals to calculate the sensitivity coefficient in the parameter design range. Three improved multi-level optimization strategies based on different optimization algorithms and sequential sensitivity strategy are proposed, analyzed, and compared with the conventional multi-level optimization strategy. Through a case study of a synchronous reluctance machine, it can be seen that the proposed optimization strategies can improve the optimization results and efficiency of ultra-high-dimensional optimization of electrical machines.

show abstract

A Novel Surrogate-Assisted Multi-Objective Optimization Algorithm for an Electromagnetic Machine Design

Cited by 38 publications

References 8 publications

Rapid multi-criterial design of microwave components with robustness analysis by means of knowledge-based surrogates

Rapid multi-criterial design of microwave components with robustness analysis by means of knowledge-based surrogates

Globalized Knowledge-Based, Simulation-Driven Antenna Miniaturization Using Domain-Confined Surrogates and Dimensionality Reduction

Ultra-High-Dimensional Multi-Level Optimization Strategies for Electrical Machines

Contact Info

Product

Resources

About