A FEM-Based Surrogate Modelling and Optimization Framework for Physics-Constrained Electromagnetic Coil Design

Yucheng Liu

cs.LGAug 19, 2026

A FEM-Based Surrogate Modelling and Optimization Framework for Physics-Constrained Electromagnetic Coil Design

Authors: Yucheng Liu

Organizations: Department of Engineering Science University of Oxford Oxford, United Kingdom

Abstract

This work evaluates surrogate-assisted optimization of a seven-parameter current-excited coil--core benchmark subject to geometric, manufacturing, and separate core and copper mass constraints. A Python--MPh--COMSOL workflow couples a two-dimensional axisymmetric finite-element method (FEM) model to a Matern 5/2 Gaussian-process (GP) probabilistic surrogate. Here, physics-constrained denotes a design problem evaluated by a governing-equation FEM model and restricted by explicit physical, geometric, manufacturing, and material-allocation constraints; it does not denote a physics-informed GP architecture. Sequential Bayesian optimization (BO) ranks candidates using expected improvement (EI), and every reported incumbent is verified by FEM. Five paired runs show that optimizer ranking depends on the available FEM-evaluation budget: EI--BO improves rapidly at small continuation budgets, COBYLA is stronger at the earliest checkpoint, and BOBYQA attains the highest mean terminal response. A retrospective finite-pool study further finds no robust endpoint advantage of EI over posterior-mean ranking on this smooth response surface. The broader result is that early progress, terminal response, information use, and wall-clock cost can favor different methods in simulation-driven design. A selected-design check at a common total current preserves the observed BOBYQA--COBYLA--EI-BO ordering. The conclusions nevertheless remain conditional on this axisymmetric benchmark and do not establish a fixed-current optimum, fixed-power performance, or electrical-efficiency superiority.

Figures & tables

Study	FEM/EM	GP uncertainty	Sequential BO	Constraints	Repeated	Distinguishing scope
Li et al. [ 11 ]	Yes	No	No	Geometry	No	RF-coil $B_{1}$ homogeneity evaluated with field histograms.
Shi and Ludwig [ 12 ]	Yes	No	No	Application-specific	No	MRI gradient-coil optimization coupled directly to FEM.
Petkovska et al. [ 13 ]	Yes	No	No	Application-specific	No	FEM-coupled genetic optimization of electromagnetic-device designs.
Satonkar et al. [ 14 ]	Yes	No	No	Bounded DOE	No	Two-dimensional FEM with deterministic response-surface methodology.
This benchmark study	Yes	Yes	Yes	Geometry and mass	Five EI seeds	Held-out calibration, observed-FEM accounting, and a paired policy ablation.

TABLE I: Illustrative positioning against selected verified electromagnetic-design studies. The table is not an exhaustive survey. “Repeated” denotes repeated optimization runs, not repeated solver calls.

Panel of Figure 2 — Fig. 1: Seven-stage workflow used in the reported experiment.

Symbol	Description	Unit	Feasible range
$c_{1}$	Aperture radius	mm	$[0.5,\,5]$
$r_{1}$	Lower core radius	mm	$[10,\,20]$
$t_{1}$	Radial extension of upper core	mm	$[0.5,\,10]$
$l_{1}$	Lower core height	mm	$[2.5,\,20]$ , with $l_{1}\geq h_{1}+2$
$l_{2}$	Upper core height	mm	$[0.5,\,20]$
$w_{1}$	Coil radial width	mm	$[0.5,\,5]$

TABLE II: Independent design variables defining the parameterized benchmark geometry.

Symbol	Description	Unit	Value / Assumption
$\rho_{\mathrm{Cu}}$	Copper density	kg m -3	8940
$\sigma_{\mathrm{Cu}}$	Coil electrical conductivity	S m -1	$6.0\times 10^{7}$
$J_{\mathrm{apply}}$	Applied current-density parameter	A m -2	$1.0\times 10^{6}$
$\rho_{\mathrm{core}}$	Core density	kg m -3	7000
$B_{\mathrm{sat}}$	High Flux saturation flux density	T	1.5 [ 18 ]
Grade	Manufacturer nominal permeability grade	–	125 [ 18 ]

TABLE III: Fixed physical and material parameters for the regenerated benchmark.

Symbol	Description	Unit	Expression
$r_{2}$	Upper core radius	mm	$r_{1}+t_{1}$
$r_{0}$	Coil outer radius	mm	$r_{1}+w_{1}$
$M_{\mathrm{core}}$	Core mass	kg	$\rho_{\mathrm{core}}V_{\mathrm{core}}$
$M_{\mathrm{coil}}$	Coil mass	kg	$\rho_{\mathrm{Cu}}V_{\mathrm{coil}}$
$M_{\mathrm{total}}$	Total mass	kg	$M_{\mathrm{core}}+M_{\mathrm{coil}}$
$I_{\mathrm{coil}}$	Applied coil current	A	$J_{\mathrm{apply}}w_{1}h_{1}$

TABLE IV: Derived geometric and screening quantities.

Panel of Figure 6 — Fig. 2: Meridional schematic of the axisymmetric benchmark parameterization (not to scale). The dashed copper-coil domain carries the current excitation and is included in the geometric and mass constraints.

Panel of Figure 7 — Fig. 3: Data flow of the proposed surrogate-modelling framework. The bounded physical design space is represented using dimensionless coordinates in the unit hypercube, where Latin hypercube sampling is performed. Each normalized sample is mapped back to its corresponding physical geometry for constraint screening and FEM reference-model evaluation. The normalized coordinates and their associated FEM responses are subsequently paired to construct the Gaussian-process dataset.

Panel of Figure 8 — Fig. 4: Representative seed-42 learning curves: (a) $R^{2}$ , (b) RMSE, (c) MAE, (d) empirical $\pm 1\sigma$ coverage, and (e) empirical $\pm 2\sigma$ coverage.

$N_{\mathrm{train}}$	$R^{2}$	RMSE	MAE	$C_{1\sigma}$	$C_{2\sigma}$
25	$0.9872\pm 0.0041$	$20.32\pm 2.92$	$14.07\pm 1.63$	$0.516\pm 0.097$	$0.776\pm 0.085$
50	$0.9973\pm 0.0013$	$9.14\pm 2.17$	$6.83\pm 1.62$	$0.580\pm 0.110$	$0.856\pm 0.071$
75	$0.9985\pm 0.0008$	$6.77\pm 1.86$	$4.77\pm 1.14$	$0.572\pm 0.117$	$0.868\pm 0.061$
100	$0.9991\pm 0.0004$	$5.33\pm 1.12$	$3.61\pm 0.53$	$0.668\pm 0.046$	$0.920\pm 0.035$
125	$0.9992\pm 0.0004$	$4.96\pm 1.30$	$3.18\pm 0.75$	$0.720\pm 0.075$	$0.908\pm 0.030$
150	$0.9994\pm 0.0003$	$4.38\pm 1.39$	$2.78\pm 0.77$	$0.712\pm 0.083$	$0.908\pm 0.058$

TABLE V: Learning-curve metrics across five train–validation splits, reported as mean

\pm

sample SD. RMSE and MAE are in

\mu\mathrm{T}

Metric	Value
$R^{2}$	$0.9993$
RMSE	$4.680~\mu\mathrm{T}$
MAE	$2.235~\mu\mathrm{T}$
$C_{1\sigma}$	$0.76$
$C_{2\sigma}$	$0.90$
Standardized-residual mean	$-0.449$

TABLE VI: Held-out performance of the 200-sample seed-42 GP used for the detailed diagnostic plots.

Variable	Length scale	Rank
$h_{1}$	$21.10\pm 3.36$	1
$w_{1}$	$22.56\pm 4.14$	2
$t_{1}$	$28.74\pm 3.35$	3
$l_{1}$	$28.84\pm 3.18$	4
$l_{2}$	$35.29\pm 6.24$	5
$r_{1}$	$36.58\pm 3.82$	6

TABLE VII: ARD length scales from the five 200-sample fits. Values are mean

\pm

sample SD on standardized input coordinates; lower values indicate stronger surrogate-implied variation, not causal importance.

Panel of Figure 12 — Fig. 5: Surrogate diagnostics: (a) seed-42 parity with $\pm 1\sigma$ error bars; and five-split 200-sample diagnostics comprising (b) the reliability curve with a cross-split $\pm$ sample-SD band (not a confidence band), (c) absolute error versus predictive standard deviation, and (d) a pooled standardized-residual Q–Q plot.

Fig. 6: Best FEM-observed response versus cumulative accounted FEM observations over five paired seeds. Every trajectory includes the same seed-specific 25-point initial set. Bands are pointwise 95% Student- $t$ intervals, not simultaneous confidence bands.

Policy	Endpoint (mT)	Improvement (mT)
Random	$0.713\pm 0.055$	$0.039\pm 0.053$
scikit-learn posterior mean	$0.738\pm 0.000$	$0.063\pm 0.097$
scikit-learn latent EI	$0.738\pm 0.000$	$0.063\pm 0.097$
BoTorch posterior mean	$0.738\pm 0.000$	$0.063\pm 0.097$
BoTorch logarithmic EI	$0.738\pm 0.000$	$0.063\pm 0.097$

TABLE VIII: Paired retrospective 25+50 policy ablation on the finite FEM pool. Values are mean

\pm

sample SD over five shared initializations.

Method	Runs	Best response, mean $\pm$ SD (mT)	Min–max (mT)
BOBYQA	5	$0.943\pm 0.027$	$0.910$ – $0.974$
COBYLA	5	$0.940\pm 0.021$	$0.918$ – $0.965$
EI-BO	5	$0.909\pm 0.012$	$0.890$ – $0.920$
Nelder–Mead	5	$0.743\pm 0.062$	$0.636$ – $0.780$
EGO	5	$0.724\pm 0.033$	$0.665$ – $0.740$

TABLE IX: Terminal FEM-observed responses. Values are mean

\pm

sample SD and range over five paired seeds. COBYLA terminal values include native early stopping.

Method	$n=25$	$n=30$	$n=40$	$n=50$
EI-BO	0.675	0.883	0.890	0.893
BOBYQA	0.675	0.675	0.685	0.830
COBYLA	0.675	0.938	–	–
EGO	0.675	0.675	0.680	0.680
Nelder–Mead	0.675	0.680	0.696	0.713

TABLE X: Mean best-observed response at selected cumulative FEM budgets (mT), over five paired seeds. A dash indicates that fewer than five COBYLA runs remained active at the checkpoint.

Method	Mean accounted FEM calls	End-to-end time (s)
EI-BO	75	$178.3\pm 28.3$
BOBYQA	75	$116.4\pm 1.8$
COBYLA	36	$91.6\pm 27.7$
EGO	75	$109.6\pm 3.8$
Nelder–Mead	75	$122.0\pm 5.1$

TABLE XI: End-to-end costs under the reported implementations. Values are means over five seeds and include the common estimated 25-point initial-FEM cost.

Quantity	EI-BO (seed 45)	BOBYQA (seed 45)	COBYLA (seed 42)
$c_{1}$	1.2371	0.5000	3.0313
$r_{1}$	11.8847	10.0921	10.0000
$t_{1}$	9.3159	10.0000	10.0000
$l_{1}$	7.7991	7.0412	7.0000
$l_{2}$	14.8635	19.7206	18.0930
$w_{1}$	4.9086	5.0000	5.0000

TABLE XII: Best FEM-observed designs from EI-BO, BOBYQA, and COBYLA. Dimensions are in mm, masses in g, current in A, and response in mT.

Fig. 7: Fresh-solve magnetic-flux-density maps for the selected EI-BO, BOBYQA, and COBYLA geometries at the production current density. The red segment marks the meridional ROI whose revolution defines the averaging surface. A common color scale is used across panels.

Fig. 8: Radial magnetic-flux-density profiles on the ROI line (z=-10) mm for the three selected designs. The plotted curves are interpolated from the fresh FEM solution nodes; the reported scalar objective remains COMSOL’s axisymmetrically weighted boundary average.

Fig. 9: Manufacturer-sourced High Flux 125 input (B)–(H) curve and the core-domain mean-to-maximum (B) intervals from fresh solves of the selected geometries. Each interval is a field-magnitude range, not a paired (B(H)) trajectory.

Design	Production $I$ (A)	Production ROI (mT)	Common- $I$ ROI (mT)	Core mean $B$ (mT)	Core max $B$ (mT)	Common- $I$ rank
EI-BO	24.234	0.91952	0.91952	2.858	18.981	3
BOBYQA	25.000	0.97361	0.94378	2.615	63.424	1
COBYLA	25.000	0.96515	0.93558	2.816	19.444	2

TABLE XIII: Selected-geometry physical diagnostics. The common-current case uses 24.234 A, the minimum production current among the three designs; no re-optimization is performed.

Check	Setting	$B_{\mathrm{ROI}}$ (T)	Relative change
$l_{1}$ variation	7.7991 mm (optimized)	0.00091952	reference
	6.9370 mm	0.00093006	$+1.147\%$
	7.3681 mm	0.00092518	$+0.616\%$
	7.2991 mm	0.00092584	$+0.688\%$
	8.2991 mm	0.00091372	$-0.631\%$
Automatic mesh	hauto =3, 2574 elements	0.00091952	$-0.069\%$ vs. finest

TABLE XIV: Local sensitivity checks around the seed-45 EI-BO design. The

l_{1}

rows use the production mesh and 200-mm domain; mesh and domain rows retain the optimized geometry.

Design	Setting	Elements	$B_{\mathrm{ROI}}$ (T)	Relative change
BOBYQA	hauto =3, 200 mm	6342	0.00097361	$-0.0036\%$ vs. finest
	hauto =2, 200 mm	12166	0.00097384	$+0.0206\%$ vs. finest
	hauto =1, 200 mm	36134	0.00097364	reference
	hauto =3, 300 mm	6670	0.00097540	$-0.0556\%$ vs. largest
	hauto =3, 400 mm	6450	0.00097594	reference
COBYLA	hauto =3, 200 mm	2149	0.00096515	$+0.5478\%$ vs. finest

TABLE XV: Mesh and outer-domain checks at the selected BOBYQA and COBYLA geometries. Mesh changes are relative to hauto =1 at 200 mm; domain changes are relative to 400 mm at hauto =3.

Surrogate-Assisted Optimization

Surrogate-assisted optimization uses learned approximations to find strong solutions when experiments or simulations are costly.

See all 104 papers

Jul 31, 2026

Frugal Bayesian Optimization: Scalable Surrogates for Data- and Resource-Limited Discovery

Bayesian Optimization (BO) is widely adopted for data-efficient optimization in scientific and engineering applications, yet its computational cost is rarely evaluated alongside optimization performance. Here we present a systematic, compute-aware study of BO that evaluates surrogate models along two axes: optimization quality and computational frugality. Across eight benchmark functions and nine real-world datasets spanning materials science, mechanics, robotics, chemistry, and machine learning, we benchmark four surrogate models: Gaussian Processes, Random Forests, NGBoost, and Bayesian Adaptive Spline Surfaces. We show that Gaussian Process-based BO consistently incurs the highest time and memory overhead without delivering superior optimization or sample efficiency. In contrast, scalable alternatives achieve equal or better performance at a fraction of the computational cost. Motivated by these findings, we introduce a surrogate-recommendation framework that predicts the most suitable BO surrogate from inexpensive dataset characteristics. Together, these results establish FruBO as a reproducible, compute-aware baseline for Bayesian Optimization and provide practical guidance for surrogate selection under limited computational and experimental budgets.

Panagiotis Krokidas, Christoforos Rekatsinas, Vassilis Sioros +3

Institute of Informatics and Telecommunications, National Centre for Scientific Research "Demokritos", Agia Paraskevi, Greece. · Department of Mechanical Engineering and Aeronautics, University of Patras, Patras Greece. · Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece. +4

Surrogate Modeling Bayesian Optimization

Ask PDF

Jun 13, 2026

Surrogate-Assisted Framework for SI-Compliant Interconnect Design Optimization Using the Earth Mover's Distance

This work presents a deterministic, machine-assisted framework for SI-compliant PCB design based on the Earth Mover's Distance (EMD). In contrast to conventional surrogate-based optimization methods that rely on iterative black-box search procedures, the proposed approach follows an interpretable, sequential evaluation strategy. Neural surrogate models are first used to efficiently predict waveform describing features from topology-dependent design parameters. A decision tree then acts as a physically motivated quality gate that identifies SI-compliant waveforms according to predefined SI criteria. Within the resulting valid solution space, the Earth Mover's Distance is employed as a similarity metric to rank candidate designs according to their proximity to an ideal reference signal. This enables not only the deterministic identification of admissible parameter regions but also a transparent prioritization of physically superior solutions without inverse modeling or stochastic search procedures. The methodology is demonstrated using a large-scale set of simulated DDR3 fly-by waveforms. By combining surrogate prediction, interpretable classification, and EMD-based waveform evaluation, the framework provides an explainable and computationally efficient alternative to conventional optimization strategies for supporting PCB development with AI-based methods.

Emre Ecik, Werner John, Julian Withöft +2

Information Processing Lab, TU Dortmund University, 44227 Dortmund, Germany · Pyramide2525/TU Dortmund University, 33100 Paderborn, Germany · EMC Technology Center Paderborn, Zuken GmbH, 33100 Paderborn, Germany

Surrogate-Assisted Optimization Electronic Design Automation Decision Tree Learning

Ask PDF

Oct 5, 2026

Simplified Swarm Optimization for Surrogate-Assisted Reliability Design of Insulated-Gate Bipolar Transistor Power Modules Using an Open-Source Process Finite-Element Model

Process-induced warpage, ceramic stress and solder strain limit the reliability of insulated-gate bipolar transistor (IGBT) modules on direct-bonded copper (DBC) substrates. Surrogate-assisted design studies train regression models on finite-element analysis (FEA) databases, but rarely check the optimized designs against new FEA or report how surrogate error interacts with the optimizer. This paper builds and evaluates an open pipeline: an open-source process finite-element model, surrogates tuned by Simplified Swarm Optimization (SSO), multi-objective design search, FEA confirmation of selected designs and confirmation-driven infill. The model starts at the second reflow and reproduces measured warpage within 18.2%, 33.6% and 15.3% at the reflow, housing and molding stages without fitted parameters. On a balanced 60-design database, all stochastic tuners reach the same test accuracy, outperform the published grid on cross-validated performance for every output but generalize better only for warpage; the cross-validated ranking of tuners does not transfer to the test set. With equal result reporting, multi-objective SSO and the non-dominated sorting genetic algorithm II give comparable Pareto fronts; a corrected multi-objective particle swarm optimizer trails both. FEA confirmation shows that warpage predictions hold (mean absolute error 0.5%), whereas at the design-space bounds reached by the optimizers the ceramic-stress surrogate is optimistic by up to 26%. Two confirmation-driven infill rounds reduce this error to 1-10% and halve the out-of-sample error; no confirmed design improves on the database in ceramic stress. Ceramic-stress results are indicative, as the metric is mesh-sensitive at production resolution. The model, database, scripts and pre-registered and post-registration results are released.

Wei-Chang Yeh

Department of Industrial Engineering and Engineering Management, National Tsing Hua University, Hsinchu 300044, Taiwan

Surrogate-Assisted Optimization Semiconductor Manufacturing Finite Element Method Particle Swarm Optimization Multi-Objective Optimization

Ask PDF

Abstract

Surrogate-Assisted Optimization

Explore similar work

Frugal Bayesian Optimization: Scalable Surrogates for Data- and Resource-Limited Discovery

Surrogate-Assisted Framework for SI-Compliant Interconnect Design Optimization Using the Earth Mover's Distance

Simplified Swarm Optimization for Surrogate-Assisted Reliability Design of Insulated-Gate Bipolar Transistor Power Modules Using an Open-Source Process Finite-Element Model