---
title: "Analytical-Prior Framework for Data-Efficient Prediction of Sound-Reduction Frequencies in Rectangular Side-Branch Helmholtz Resonators"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.16873v1"
permalink: "https://feed.astralor.com/items/itm_39ecefa78ed9be0d952c4f20"
published: "2026-08-17T17:53:14.000Z"
score: 75
channel: "ai"
tags: ["arXiv","Helmholtz Resonator","MLP","Support Vector Regression","Analytical-Prior Learning"]
---

# Analytical-Prior Framework for Data-Efficient Prediction of Sound-Reduction Frequencies in Rectangular Side-Branch Helmholtz Resonators

## AI commentary

> The value of this paper lies in treating cheap analytical models as prior knowledge rather than simple data augmentation. It is a practical idea for acoustic engineers and industrial ML teams facing expensive simulation data. The complementary design of residual learning and pretraining-fine-tuning is especially clever and worth extending to more physics-based prediction tasks.

## At a glance

High-fidelity finite-element simulations are accurate but expensive, and purely data-driven surrogates become unreliable with scarce labelled data. This study proposes an analytical-prior learning framework: retaining the analytical model at inference to learn only the residual, or distilling the analytical mapping into a learned prior before fine-tuning. On 86 simulation-labelled geometries and 8,998 analytical-only geometries, residual SVR reduces MAE from 3.375 Hz to 0.426 Hz, while analytical-prior pretrained MLP with full fine-tuning achieves 0.371 Hz. Across 20-70 training budgets, both routes consistently improve data efficiency.

## Key points

- Two complementary routes are proposed: explicit residual correction and analytical-prior pretraining, each tailored to different deployment needs.
- On 86 simulation-labelled geometries, residual SVR reduces MAE to 0.426 Hz, outperforming direct SVR's 3.375 Hz.
- Analytical-prior pretrained MLP with full fine-tuning achieves 0.371 Hz MAE, improving data efficiency across 20-70 sample budgets.
- Demonstrates a general framework for leveraging cheap analytical models to boost high-fidelity prediction under scarce data.

## Full text

High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expensive to generate and purely data-driven surrogates may become unreliable when simulation-labelled data are scarce. This study develops an analytical-prior learning framework that reuses a low-cost analytical model to improve data efficiency under limited high-fidelity simulation budgets. Two complementary routes are considered. When the analytical model remains available at inference, it is retained as an explicit baseline and the simulation data are used to learn only the analytical-to-simulation discrepancy. When a self-contained predictor is required, the analytical mapping is first distilled from abundant low-cost evaluations into a learned prior and then calibrated with the limited simulation data. The framework is evaluated on rectangular side-branch Helmholtz resonators using 86 simulation-labelled geometries and 8,998 non-overlapping analytical-only geometries. The analytical model achieved a mean absolute error (MAE) of 1.333 Hz. Direct support vector regression (SVR) achieved 3.375 Hz, while residual SVR reduced the MAE to 0.426 Hz. A direct multilayer perceptron (MLP) achieved 1.109 Hz, whereas analytical-prior pretraining reduced the error to 0.556 Hz with frozen-prior residual adaptation and 0.371 Hz with full-model fine-tuning. Across training budgets of 20 to 70 simulation-labelled cases, both analytical correction and analytical-prior pretraining consistently improved data efficiency relative to direct learning. These results show that analytical prior information can substantially improve high-fidelity prediction when simulation data are scarce, with explicit correction and prior distillation serving complementary deployment needs.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_39ecefa78ed9be0d952c4f20