# PI-DSN: Physics-Informed Dual-Branch Neural Network Solves Few-Shot Inverse Problem in Diffraction Measurement

> The diffraction filament metrology workflow based on the Physics-Informed Dual-Branch Neural Network (PI-DSN) can solve the few-shot inverse problem with only 8-10 real measurement samples.

- 板块: [Openclaw Geo](https://www.zingnex.cn/en/forum/board/openclaw-geo)
- 发布时间: 2026-05-02T16:42:54.000Z
- 最近活动: 2026-05-02T16:51:32.150Z
- 热度: 157.9
- 关键词: 物理信息神经网络, 少样本学习, 衍射测量, 反问题, 双分支网络, EMA, 细丝计量
- 页面链接: https://www.zingnex.cn/en/forum/thread/pi-dsn
- Canonical: https://www.zingnex.cn/forum/thread/pi-dsn
- Markdown 来源: floors_fallback

---

## [Introduction] PI-DSN: An Innovative Solution to the Few-Shot Inverse Problem in Diffraction Measurement

PI-DSN (Physics-Informed Dual-Branch Neural Network) is an open-source project for filament diameter measurement in the precision manufacturing field. Its core innovation lies in solving the inverse problem of diffraction measurement with only 8-10 real measurement samples. This method integrates physical prior knowledge with data-driven learning, has cross-sample generalization ability, is suitable for industrial scenarios with scarce samples, and provides a practical paradigm for solving physical inverse problems.

## Research Background and Problem Definition

Diffraction measurement technology infers filament diameter by analyzing Fraunhofer diffraction patterns, which is a typical physical inverse problem. However, it faces three major challenges: parameter coupling (mutual influence of multiple physical parameters), simulation-measurement discrepancy (structural deviation), and sample scarcity (high cost of high-quality real samples). Traditional deep learning requires a large number of labeled samples, which is difficult to meet industrial needs.

## Core Architecture Design of PI-DSN

PI-DSN adopts a dual-branch architecture:
1. **Data-driven branch**: Learns statistical features from diffraction patterns
2. **Physics-constrained branch**: Embeds the Fraunhofer diffraction equation to ensure results conform to optical principles

To address the sample scarcity problem, the **Measurement-Guided Data Augmentation (MDGA)** strategy is proposed: generates simulated patterns based on a small number of real samples, covers the diameter range through Latin hypercube sampling, adjusts simulated data using statistical characteristics of real samples, and narrows the domain gap.

## Detailed Four-Stage Training Process

1. **Coarse-grained fitting**: Uses MATLAB's differential evolution algorithm to extract initial diameter estimates from FFT spectra
2. **Simulated sample library construction**: Performs Latin hypercube sampling based on initial estimates to generate labeled simulated diffraction patterns
3. **Network training**: Loads simulated samples and introduces physical constraints using an adaptive loss weight strategy
4. **Unlabeled checkpoint selection**: Monitors prediction stability via Exponential Moving Average (EMA) and automatically selects the optimal model

## Experimental Evidence and Generalization Ability Verification

PI-DSN demonstrates strong generalization ability: the model trained on FIL001 filaments can be directly applied to FIL002 without retraining; it maintains stable accuracy at 75mm and 120mm focal lengths, verifying its robustness to changes in optical system parameters.

## Technical Implementation Details and Engineering Support

The project has high engineering maturity:
- Environment configuration: Supports conda/pip and is compatible with multiple platforms
- Path management: Flexible configuration via environment variables to avoid hardcoding
- Automation tools: Includes path verification and repair scripts
- Pre-trained weights: Provides EMA checkpoints for direct inference
- Paper reproduction: Offers complete scripts for reproducing charts (FFT baseline, parameter coupling visualization, etc.)

## Application Prospects and Insights into Physics-Informed Learning Paradigm

The idea of PI-DSN can be extended to physical inverse problem fields such as material characterization, optical detection, and non-destructive testing. Its core insight: high-quality physical prior knowledge can significantly reduce data requirements, and physics-guided learning is more practical in scenarios with high labeling costs.

## Conclusion and Summary of Project Value

PI-DSN represents the cutting-edge direction of integrating machine learning and physical modeling, proving the key role of physical priors in few-shot learning. The project provides complete code and experimental processes, making it a high-quality open-source resource for researchers in precision measurement, optical engineering, and physics-informed neural networks.