Multimodal Fusion Network for Micro-displacement Measurement via Michelson Interferometer

TL;DR

This paper introduces a multimodal fusion network that accurately measures micro-displacements using a modified Michelson interferometer, overcoming traditional limitations with a dual-head learning approach for real-time, noise-tolerant predictions.

Contribution

The paper presents a novel deep learning model that directly predicts displacement and interference order from interferograms, eliminating the need for multi-wavelength hardware or complex fitting.

Findings

Achieves 4.84 nm displacement precision

Classifies interference orders with 98% accuracy

Maintains stable accuracy under severe noise

Abstract

We propose a multimodal fusion network (MFN) for precise micro-displacement measurement using a modified Michelson interferometer. The model resolves the intrinsic half-wave displacement ambiguity that limits conventional single-wavelength interferometry by introducing a dual-head learning mechanism: one head performs sub-half-wave displacement regression, and the other classifies integer interference orders. Unlike dual-wavelength or iterative fitting methods, which require high signal quality and long computation time, MFN achieves robust, real-time prediction directly from interferometric images. Trained on 2x10^5 simulated interferograms and fine-tuned with only about 0.24% of real experimental data (about 500 images), the model attains a displacement precision of 4.84(15) nm and an order-classification accuracy of 98%. Even under severe noise, MFN maintains stable accuracy (about 16 nm RMSE), whereas conventional heuristic algorithms exhibit errors exceeding 100 nm. These results demonstrate that MFN offers a fast, noise-tolerant, and cost-efficient solution for single-wavelength interferometric metrology, eliminating the need for multi-wavelength hardware or complex phase fitting.