Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram Prediction

A high-resolution and wide measurement range displacement sensing method based on multimode fiber (MMF) is proposed. To achieve a high-resolution displacement detection model, a one-shot dataset was constructed by collecting MMF specklegram images for 1801 displacements with resolution of 0.01 mm. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Bohao Shen, Jianzhi Li
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030297852149760
author Bohao Shen
Jianzhi Li
author_facet Bohao Shen
Jianzhi Li
author_sort Bohao Shen
collection DOAJ
description A high-resolution and wide measurement range displacement sensing method based on multimode fiber (MMF) is proposed. To achieve a high-resolution displacement detection model, a one-shot dataset was constructed by collecting MMF specklegram images for 1801 displacements with resolution of 0.01 mm. This work modifies the fully connected layer of a residual network (ResNet) to achieve displacement prediction and applies residual scaling to reduce prediction errors in the one-shot learning task. Under stable environmental conditions, experimental results show that this method achieves an average error as low as 0.0083 mm in displacement prediction with resolution of 0.01 mm; meanwhile, the measurement range reaches 18 mm. Additionally, the model trained on a 0.01 mm resolution dataset was evaluated on a specklegram dataset with a resolution of 0.005 mm for its generalization ability, yielding an average error of 0.0138 mm. Regression evaluation metrics demonstrate that the proposed model has a significant improvement over other displacement-sensing methods based on MMF specklegrams, with prediction errors approximately three times lower than ResNet. Additionally, temperature immunity was studied within an 18 mm measurement range under a temperature range from 21.25 °C to 22.35 °C; the MMF displacement sensor demonstrates a dispersion of 5.08%, an average nonlinearity of 7.71% and a hysteresis of 6.13%. These findings demonstrate the potential of this method for high-performance displacement-sensing in practical applications.
format Article
id doaj-art-bf4ebf0dbdb54ce5b348428004710f52
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-bf4ebf0dbdb54ce5b348428004710f522025-08-20T02:59:15ZengMDPI AGSensors1424-82202025-02-01255143410.3390/s25051434Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram PredictionBohao Shen0Jianzhi Li1School of Mechanical Engineering, Shijiazhuang Tiedao University, Shijiazhuang 050043, ChinaKey Laboratory of Structural Health Monitoring and Control, Shijiazhuang Tiedao University, Shijiazhuang 050043, ChinaA high-resolution and wide measurement range displacement sensing method based on multimode fiber (MMF) is proposed. To achieve a high-resolution displacement detection model, a one-shot dataset was constructed by collecting MMF specklegram images for 1801 displacements with resolution of 0.01 mm. This work modifies the fully connected layer of a residual network (ResNet) to achieve displacement prediction and applies residual scaling to reduce prediction errors in the one-shot learning task. Under stable environmental conditions, experimental results show that this method achieves an average error as low as 0.0083 mm in displacement prediction with resolution of 0.01 mm; meanwhile, the measurement range reaches 18 mm. Additionally, the model trained on a 0.01 mm resolution dataset was evaluated on a specklegram dataset with a resolution of 0.005 mm for its generalization ability, yielding an average error of 0.0138 mm. Regression evaluation metrics demonstrate that the proposed model has a significant improvement over other displacement-sensing methods based on MMF specklegrams, with prediction errors approximately three times lower than ResNet. Additionally, temperature immunity was studied within an 18 mm measurement range under a temperature range from 21.25 °C to 22.35 °C; the MMF displacement sensor demonstrates a dispersion of 5.08%, an average nonlinearity of 7.71% and a hysteresis of 6.13%. These findings demonstrate the potential of this method for high-performance displacement-sensing in practical applications.https://www.mdpi.com/1424-8220/25/5/1434multimode fiber specklegramdisplacement sensorhigh resolution and wide rangedeep learningresidual scalingone-shot prediction
spellingShingle Bohao Shen
Jianzhi Li
Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram Prediction
Sensors
multimode fiber specklegram
displacement sensor
high resolution and wide range
deep learning
residual scaling
one-shot prediction
title Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram Prediction
title_full Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram Prediction
title_fullStr Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram Prediction
title_full_unstemmed Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram Prediction
title_short Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram Prediction
title_sort displacement sensing method based on residual scaling for one shot mmf specklegram prediction
topic multimode fiber specklegram
displacement sensor
high resolution and wide range
deep learning
residual scaling
one-shot prediction
url https://www.mdpi.com/1424-8220/25/5/1434
work_keys_str_mv AT bohaoshen displacementsensingmethodbasedonresidualscalingforoneshotmmfspecklegramprediction
AT jianzhili displacementsensingmethodbasedonresidualscalingforoneshotmmfspecklegramprediction