Weak feedback self-mixing interference fringe slope discrimination method based on deep learning

Abstract

In order to identify the tilt direction of the self-mixing signals under weak feedback regime interfered by noise, a deep learning method is proposed. The one-dimensional U-Net (1D U-Net) neural network can identify the direction of the self-mixing fringes accurately and quickly. In the process of measurement, the measurement signal can be normalized and then the neural network can be used to discriminate the direction. Simulation and experimental results show that the proposed method is suitable for self-mixing interference signals with noise in the whole weak feedback regime, and can maintain a high discrimination accuracy for signals interfered by 5 dB large noise. Combined with fringe counting method, accurate and rapid displacement reconstruction can be realized.

Keywords

A

References

[1] Taimre T, Nikolic M, Bertling K. et al.. Laser feedback interferometry: a tutorial on the self-mixing effect for coherent sensing. Advances in optics and photonics, 2015, 7(3): 570-631. J]

[2] Sun H, Liu J G, Kennel R. Improving the accuracy of laser self-mixing interferometry for velocity measurement. 2017 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), May 22–25, 2017, Turin, Italy, 2017New YorkIEEE1-5[C]

[3] Zhao Y K, Guo Y, Wang C C. et al.. Design and experimental study of the biorthogonal linkage laser self-mixing angle sensor. Optics communications, 2020, 475: 126248. J]

[4] Wang X F, Yuan Y, Sun L Q. et al.. Self-mixing interference displacement measurement under very weak feedback regime based on integral reconstruction method. Optics communications, 2019, 445: 236-240. J]

[5] Hua Z Y, Zhu K Y, Wang Y F. et al.. Contrast-enhanced ultrasound-modulated laser feedback imaging with microbubbles. Optics and lasers in engineering, 2022, 157: 107134. J]

[6] Zhao Y K, Xiang R, Chen J S. et al.. Absolute angle-measurement with a dihedral mirror of the multi-longitudinal mode laser self-mixing sensor. Precision engineering, 2021, 68: 256-261. J]

[7] Sadiq O M, Amin S, Abmad Z. et al.. Fast and highly accurate phase unwrapping algorithm for displacement retrieval using self-mixing interferometry sensor. Optical materials, 2022, 129: 112553. J]

[8] Amin S. Implementation of Hilbert transform based high-resolution phase unwrapping method for displacement retrieval using laser self mixing interferometry sensor. Optics and laser technology, 2022, 149: 107887. J]

[9] Zhao Y, Zhang B F, Han L F. Laser self-mixing interference displacement measurement based on VMD and phase unwrapping. Optics communications, 2020, 456: 124588. J]

[10] Dong T J, Gao B K, Chen S H. et al.. Quadrature phase detection based on phase shift of self-mixing interferometer for real-time displacement measurement. Optics communications, 2021, 498: 127202. J]

[11] Li J Y, Niu H S, Niu Y X. Laser feedback interferometry and applications: a review. Optical engineering, 2017, 56: 050901. J]

[12] Siddiqui A A, Zabit U, Bernal O D. et al.. All analog processing of speckle affected self-mixing interferometric signals. IEEE sensors journal, 2017, 17: 5892-5899. J]

[13] Huang Z, Li C W, Li S Q. et al.. Speckle affected fringe detection based on three envelope extraction for self-mixing displacement measurement. Optics communications, 2017, 392: 100-108. J]

[14] Lecun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521: 436-444. J]

[15] Barland S, Gustave F. Convolutional neural network for self-mixing interferometric displacement sensing. Optics express, 2021, 29(8): 00433-11444. J]

[16] Chen J B, Wang X M, Wu Y B. et al.. Self-mixing interferometry based on a phase decomposition neural network. Chinese physics B, 2022, 61: 054103. J]

[17] An L, Liu B. Measuring parameters of laser self-mixing interferometry sensor based on back propagation neural network. Optics express, 2022, 30: 19134-19144. J]

[18] Xiao H Y, Yang W D, Wang Q. Liver cancer detection algorithm in dual-phase CT based on deep learning. Journal of optoelectronics-laser, 2025, 36(6): 664-672[J]

[19] Zhang S S, Zhang C, Wang X F. Rolling bearing fault diagnosis method based on deep subspace learning and data augmentation. Journal of optoelectronics-laser, 2025, 36(1): 69-76[J]

[20] Ahmed I, Zabit U, Salman A. Self-mixing interferometric signal enhancement using generative adversarial network for laser metric sensing applications. IEEE access, 2019, 7: 174641-174650. J]

[21] Kou K, Wang C, Lian T H. et al.. Fringe slope discrimination in laser self-mixing interferometry using artificial neural network. Optics and laser technology, 2020, 132: 106449. J]

[22] Moskalenko V, Zolotykh N, Osipov G. Deep learning for ECG segmentation. Advances in Neural Computation, Machine Learning, and Cognitive Research III, October 7–11, 2019, Dolgoprudny, Moscow Region, Russia, 2019ChamSpringer International Publishing246-254[C]

[23] Donati S. Developing self-mixing interferometry for instrumentation and measurements. Laser and photonics reviews, 2012, 6: 393-417. J]

[24] Xi J T, Yu Y G, Chicharo J F. et al.. Estimating the parameters of semiconductor lasers based on weak optical feedback self-mixing interferometry. IEEE journal of quantum electronics, 2005, 41(8): 1058-1064. J]

RIGHTS & PERMISSIONS

Tianjin University of Technology