High-Precision Mode Decomposition for Few-Mode Fibers Based on Multi-Task Deep Learning

Tian, Zichen; Li, Pei; Wang, Jianshuai; Jiao, Z.; Hu, Kaihua; Chang, Yanbiao; Li, Zhiqi; Li, Jing; Ning, Tigang

doi:10.1109/jlt.2022.3208658

Cited by 6 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The normalized frequency of this fiber is about 4.43, so it can support six modes, which can be sequentially arranged as LP01, LP11e, LP11o, LP21e, LP21o, and LP02 modes. Due to the simplicity of the modes [30] , there are three possible cases of modes propagated by this fiber, which are the first three, five, and six modes. As the number of modes increases, the combination of eigenmodes becomes more complex and the number of near-field optical field images with different mode coefficients increases [25][26][27][28][29][30] .…”

Section: Resultsmentioning

confidence: 99%

“…Due to the simplicity of the modes [30] , there are three possible cases of modes propagated by this fiber, which are the first three, five, and six modes. As the number of modes increases, the combination of eigenmodes becomes more complex and the number of near-field optical field images with different mode coefficients increases [25][26][27][28][29][30] . Therefore, under the condition of supporting six modes with FMF, we generated 1000 random near-field light-field images for testing the MobileNetV3_Light network model for different training periods.…”

Section: Resultsmentioning

confidence: 99%

“…Rothe et al utilized Dense-Net convolutional neural network with up to 121 layers to achieve high-precision MD with eight modes superimposed [28] . Also artificially designed neural network-based methods [29] and multitask deep-learning methods [30] to achieve MD have been proposed successively and have shown better performance. However, all of the above methods use traditional convolutional neural networks for MD, which have problems such as long training time, high computer equipment requirements, and excessive computing resources consumption.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast mode decomposition for few-mode fiber based on lightweight neural network

Zhao,

Chen,

et al. 2024

中国光学快报

View full text Add to dashboard Cite

In this paper, we present a fast mode decomposition method for few-mode fibers, utilizing a lightweight neural network called MobileNetV3-Light. This method can quickly and accurately predict the amplitude and phase information of different modes, enabling us to fully characterize the optical field without the need for expensive experimental equipment. We train the MobileNetV3-Light using simulated near-field optical field maps, and evaluate its performance using both simulated and reconstructed near-field optical field maps. To validate the effectiveness of this method, we conduct mode decomposition experiments on a few-mode fiber supporting six linear polarization (LP) modes (LP01, LP11e, LP11o, LP21e, LP21o, LP02). The results demonstrate a remarkable average correlation of 0.9995 between our simulated and reconstructed near-field lightfield maps. And the mode decomposition speed is about 6 ms per frame, indicating its powerful real-time processing capability. In addition, the proposed network model is compact, with a size of only 6.5 MB, making it well suited for deployment on portable mobile devices.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast mode decomposition for few-mode fiber based on lightweight neural network

Zhao,

Chen,

et al. 2024

中国光学快报

View full text Add to dashboard Cite

show abstract

“…Alternatively, there have been significant process on developing additional modal decomposition methods working in near real time. Many approaches utilizing deep learning and neural networks have been proposed recently [7][8][9] while some incorporate physics inspired constraints and modeling to achieve more robust results 10,11 while others have proposed machine learning approaches operating in near real time. [12][13][14][15] The general trend in this category of modal decomposition methods rely on machine learning to shortcut computational steps in optimization routines or in interferometric beam analysis previously presented.…”

Section: Monitoring Transverse Modal Instability and Beam Qualitymentioning

confidence: 99%

Photonic lantern based real-time modal instability diagnostic tool for high power lasers

Cooper¹,

Yerolastsitis²,

Lopez-Zelaya³

et al. 2023

Fiber Lasers XX: Technology and Systems

View full text Add to dashboard Cite

We demonstrate a fast and versatile approach to analyze the modal content of a high power fiber amplifier using a low-loss photonic lantern. By monitoring the first three modes of the photonic lantern on a photodetector we can directly determine the modal content of a laser beam, enabling real time diagnostics of the output and its corresponding beam quality factor, M2. We first investigate the beam quality and modal content of the output of a passive LMA double clad fiber commonly used as a delivery fiber in high power fiber laser amplifiers. The output of the fiber is analyzed by both a 6-mode mode-selective photonic lantern and a conventional M2 setup utilizing a translation stage and beam profiler. The modal content and beam quality measurements produced in real-time by the photonic lantern are compared to the M2 measurements resulting in an RMS error less than 0.098 across M2 values between 1.020 to 2.260. We then conduct a follow on experiment using the same photonic lantern to monitor modal instability in a large mode area fiber laser amplifier. In this case, we compare our photonic lantern mode analysis approach versus the commonly used RIN/pinhole method evaluating modal instabilities. Not only does the photonic lantern estimate the modal content and beam quality in real-time but the modal content trends with the RIN metric as the fiber laser amplifier progresses from stable regime below 300W through the chaotic transverse modal instability regime above 400W.

show abstract

Bridge the gap between simulated and real-world data in optical fiber mode decomposition for accuracy improvement: A deep learning-based co-learning framework with visual similarity-based matching

Ren,

Xie,

et al. 2024

Expert Systems with Applications

View full text Add to dashboard Cite

High-Precision Mode Decomposition for Few-Mode Fibers Based on Multi-Task Deep Learning

Cited by 6 publications

References 27 publications

Fast mode decomposition for few-mode fiber based on lightweight neural network

Fast mode decomposition for few-mode fiber based on lightweight neural network

Photonic lantern based real-time modal instability diagnostic tool for high power lasers

Bridge the gap between simulated and real-world data in optical fiber mode decomposition for accuracy improvement: A deep learning-based co-learning framework with visual similarity-based matching

Contact Info

Product

Resources

About