Machine learning-assisted design and control for period-one microwave photonic sensing signal

Microwave photonic (MWP) sensing and measurement are envisioned to be a promising alternative to the conventional pure electronic or optical solutions. A semiconductor laser (SL) with external optical feedback (EOF) operating in a period-one (P1) dynamic state contributes a new implementation archit...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Optics and laser technology Ročník 180; s. 111449
Hlavní autoři: Fang, Can, Ruan, Yuxi, Guo, Qinghua, Yu, Yanguang
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.01.2025
Témata:
Laser dynamics
Machine learning
Microwave photonics
Optical feedback effect
Self-mixing effect
Semiconductor laser with optical feedback
Self-mixing effect
Optical feedback effect
Semiconductor laser with optical feedback
Microwave photonics
Machine learning
Laser dynamics
ISSN:0030-3992
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Microwave photonic (MWP) sensing and measurement are envisioned to be a promising alternative to the conventional pure electronic or optical solutions. A semiconductor laser (SL) with external optical feedback (EOF) operating in a period-one (P1) dynamic state contributes a new implementation architecture for MWP systems. However, designing such a SL system to generate frequency-modulated MWP sensing signals through traditional Lang–Kobayashi (L–K) equations requires extensive computational effort to derive the system control parameters (SCP), making real-time adjustment of the SCP impossible in cases where it is needed. This paper proposes an effective design approach based on machine learning. A feedforward neural network (FNN), in conjunction with a gradient descent algorithm, is employed to fast and accurately ascertain the SCP, offering a solution readily applicable in the system design. Both simulation and experiment are conducted to validate the proposed approach. •Proposes a machine learning approach to optimize control for period-one state.•Solves computational bottlenecks of Lang–Kobayashi (L–K) equation method.•Uses a neural network with gradient descent to determine control parameters quickly.•Experimental validation confirmed the performance of the proposed method.
ISSN:0030-3992
DOI:10.1016/j.optlastec.2024.111449