• Chinese Journal of Lasers
  • Vol. 50, Issue 11, 1101001 (2023)
Hanshuo Wu1、2、3, Min Jiang1、4, and Pu Zhou1、*
Author Affiliations
  • 1College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, Hunan, China
  • 2Nanhu Laser Laboratory, National University of Defense Technology, Changsha 410073, Hunan, China
  • 3State Key Laboratory of Pulsed Power Laser Technology, Changsha 410073, Hunan, China
  • 4Test Center, National University of Defense Technology, Xi an 710106, Shaanxi, China
  • show less
    DOI: 10.3788/CJL230692 Cite this Article Set citation alerts
    Hanshuo Wu, Min Jiang, Pu Zhou. Artificial Intelligence-Assisted Laser Science and Technology: Status, Opportunities, and Challenges[J]. Chinese Journal of Lasers, 2023, 50(11): 1101001 Copy Citation Text show less
    Publication numbers of in-title papers and in-topic papers related to AI-assisted laser technology in Web of Science
    Fig. 1. Publication numbers of in-title papers and in-topic papers related to AI-assisted laser technology in Web of Science
    Word cloud of keywords
    Fig. 2. Word cloud of keywords
    Topological graph of neural network model for predicting PCF properties[22]
    Fig. 3. Topological graph of neural network model for predicting PCF properties[22]
    Flow chart of forward design and inverse design of mode selective coupler[34]
    Fig. 4. Flow chart of forward design and inverse design of mode selective coupler[34]
    Topology structure of forward neural network with 7 input ports and 200 output ports[35]
    Fig. 5. Topology structure of forward neural network with 7 input ports and 200 output ports[35]
    Schematic of self-tuning mode-locked fiber laser[45]. (a) Objective function of laser cavity, optic components, and laser; (b) variational autoencoder; (c) latent variable mapping; (d) model prediction module
    Fig. 6. Schematic of self-tuning mode-locked fiber laser[45]. (a) Objective function of laser cavity, optic components, and laser; (b) variational autoencoder; (c) latent variable mapping; (d) model prediction module
    Model diagram and modeling process[47]. (a) Model diagram with prior information; (b) modeling process of mode-locked laser based on AI
    Fig. 7. Model diagram and modeling process[47]. (a) Model diagram with prior information; (b) modeling process of mode-locked laser based on AI
    Schematics of model network structure[50]. (a) Specific type of optical fiber model; (b) general optical fiber model
    Fig. 8. Schematics of model network structure[50]. (a) Specific type of optical fiber model; (b) general optical fiber model
    CBC system based on deep learning technique[63]. (a) Principle of system; (b) schematic of neural network workflow
    Fig. 9. CBC system based on deep learning technique[63]. (a) Principle of system; (b) schematic of neural network workflow
    Schematic of mode decomposition network[66]
    Fig. 10. Schematic of mode decomposition network[66]
    Architecture diagram of pulse shape prediction model based on convolutional neural network[79]
    Fig. 11. Architecture diagram of pulse shape prediction model based on convolutional neural network[79]
    Network architecture used for optimization of carbon dioxide laser cutting tungsten alloy process parameters[84]
    Fig. 12. Network architecture used for optimization of carbon dioxide laser cutting tungsten alloy process parameters[84]
    Hanshuo Wu, Min Jiang, Pu Zhou. Artificial Intelligence-Assisted Laser Science and Technology: Status, Opportunities, and Challenges[J]. Chinese Journal of Lasers, 2023, 50(11): 1101001
    Download Citation