Laser & Optoelectronics Progress, Volume. 59, Issue 12, 1220001(2022)

Inverse Modeling Approach for Ultra-Wideband Filters Based on IALO-HBP Neural Networks

Jingchang Nan1, Jingjing Du1、*, Mingming Gao1,2, and huan Xie1
Author Affiliations
  • 1School of Electronics and Information Engineering, Liaoning Technical University, Huludao 125105, Liaoning , China
  • 2Information Science and Technology College, Dalian Maritime University, Dalian 116026, Liaoning , China
  • show less
    Figures & Tables(9)
    HBP neural network structure
    Structure of dual notched bands UWB filter
    Correspondence between S21 with L5 and W5
    Reverse modeling process of double notch ultra-wideband filter based on IALO-HBP
    Comparison of the output values L5 of the four inverse models with the actual values of HFSS
    Comparison of the output values W5 of the four inverse models with the actual values of HFSS
    Comparison of the output values f of the four inverse models with the actual values of HFSS
    Comparison diagram of algorithm convergence curve
    • Table 1. Performance comparison of four modeling methods

      View table

      Table 1. Performance comparison of four modeling methods

      Reverse modeling methodMean square errorRunning time /s
      L5 /mmW5 /mmf /GHz
      IALO-HBP0.00166.0507×10-4

      0.0014

      0.0085

      0.0071

      0.0364

      3.977
      ALO-HBP0.00940.01039.711
      GA-HBP0.00800.006210.038
      BP0.06250.107111.700
    Tools

    Get Citation

    Copy Citation Text

    Jingchang Nan, Jingjing Du, Mingming Gao, huan Xie. Inverse Modeling Approach for Ultra-Wideband Filters Based on IALO-HBP Neural Networks[J]. Laser & Optoelectronics Progress, 2022, 59(12): 1220001

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Optics in Computing

    Received: Apr. 15, 2021

    Accepted: Jun. 11, 2021

    Published Online: May. 23, 2022

    The Author Email: Du Jingjing (1431181393@qq.com)

    DOI:10.3788/LOP202259.1220001

    Topics