Infrared and Laser Engineering, Volume. 54, Issue 7, 20250065(2025)

COD determination method using small-sample UV-Visible absorption spectral data

Peichao ZHENG1, Wei RUAN1, Shubin CHEN2, Haijuan LI2, Yan HOU2, Chenglin LI1, Haonan HE1, Qin YANG1, Jinmei WANG1、*, Biao LI1, and Lianbo GUO3
Author Affiliations
  • 1School of Electronic Science and Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • 2Chongqing Feiyang Measurement and Control Technology Research Institute Co., Ltd., Chongqing 400065, China
  • 3Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan 430074, China
  • show less
    Figures & Tables(12)
    GAN network structure diagram
    Process flow diagram
    COD concentration
    Experimental device
    Ultraviolet-Visible absorption spectrum
    Cumulative variance contribution ratio of top 15 principal components
    Comparison of the original data with the generated data. (a) Mean value; (b) Variance; (c) Skewness; (d) Kurtosis
    NRBO-SVR model fitting curves. (a) Training set; (b) Test set
    • Table 1. Differences in mean, variance, skewness, and kurtosis for different samples

      View table
      View in Article

      Table 1. Differences in mean, variance, skewness, and kurtosis for different samples

      Sample numberMean difference/arb.unitsVariance difference/arb.units2Skewness differenceKurtosis difference
      10.02%0.21%6.02%0.55%
      20.79%0.05%10.22%9.52%
      30.53%0.86%1.02%6.64%
      40.17%0.16%0.82%1.36%
      50.11%0.11%7.01%8.33%
      60.57%0.63%5.75%9.52%
      70.08%0.07%0.79%5.13%
      80.40%1.02%0.48%6.24%
      90.58%0.16%0.66%4.67%
      10-29············
      300.40%0.29%2.97%3.96%
      Average0.39%0.53%2.78%4.75%
    • Table 2. Comparison of prediction performance of different samples

      View table
      View in Article

      Table 2. Comparison of prediction performance of different samples

      SampleR2RMSEMAE
      Original samples0.88420.33680.2760
      Combined samples0.91030.29640.2406
    • Table 3. The standard deviations of hyperparameters for different optimization algorithms

      View table
      View in Article

      Table 3. The standard deviations of hyperparameters for different optimization algorithms

      Optimization algorithmStandard deviation of CStandard deviation of gamma
      PSO35.138040.02140
      SSA0.654180.00461
      NRBO0.036380.00133
    • Table 4. The evaluation metrics and convergence time of different optimization algorithms

      View table
      View in Article

      Table 4. The evaluation metrics and convergence time of different optimization algorithms

      Optimization algorithmR2RMSEMAEConvergence time/s
      MeanOptimal valueMeanOptimal valueMeanOptimal value
      PSO0.939880.941870.228740.224950.172570.158773.32894
      SSA0.937400.937580.233460.233110.191970.191265.00998
      NRBO0.962440.962480.214530.214410.139280.139276.34334
    Tools

    Get Citation

    Copy Citation Text

    Peichao ZHENG, Wei RUAN, Shubin CHEN, Haijuan LI, Yan HOU, Chenglin LI, Haonan HE, Qin YANG, Jinmei WANG, Biao LI, Lianbo GUO. COD determination method using small-sample UV-Visible absorption spectral data[J]. Infrared and Laser Engineering, 2025, 54(7): 20250065

    Download Citation

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

    Category: 光电测量

    Received: Jan. 20, 2025

    Accepted: --

    Published Online: Aug. 29, 2025

    The Author Email: Jinmei WANG (wangjm@cqupt.edu.cn)

    DOI:10.3788/IRLA20250065

    Topics