• Laser & Optoelectronics Progress
  • Vol. 55, Issue 11, 112001 (2018)
Ping Song** and Yian Liu*
Author Affiliations
  • College of IOT Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China
  • show less
    DOI: 10.3788/LOP55.112001 Cite this Article Set citation alerts
    Ping Song, Yian Liu. Multi-Static Sky-Wave Over-the-Horizon Radar Location Model Based on Improved Dragonfly Algorithm[J]. Laser & Optoelectronics Progress, 2018, 55(11): 112001 Copy Citation Text show less
    Multi-static location model
    Fig. 1. Multi-static location model
    Target location model implementation flow chart of multi-static sky-wave over-the-horizon radar based on LACMODA-ELM
    Fig. 2. Target location model implementation flow chart of multi-static sky-wave over-the-horizon radar based on LACMODA-ELM
    Influence of the number of hidden layer nodes on the locating error of ELM
    Fig. 3. Influence of the number of hidden layer nodes on the locating error of ELM
    Prediction error of neural network. (a) Prediction error of three neural networks; (b) prediction error from ELM neural network optimized by different algorithms
    Fig. 4. Prediction error of neural network. (a) Prediction error of three neural networks; (b) prediction error from ELM neural network optimized by different algorithms
    Longitude and latitude predicted by ELM optimized by different algorithms. (a) Longitude prediction; (b) latitude prediction
    Fig. 5. Longitude and latitude predicted by ELM optimized by different algorithms. (a) Longitude prediction; (b) latitude prediction
    Location predicted by ELM optimized by different algorithms
    Fig. 6. Location predicted by ELM optimized by different algorithms
    No.Function nameDimensionSearch scopeOptimal valuePeak
    f1Step10[-100,100]0Unimodal
    f2Quartic10[-1.28,1.28]0Unimodal
    f3Rastrigin10[-5.12,5.12]0Multimodal
    f4Ackley10[-32,32]0Multimodal
    Table 1. Benchmark function
    FunctionAlgorithmOptimal valueWorst valueAverage valueStandard deviation
    f1PSO1.01151.2092×1044.1767×1034.5314×103
    DA0.03091.4434×104347.48951.6229×103
    LACMODA2.0781×10-260.11070.00640.0237
    f2PSO0.00841.11670.02290.0856
    DA0.03808.11440.27461.2505
    LACMODA1.1679×10-40.01820.00150.0022
    f3PSO19.8995107.252823.650113.8974
    DA7.222191.283514.323718.0229
    LACMODA03.18570.05990.2826
    f4PSO4.990219.45907.47464.6434
    DA2.579919.77793.96963.7016
    LACMODA0.00271.20110.06630.1356
    Table 2. Simulation results of improved DA
    NeuralNetworkLongitudeAE /(°)LatitudeAE /(°)MAPE /(°)Distanceerror /km
    BP0.7880.4240.22499.91
    RBF1.4690.3640.271167.77
    ELM0.1760.1070.04022.53
    Table 3. Error comparison based on different neural network prediction methods
    Optimization algorithmLongitude AE /(°)Latitude AE /(°)MAPE /(°)Distance error /km
    PSO-ELM0.1340.0310.02315.20
    DA-ELM0.1250.0210.01813.90
    LACMODA-ELM0.0180.0170.0082.71
    Table 4. Error comparison of ELM prediction methods based on different optimization algorithms
    Positioning methodDistance error /km
    Ray tracing technology17.2
    Hybrid sky-surfacewave propagation mode9
    Coordinate registration andmultipath data correction2.75
    LACMODA-ELMpositioning model2.71
    Table 5. Comparison of errors in different positioning methods
    Ping Song, Yian Liu. Multi-Static Sky-Wave Over-the-Horizon Radar Location Model Based on Improved Dragonfly Algorithm[J]. Laser & Optoelectronics Progress, 2018, 55(11): 112001
    Download Citation