Sea Clutter Suppression Method of HFSWR Based on RBF Neural Network Model Optimized by Improved GWO Algorithm.

Area of Science:

• Radar Systems Engineering
• Signal Processing
• Artificial Intelligence

Background:

• High-frequency surface-wave radar (HFSWR) detection performance is critically dependent on effective sea clutter suppression.
• Existing optimization algorithms like the standard gray wolf optimization (GWO) suffer from slow convergence and local optima.
• Radial basis function neural networks (RBFNN) offer potential for sea clutter prediction but require robust optimization.

Purpose of the Study:

• To propose an improved gray wolf optimization (IGWO) algorithm for optimizing RBFNN.
• To develop a novel sea clutter prediction and suppression model for HFSWR.
• To enhance the detection performance of HFSWR by effectively mitigating sea clutter interference.

Main Methods:

• An adaptive division of labor search strategy was introduced to overcome GWO's limitations, enhancing both exploration and exploitation.
• The IGWO algorithm was employed to optimize the parameters of a radial basis function neural network (RBFNN).
• A sea clutter prediction model, termed IGWO-RBFNN, was established and validated through experimental analysis.

Main Results:

• The IGWO algorithm demonstrated significantly improved convergence speed and optimization accuracy compared to standard GWO.
• The IGWO-RBFNN model achieved higher prediction accuracy for sea clutter than models optimized with LDWPSO and GWO.
• Experimental results confirmed a superior sea clutter suppression effect for HFSWR using the proposed IGWO-RBFNN method.

Conclusions:

• The proposed IGWO algorithm effectively addresses the shortcomings of traditional GWO, offering enhanced optimization capabilities.
• The IGWO-RBFNN model provides a more accurate and effective approach to sea clutter prediction and suppression in HFSWR.
• This advancement holds significant promise for improving the overall detection performance and reliability of HFSWR systems.