A Novel Denoising Method for Mud Continuous-Wave Signals Based on Selective Ensemble Strategy with Particle Swarm...

During drilling operations, mud continuous-wave signals suffer severe distortion at the surface receiver due to dynamic and complex background noise. Traditional noise cancelation methods face limitations in effectiveness and generalization. To address this, this paper proposes a particle swarm optimization (PSO)-based selective ensemble filtering strategy. It adaptively selects optimal filtering algorithms matched to the target scenario and assigns their weights, enabling complementary strengths from diverse filters. Preferred filtering methods are applied in parallel, generating initial signals as candidate solutions within the reconstructed ensemble. The PSO algorithm identifies the optimal matching weights for each particle and performs the optimal selective ensemble of these candidates. This process enhances generalization capability and achieves high-precision reconstruction of the continuous-wave signal in complex drilling environments. Experimental results demonstrate that the reconstructed signal using this method exhibits superior quality metrics and greater robustness compared to any single-filter output, validating the proposed approach's effectiveness.