U-Net-Based Contrastive Blind Denoising Method for Micro-Thrust Measurement Signal

Accurate noise suppression is vital for precise microthrust sensing measurement. Conventional methods often fail to recover both step and tendency within the signal effectively. In this research, we present an innovative U-Net-based contrastive blind denoising method that operates without needing a reference clean signal. Our method introduces contrastive representation learning combined with self-supervised blind denoising, forming a multi-target network. This multi-target network captures the decouples features of the inputs, i.e., clean signal features). Experiments validate the proposed method's superior performance in recovering both step and tendency in the signal, outperforming traditional methods.