引力参考传感器耦合噪声的CNN-BiLSTM逐层自适应剥离OA

This study addresses the difficulty of interpreting and separating multi-source coupling noise in gravitational reference sensors(GRSs)for spaceborne gravitational-wave detection.A unified acceleration-noise spectrum model is established for Brownian noise,thermal-field coupling,magnetic noise,electrostatic noise,drive-voltage noise,and residual low-frequency noise,with key parameters calibrated against LISA Pathfinder measurements.CNN layers are used to extract local transient features,BiLSTM layers are used to capture long-range temporal dependence,and adaptive spectral subtraction is then applied sequentially by physical noise category.At an input SNR of 10.2 dB,the proposed method achieves a recovery fidelity of 0.969 4 and a waveform overlap of 0.969 5,outperforming matched filtering,pure CNN,and pure BiLSTM baselines.Across an SNR range from −15 dB to+25 dB,the method shows a slower performance degrada-tion in the negative-SNR regime.Combining physics-guided noise classification with CNN-BiLSTM tempor-al modeling improves signal recovery under complex GRS noise backgrounds and provides a useful refer-ence for noise budgeting,simulation pipelines,and onboard denoising algorithms in spaceborne gravitational-wave missions.