OFDM receiver signal compensation method
By combining frequency-domain complex-valued neural networks and time-domain causal convolutional networks, the coupling problem of nonlinear distortion and phase noise in low-Earth orbit satellite communication is solved, thereby improving signal quality and system performance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING UNIV OF POSTS & TELECOMM
- Filing Date
- 2026-03-16
- Publication Date
- 2026-06-02
AI Technical Summary
In low-Earth orbit satellite communications, the nonlinear distortion and phase noise of broadband OFDM signals cause signal quality degradation, which existing processing architectures cannot effectively address in combination, thus affecting the bit error rate performance of the communication link.
A complex-valued neural network is used for feature enhancement in the frequency domain, and a causal temporal convolutional network is combined with residual compensation in the time domain to construct an end-to-end signal compensation method, which realizes the joint processing of power amplifier nonlinearity and phase noise.
It effectively suppresses the coupling error propagation of nonlinear interference and phase noise, improves the signal quality of the OFDM receiver, and enhances the overall system performance.
Smart Images

Figure CN122137709A_ABST