According to the influence of Doppler frequency shift on the detection of Physical Random Access Channel (PRACH) signals, the signal detection algorithms were were divided into medium speed, high speed, ultra-high speed modes, and they were improved respectively. In the medium speed mode, a preamble detection algorithm based on frequency offset correction was proposed. In the high speed mode, an multi-sliding window peak detection algorithm was proposed. In the ultra-high speed mode, a frequency offset compensation preamble detection algorithm based on integer subcarrier was proposed. The simulation results show that, in different scenarios, when the PRACH signals are transmitted through the Additive White Gaussian Noise (AWGN) channel, and the false alarm rate performance of the receiver is improved by at least 3.8 dB, when the PRACH signals are transmitted through the Extend Typical Urban model (ETU) channel, the false alarm rate performance is improved by at least 1 dB. Compared with the frequency domain correlation detection algorithm, the proposed algorithms can improve the probability of successful detection of preamble signals and reduce the random access delay.