Abstract: A identification method based on fractal theory was proposed.First, the simulation model of mid-latency auditory evoked potentials (MLAEP) signal is gave out and the simulation MLAEP signal which is according with reality during anesthesia monitoring is built up.Then, the noise in evoked potential signal is denoised through the wavelet transform method and the correlation dimensions are computed.Finally, according to the correlation dimension, the signal type is identified for evoked potential signal during anesthesia monitoring.The experimental simulation results show that the proposed method has higher identification rate for MLAEP during anesthesia states.