Transformation Equipment Voice Reconstruction Based on Fourier Spectrum of Power-Frequency Multiple

Abstract

The equipment voice de-noising and reconstruction algorithm is presented in this paper based on intelligent robot in transformer situation (transformer and high resistance). The method is an embodiment of information and intelligence which can be applied in voice recognition of inspection robot. Firstly, equipment voice was collected and formed a sample database. Secondly, the voice features were analyzed in sample database, and the power-frequency Fourier spectrum as the voice features was extracted in the frequency domain. Finally, Fourier spectrum of power-frequency multiple was used to construct the voice by taking advantage of the inverse Fourier transform. The experimental results show that the algorithm has stable performance, strong robustness, and can accurately reconstruct the voice, so it is benefit to the follow-up voice recognition.