Abstract:Through the acquisition, processing and characteristic analysis of voiceprint signal of large power transformer (reactor), this paper proposes a detection and recognition algorithm model and system of transformer working condition based on voiceprint recognition technology, which can judge and detect the working state of transformer. Firstly, 73 groups of transformer audio including 1800 minutes are collected by voice acquisition sensor. And then the noise of the collected transformer voiceprint is processed by segmenting, framing and windowing pretreatment methods. Secondly, the features of transformer voiceprint are extracted and effectively fused by using energy feature, frequency feature, Mel frequency cepstrum coefficient and frequency compression method. Finally, in order to solve the problem of additive superposition of sound from stable working condition and unstable instantaneous noise of transformer, this paper proposes a separation method of voice print superposition based on cosine similarity algorithm, and establishes transformer working condition detection and verification analysis system. |