An early fault detection method of steel cord conveyor belt

In view of problem that using traditional wavelet transform to analyze singularity of metal magnetic memory signal easily suffered from noise interference, an early fault detection model combining empirical mode decomposition with wavelet transform was proposed. Firstly, metal magnetic memory signal of steel cord conveyor belt is decomposed into intrinsic mode function components through empirical mode decomposition, then singularity characteristic of the signal is extracted by use of wavelet transform modulus maxima method. The experimental results show that the model can reflect local characteristic of the signal with stronger anti-interference ability, and determine abnormal stress concentration zone of steel cord conveyor belt effectively, which provides basis for early fault diagnosis.