Fault diagnosis of elevator braking system based on wavelet packet algorithm and fuzzy neural network

Aiming at the fault features of the elevator braking system, the basic characteristics of three faults types are analysised. By detecting the brake shoe gap-time signals in the process of braking, the fault signals are decomposed using wavelet packet, and the signal characteristics of 8 frequency components from the low-frequency to high-frequency in the third layer are extracted. Then taking advantages of B-spline and fuzzy neural networks to set up the elevator braking system fault diagnosis model, the 8 obtained eigenvalue are used as the model inputs for fault diagnosis. The result shows that this method is effectual and applied.