Early fault detection method for variable-speed elevator

The invention discloses an early fault detection method for a variable-speed elevator. The method comprises steps of estimating the instantaneous rotating speed of the variable-speed elevator by usinga CPP method; performing equal-angle sampling on the vibration signal; eliminating the influence of the speed on a fault-related vibration signal; solving an optimal model parameter; extracting weakfault impact characteristics from vibration signals in a self-adaptive mode. The problem that the fault impact characteristics are not obvious due to improper parameter setting is avoided, successfulapplication of DCNN and deep residual learning in fault diagnosis is considered, residual connection is fused into the DCNN, and the fault classification performance of a DCNN model is improved. Extracting time domain and frequency domain features from the filtering signals respectively; instantaneous frequency and amplitude characteristics and a Hilbert spectrum of a signal envelope are extractedon the basis of a Teager op