Cage type asynchronous motor stator and rotor fault joint diagnosis method based on stack type self-encoding and light gradient elevator algorithm
A stack-type self-encoding, asynchronous motor technology, applied in the field of detection, can solve problems such as performance to be improved, and achieve the effect of reducing the amount of calculation
Image
Examples
Embodiment Construction
[0030] The present invention proposes a joint and simultaneous diagnosis method of cage-type asynchronous motor stator winding inter-turn short circuit and rotor broken bar fault and its severity based on stacked self-encoder and light gradient hoist algorithm. The diagnostic accuracy of the method is Up to 99.83%. Obviously, the basis of the present invention lies in the acquisition of a large amount of sample data, the construction of a stacked autoencoder and a light gradient booster, which will be described in detail below.
[0031] figure 1 For the experimental wiring diagram, according to the system, a large number of experiments are carried out on the motor, so as to obtain sufficient samples. Among them, the data acquisition system collects the instantaneous three-phase current signal of the stator through the current converter and the voltage converter sA i sB i sC , stator three-phase voltage instantaneous signal u sA , u sB , u sC . This experimental work is...
PUM
Login to View More Abstract
Description
Claims
Application Information
- IPC
- G01R31/34; G06N3/04; G06N3/08; G06N5/00; G06F17/11; G06F17/15
- CPC
- G01R31/343; G01R31/346; G06N3/084; G06F17/11; G06F17/15; G06N5/01; G06N3/045
- Inventors
- 许伯强; 何俊驰



