Fault diagnosis method for PWM inverter of motor drive system

Abstract

The invention discloses a fault diagnosis method for a PWM inverter of a motor drive system. The fault diagnosis method is characterized in that an inverter fault diagnosis model based on both wavelet packet decomposition and an RBF neural network is designed, wavelet packet transformation is utilized to extract a feature vector of a fault signal of the inverter, and the feature vector is taken as the input quantity of the RBF neutral network; a wolf pack-simulated annealing algorithm is adopted to optimize structural parameters of the RBF neutral network; and 22 groups of learning samples and 6 groups of test samples are utilized to train and examine the RBF neutral network. Simulation experiment analysis shows that when the fault diagnosis method is used for an open-circuit fault of the PWM inverter of a three-phase motor drive system, the fault position of an inverter TGBT power tube can be accurately positioned, fault diagnosis is quick, accurate and efficient, and the fault diagnosis method contributes to improving the running reliability of the motor drive system.

Description

Fault Diagnosis Method of PWM Inverter in Motor Drive System technical field The invention relates to the technical field of inverter fault diagnosis for motor drive systems, in particular to a PWM three-phase inverter fault detection method based on wavelet packet transform and wolf pack-simulated annealing algorithm to optimize radial basis function (RBF) neural network. Background technique At present, motor drive systems are more and more widely used in the fields of industry, agriculture, transportation, national defense, aerospace and other fields. A motor drive system usually consists of a motor, an inverter, a sensor, and a controller, while a three-phase motor drive system is generally powered by a voltage source pulse width modulation (referred to as PWM) inverter. The PWM inverter is a kind of power semiconductor circuit. Because the main circuit structure is relatively simple and the control is relatively flexible, it has many applications and uses. The PWM in...

AI Technical Summary

Problems solved by technology

The learning algorithms adopted by the above neural network fault diagnosis model are BP algorithm, ant colony algorithm, etc. These algorithms mainly have defects such as slow convergence speed, long calculation time, low search efficiency, and easy to fall into local optimum, which greatly affects the inverter. Fault diagnosis speed and accuracy

Images