Method for fault diagnosis of three-phase full-bridge rectifier circuit thyristor

Abstract

The invention discloses a method for fault diagnosis of a three-phase full-bridge rectifier circuit thyristor. The method comprises steps of: 1, constructing a thyristor fault sample set: 101, determining the quantity D of thyristor fault state types in a three-phase full-bridge rectifier circuit; 102, acquiring each type of thyristor fault state data and expressing a matrix space; 103, constructing a matrix space sample; 2, classifying and positioning a thyristor fault: 201, extracting a fault vector beta; 202, solving the distance d(beta, w) from the fault vector beta to the matrix space sample Si; 203, completing the calculation process of the value of d(beta, w); and 3, synchronously outputting a thyristor fault processing result. The method is novel in design; the fault is classified and positioned by adopting a method of vector-to-subspace distance, so that the method is high in precision, small in calculation amount, intuitive, quick and effective, overcomes the defect of weak normalization capability of a neural network detection method in the prior art, and eliminates local minimum points.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis, and in particular relates to a method for fault diagnosis of a thyristor of a three-phase full-bridge rectifier circuit. Background technique [0002] Once the rectification device fails, it will cause damage to electronic products and traffic paralysis, and it will cause major accidents and threaten the safety of people's lives and properties. Therefore, fault detection for power electronic devices is extremely important. A large number of studies have shown that the performance degradation of most power electronic circuits is caused by the failure of components in the circuit, and the performance and indicators of components directly affect the performance of the entire circuit. Under typical operating conditions, the IGBT failure rate is 31%, the inductor device failure rate is 6%, and the diode failure rate is 3%. Therefore, in order to realize the fault prediction of power electron...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method for diagnosing thyristor faults in three-phase full-bridge rectifier circuits in view of the deficiencies in the prior art above. Classification and positioning, high precision, small amount of calculation and intuitive, fast and effective, overcomes the defect of weak normalization ability of neural network detection methods, and does not fall into local minimum points, which is convenient for popularization and use

Images