Three-level inverter open-circuit fault diagnosis method based on optimized support vector machine

Abstract

The invention relates to a three-level inverter open-circuit fault diagnosis method based on an optimized support vector machine. The method comprises following steps: (1) extracting a fault characteristic, and allocating samples; (2) performing nuclear Fisher dimension reduction, and optimizing a nuclear function parameter; (3) determining a range in which a support vector is; (4) extracting a KNN reference point; (5) allocating test samples; and (6) classifying test samples. In the method, characteristics are extracted through intrinsic mode decomposition and singular value decomposition, sothat time-varying nonlinear signal characteristics can be better extracted; a support vector is extracted by using nuclear Fisher algorithm and is used as a training sample, effectively improving training speed of the vector machine; test samples nearby a classification super plane are classified by using a KNN algorithm, thereby being classified more accurately; and the SVM-KNN classifier builtbased on the nuclear Fisher algorithm can correctly classify three-level inverter open-circuit faults more accurately within shorter test time.

Description

technical field [0001] The invention relates to the technical field of photovoltaic inverter circuit fault diagnosis, in particular to a three-level inverter open-circuit fault diagnosis method based on an optimized support vector machine. Background technique [0002] In recent years, the rapid development of high-speed rail, electric vehicles, and photovoltaic power generation has stimulated the demand for high-performance power converters with low harmonics, high efficiency, small size, light weight, and high power density. Because of such advantages, the three-level inverter will replace the application of the two-level inverter in this field. However, the three-level inverter also has its own disadvantages. Compared with the two-level inverter, it uses more power tubes. As a key component of the inverter, the power tube carries large voltage, high current, high temperature, and frequent switching operations. Any failure of a power component will cause the circuit to wo...

AI Technical Summary

Problems solved by technology

Although wavelet transform has great advantages in signal feature extraction, it is necessary to try to use different wavelet basis functions to achieve the optimal result in actual use; traditional support vector machine is used for fault feature classification, although it can Optimizing parameters to improve classification accuracy, but cannot solve its own inherent defects: 1. The number of training samples determines the training time, and the actual valuable sample points are only those few support vectors; 2. The classification of training points near the hyperplane The classification accuracy rate is not high, and the classification accuracy cannot be fundamentally improved, which leads to long training time of the classifier and difficulty in improving the test accuracy

Images