Decision tree svm fault diagnosis method for photovoltaic diode clamped three-level inverter

Abstract

The invention discloses a decision tree SVM fault diagnosis method for a photovoltaic diode-clamped three-level inverter. Aiming at the fault diagnosis problem of a three-level inverter in a photovoltaic microgrid, taking the inverter state as an example, first analyze The operating conditions of the main circuit of the inverter are classified into faults, and then the voltages of the middle, upper and lower bridge arms are used as the measurement signals, and the characteristic signals are extracted by using the wavelet multi-scale decomposition method, and then the decision tree SVM is generated by using the particle swarm clustering algorithm The classification model finally realizes the multi-mode fault diagnosis of the photovoltaic diode-clamped three-level inverter. Its advantages are: the algorithm can clearly distinguish each fault state of the photovoltaic diode clamped three-level inverter, uses fewer classification models to complete the fault diagnosis task, and has high diagnostic accuracy and strong anti-interference ability.

Description

technical field [0001] The invention relates to the field of fault diagnosis of power electronic devices, in particular to a decision tree SVM fault diagnosis method for a photovoltaic diode clamp type three-level inverter. Background technique [0002] The global energy crisis and environmental crisis have prompted people to seek cleaner and greener new energy sources. Among clean energy sources, solar energy has attracted widespread attention due to its advantages of non-pollution, sustainability, universality, flexibility and reliability. As more and more photovoltaic systems are integrated into the power grid, photovoltaic inverters, as the core components of photovoltaic systems, are related to the safe, stable and efficient operation of the entire system. Compared with the traditional two-level inverter, the three-level inverter has been widely used in photovoltaic power generation systems due to its advantages of series voltage equalization of switching devices, small...

AI Technical Summary

Problems solved by technology

However, the three-level inverter increases the number of switching devices, and the reliability of the circuit is correspondingly reduced. The failure of any one device may lead to abnormal operation of the circuit, and even lead to secondary failures, resulting in huge economic losses.

[0003] The problems of fault diagnosis of photovoltaic three-level inverters are mainly in three aspects: First, in terms of circuit fault mode, only the fault of a single device open circuit is considered. There are still few studies in this area, and the analysis of the problem is not comprehensive enough, and the algorithm structure of the existing fault diagnosis method for two switching devices being open at the same time is relatively complicated; second, the detection signals are mostly output voltage and output current, because there is For inductive loads, the current changes slowly, which often increases the fault diagnosis time; thirdly, in terms of diagnostic algorithms, intelligent diagnostic algorithms are gradually applied to the field of inverter fault diagnosis, such as artificial neural networks, support vector machines, extreme learning machines, etc.

Among them, there are many applications of neural networks, but there are many defects in neural networks: more parameters need to be set, slow convergence speed, easy to fall into local optimum, etc., which seriously hinder the application of neural networks

[0004] There are many switching devices in the photovoltaic three-level inverter, and there are various types of fault problems. At the same time, in order to meet the real-time requirements of the system, the traditional method can no longer meet the actual needs.

Images