Fault Diagnosis Method of Photovoltaic Array Based on Differential Evolutionary Random Forest Classifier

Abstract

The invention relates to a photovoltaic array fault diagnosis method based on a differential evolution random forest classifier. The method: first, collect the voltage of the photovoltaic array and the current of each photovoltaic string under various working conditions, and identify each working condition with different identifiers; secondly, use the classification misjudgment rate based on the out-of-bag data The mean size determines the number range of decision trees in the random forest model; then, the differential evolution algorithm is used to globally optimize the number range of its decision trees to obtain the optimal number of decision trees; then, the calculated optimal number of decision trees The value is brought into the random forest classifier and the samples are trained to obtain the random forest fault diagnosis training model; finally, the fault detection and classification of the photovoltaic array is performed using the training model. The method of the invention can greatly speed up the model training speed while ensuring the optimal model classification accuracy rate, thereby more quickly and accurately realizing the fault detection and classification of the photovoltaic power generation array.

Description

technical field [0001] The invention relates to a photovoltaic array fault detection and classification technology, in particular to a photovoltaic array fault diagnosis method based on a differential evolution random forest classifier. Background technique [0002] Large-scale photovoltaic power plants are an important way to utilize new energy. The core photovoltaic power generation arrays are affected by the external natural environment and self-aging problems during operation, and some failures will inevitably occur. The photovoltaic system is relatively large, and once a failure occurs, it will cause great damage to the entire photovoltaic power generation system. If these faults are not detected and eliminated in time, it will directly affect the normal operation of the photovoltaic power generation system, and even burn out the battery components and cause a fire in severe cases. Therefore, realizing the fault diagnosis of the photovoltaic system is of great signific...

AI Technical Summary

Problems solved by technology

[0005] At present, the photovoltaic array fault diagnosis method based on the differential evolution random forest classifier proposed by the present invention has not yet been seen in the published literature and patents

Images