Decision tree model-based photovoltaic assembly fault diagnosis method

Abstract

The present invention belongs to the photovoltaic power generation technical field and provides a decision tree model-based photovoltaic assembly fault diagnosis method. The method includes the following steps that: photovoltaic assembly data are acquired, and data processing is carried out; obtained data are introduced into a decision tree-based photovoltaic assembly fault diagnosis model, the modeling steps of the model mainly comprise selection and processing of training and test sample data, tree establishment and tree pruning, decision tree model establishment and decision tree accuracy verification; and the fault type of a photovoltaic assembly is judged through a decision module. With the method of the invention adopted, manpower and resource waste caused by fault judgment errors can be avoided, the accuracy and reliability of fault judgment are improved, serious consequences to the photovoltaic assembly, caused by a fault, can be avoided, and the service life of the photovoltaic assembly can be prolonged.

Description

technical field [0001] The invention relates to a method for diagnosing faults of photovoltaic components, in particular to a method for diagnosing faults of abnormal aging and partial shadows of photovoltaic components based on a decision tree model. Background technique [0002] Due to the inexhaustible and non-polluting characteristics of solar energy, the application of photovoltaic power generation presents a trend of rapid development. The monitoring and maintenance of system operating status is crucial to the safe operation of photovoltaic power generation systems. Timely and reliable fault warnings can avoid major accidents such as fires and equipment damage, and improve the operating life and economic benefits of photovoltaic power plants. At present, most photovoltaic power plants adopt manual inspection and maintenance, and check the electrical parameters of photovoltaic modules block by block to judge whether they are normal. However, photovoltaic modules are in...

AI Technical Summary

Problems solved by technology

The above-mentioned BP network needs to be trained offline in advance with training samples, and the weight adjustment is multiple feedback, the convergence speed is slow and it is easy to fall into the local minimum point, these shortcomings limit its full advantage in the field of fault diagnosis; the fuzzy control method The logic system lacks self-learning ability, and this ability is necessary in some high-demand real-time fault diagnosis situations; infrared image analysis method and multi-sensor de

Images