Wind power generation system risk assessment method considering multi-source factors

Abstract

A wind power generation system dynamic risk prediction method considering multi-source factors comprises the steps that main factors influencing normal operation of a wind power generation system are analyzed, and a wind power generation system risk assessment system is constructed; establishing a wind power generation system risk assessment model based on the Bayesian network; collecting fault information data of the wind power plant; the fault information data is randomly divided into a training set and a test set, the training set is used for model training, and after training is completed, the test set is used for testing the trained risk assessment model; and performing quantitative scoring on the harmfulness of each fault by using an expert scoring method, and calculating risk grade score values and performing grade division in combination with a model prediction result. A risk matrix graph is drawn according to the risk grade score, risk severity possibly faced by each system is visually reflected, and operation and maintenance personnel are assisted in making decisions such as overhaul and maintenance. According to the method, various risks in the fan operation process can be reflected in real time, pre-evaluation is achieved, and the influence caused by faults is reduced.

Description

technical field [0001] The invention relates to the field of wind power generation, in particular to a dynamic risk assessment method for a wind power generation system based on a Bayesian network taking into account multi-source factors, which is used for pre-assessment of the abnormal operation state of the wind power generation system under complex conditions. Background technique [0002] At present, the huge increase in the proportion of clean energy will lead to the use of larger-scale wind turbine equipment. The uncertainty and regulation needs of wind power generation systems continue to increase, and the challenges to stable operation are even more severe. However, the control method of the wind power generation system in the prior art is still mainly in the passive control stage, and it is impossible to pre-warn the risks faced by the power grid in advance, and the best pre-prevention time is missed. Therefore, completing the transition from post-diagnosis to pre-c...

AI Technical Summary

Problems solved by technology

However, it is still possible to respond after the failure occurs, which cannot prevent it from happening, and cannot better eliminate the impact of abnormal operating conditions.

In addition, the level of wind power generation in my country is still in the preliminary stage, there are few fault samples, and the structure of the wind turbine is complex, which makes it difficult to model the system

Images