Wind machine state reliability assessment method and repair decision optimization

Abstract

The invention belongs to the field of wind machine reliability assessment and discloses a wind machine state reliability assessment method and repair decision optimization. The method comprises the following steps of (a) collecting performance indexes of a to-be-assessed wind machine at different moments, and deleting abnormal data to obtain to-be-analyzed data of a degradation stage; (b) dividinga healthy state of the to-be-assessed wind machine into four levels of normal, abnormality, degradation and fault, and selecting a Markov model as an assessment model for the reliability of the to-be-assessed wind machine; (c) performing dimensionless processing on degradation data of the wind machine, and improving a state transition probability matrix in the Markov model by adopting a dimensionless performance degradation function; and (d) determining a state probability distribution vector at an initial moment, and calculating a state probability vector and reliability at each moment, thereby realizing the assessment of the state reliability of the to-be-assessed wind machine. The method reduces the cost and is economic and efficient; and a reliability assessment result is accurate.

Description

technical field [0001] The invention belongs to the field of wind turbine reliability assessment, and more specifically relates to a method for wind turbine state reliability assessment and optimization of maintenance decisions. Background technique [0002] Reliability is a widely recognized key index in energy systems, and it plays an important role in guiding the safe and economical operation of the modern power industry. The current wind turbine reliability assessment methods mainly rely on large sample data, that is, through the statistical analysis of the fault data of multiple wind turbines in multiple wind farms, the fault time distribution law within the life cycle of wind turbines is obtained, which is used to guide The operation and maintenance of wind turbines to improve the safety and economy of wind turbine operation. [0003] China's wind turbines have only been developed on a large scale in recent years. The operating time is not long and the monitoring meth...

AI Technical Summary

Problems solved by technology

[0003] China's wind turbines have only been developed on a large scale in recent years. The operating time is not long and the monitoring methods are not perfect, resulting in a lack of wind turbine operating data, which is not enough to support the calculation of traditional reliability evaluation models based on large sample data.

Therefore, there is a serious problem of lack of reliability data for wind turbines currently in service in my country.

Moreover, due to the different meteorological resource conditions and maintenance methods of different wind farms, there are differences in the service life of wind turbines in different regions.

Therefore, there is a certain deviation between the reliability law of wind turbines obtained through large sample statistics and the actual operation of individual wind turbines.

[0004] In order to solve the problem of lack of reliability data caused by insufficient fault data of wind turbines, the present invention proposes a reliability evaluation method based on performance degradation improved Markov model, which can realize wind turbine reliability evaluation under small sample conditions

Images