Evaluation Method Of Wind Turbine Operation Performance Based On Time Dimension

In the 2020s,the design and operation life of 1.5MW and below units installed in the early onshore wind farms in China has been more than half or nearly 20 years,and the technical transformation of a large number of wind turbines has been put on the agenda.The most important problem in the technical transformation of wind turbines is to evaluate the operation performance of wind turbines,so it is very important to evaluate the operation performance of wind turbines accurately.Due to the importance of time dimension operation performance analysis and evaluation of wind turbine in the technical transformation of wind turbine,it has been paid more and more attention in the industry.In the previous literature research,scholars at home and abroad have done a lot of research on the horizontal performance evaluation of multiple wind turbines,but the vertical performance evaluation of the same wind turbine in different statistical periods based on the time dimension has not been found in the open literature.Although the horizontal evaluation and vertical evaluation of wind turbine operation performance are the same,they are also different.The main focus of longitudinal evaluation of wind turbine operation performance is to evaluate the attenuation of unit performance with the increase of unit service time.Accurate evaluation of the attenuation of wind turbines can provide support for the optimization design of wind turbine manufacturers,the operation and maintenance management of wind farms,and the technical transformation of wind turbines.Based on the above reasons,a time dimension wind turbine performance evaluation model is established.The main contents are as follows:(1)A state partition model of wind turbine operation data based on piecewise kernel density estimation is proposed.In view of the fact that the previous work of state division of wind turbine operation data is based on the statistical principle method,ignoring the control principle of different parameters such as pitch angle in different power segments of wind turbine,two-dimensional kernel density estimation is used for different power segments.In the data state division,the changes of wind speed,pitch angle and impeller speed in different power sections under normal conditions are considered to determine the operating conditions.Then the kernel density estimation is applied to determine the parameter range of each condition,so as to improve the accuracy and practicability of the data state division of wind turbine operation.(2)The operation performance evaluation index of wind turbine is improved.In the operation of wind turbine,with the extension of time,its operation performance will decline.Considering the main influencing factors of wind turbine with the increase of operation time,the evaluation index system of wind turbine operation performance in time dimension is constructed.The performance evaluation indexes of different statistical periods of wind turbines in time dimension are improved.(3)Establish a fuzzy comprehensive evaluation model for the operation efficiency of wind turbines.The relative degradation method is used to standardize the calculated value of the index system.Solve index combination weights based on coefficient of variation method and entropy weight method;establish trapezoidal and semi-trapezoidal membership functions based on relevant empirical criteria;the fuzzy comprehensive evaluation matrix and evaluation scores of wind turbine operating efficiency are obtained.