Online classification method and system for wind turbine generator of wind power plant

Abstract

The invention relates to a wind power plant wind turbine generator online classification method and system, based on SCADA data of each wind turbine generator in a wind power plant, such as wind turbine generator power output data, wind speed data, pitch angle data and rotor speed data, a characteristic matrix capable of reflecting the operation characteristics of each wind turbine generator is established, and the characteristic matrix is subjected to classification operation to obtain a classification result; according to the wind power plant optimal scheduling method, the load instruction distribution complexity in the whole wind power plant optimal scheduling process can be greatly reduced, and the real-time performance of wind power plant optimal scheduling is improved. And the benchmark unit preferentially participates in the wind power plant scheduling task in the next scheduling period, and generates power at the maximum power when participating in the scheduling task, so that frequent starting and stopping of the unit and limited power operation are not needed, the hardware loss of the benchmark unit and the control pressure of a pitch angle control system can be reduced, and the stability margin and the service life of the wind turbine generator are improved.

Description

technical field [0001] The invention relates to the technical field of wind power grid dispatching, in particular to an online classification method and system for wind turbines in a wind farm. Background technique [0002] When the wind farm receives the load command issued by the grid dispatching center, it needs to consider which strategy to adopt to distribute the total power command of the wind farm to each wind turbine. The more traditional method is the fixed weight allocation method, that is, according to the rated capacity of each wind turbine as the weight, the total power command of the wind farm is equally divided according to the weight, and then distributed to each wind turbine. However, due to the vast area of ​​wind farms, the distribution of wind turbines in wind farms is relatively scattered. Due to the different geographical environments of each wind turbine, the influence of the wake effect, and the randomness and intermittent nature of the wind, the win...

AI Technical Summary

Problems solved by technology

The power fixed weight allocation method does not take into account the different power output characteristics between wind turbines, so it cannot get a better power command allocation result, which will also reduce the utilization rate of wind power generation

[0003] In addition, in the optimal dispatching of wind farm group power, if all the units in the field are directly involved in the optimal dispatching, the calculation complexity is large and the calculation time is long, which is not conducive to the real-time performance of the optimal dispatching of wind farms.

Secondly, when the wind turbines change their power output in each scheduling cycle, more start-stop changes and larger power-limited operating states will bring greater hardware loss and increase the pitch of the wind turbines. Angle control system controls the pressure, reducing the stability margin and service life of the wind turbine

Images