A Neural Network Guaranteed Performance Virtual Synchronous Control Method for Doubly-fed Wind Turbines

Abstract

The invention provides a neural network guaranteed cost virtual synchronous control method for a DFIG (Doubly-Fed Induction Generator). A controller adopts a cascade structure; a virtual synchronous controller is used as an outer ring; the neural network guaranteed cost virtual synchronous control method comprises virtual synchronous control of an active loop and PI control of a reactive / voltage loop; outputs of the active loop is a frequency and a phase angle of a voltage; an output of the reactive loop is an amplitude of the voltage; when the voltage-current cascade structure is adopted, theoutputs of two loops are correspondingly regulated into a frequency and a phase angle of a rotor exciting current reference value and an amplitude of the rotor exciting current reference value; guaranteed cost control as an inner ring gives out control inputs, and a neural network adaptive law in the guaranteed cost control takes charge of responding to unknown DFIG parameters; and the technicalproblems that a control effect of the guaranteed cost control can be degraded and the like are solved.

Description

technical field [0001] The invention belongs to the technical field of wind power generation, and in particular relates to a neural network performance-guaranteed virtual synchronization control method for a doubly-fed wind turbine. Background technique [0002] With the rapid development of the economy, the global energy demand is increasing day by day, and a large number of wind power, photovoltaic and other renewable energy units will be connected to the stable operation of the power grid. At present, a large number of wind turbines use doubly-fed induction asynchronous motors (DFIG), which adopt variable-speed constant-frequency vector control, and the terminal frequency passively follows the grid frequency. In this way, the wind turbine cannot show any inertia at the grid end and cannot provide frequency support for the grid. When wind power penetration is high, the frequency stability of the grid will be compromised. [0003] In order to endow renewable energy units ...

AI Technical Summary

Problems solved by technology

However, the design of traditional guaranteed energy controllers requires precise values ​​of system parameters

In practice, the precise parameters of large-scale DFIG wind turbines are usually impossible to measure, and will be affected by environmental factors such as temperature and humidity to produce offsets

In such a scenario, the control effect of guaranteed performance control will be degraded

Images