Self-feedback recurrent fuzzy neural network prediction control method of active filter

Abstract

The invention discloses a self-feedback recurrent fuzzy neural network prediction control method of an active power filter. The method comprises the following steps: S1, establishing a prediction control mathematical model of the active power filter; S2, constructing a self-feedback recurrent fuzzy neural network prediction model according to the prediction control mathematical model established in the step S1; S3, designing a neural network prediction model parameter learning strategy, and calculating to obtain the adaptive rate of the neural network; and S4, designing a self-feedback recursive fuzzy neural network model prediction control rate according to the neural network prediction model obtained in the step S3, and optimizing the controller in real time. According to the method, a data-driven online optimization method is adopted, rapid and high-precision compensation can be carried out on the harmonic current without depending on an accurate model of the system, the anti-interference capability is high, the robustness is good, and good steady-state and dynamic performance is achieved.

Description

technical field [0001] The invention relates to a self-feedback recursive fuzzy neural network predictive control method of an active filter, and belongs to the technical field of intelligent control. Background technique [0002] With the wide application of power electronic equipment, the nonlinear load in the power system is increasing, and the harmonic pollution in the power grid is also becoming more and more serious. Harmonics can cause serious harm to the safety of the power system, mainly manifested in increasing the additional harmonic loss in the power system, affecting the normal operation of various electrical equipment, causing malfunctions in relay protection and automatic devices, and affecting adjacent communication systems. cause significant interference. [0003] As the most effective means of harmonic control, active power filter has received extensive attention and attention. However, as society's requirements for power quality are getting higher and hi...

AI Technical Summary

Problems solved by technology

However, as society's requirements for power quality are getting higher and higher, and the country's harmonic restrictions on power grids are becoming more and more stringent, conventional methods such as hysteresis control and PID control are difficult to meet the requirements, and intelligent control methods are applied to active filtering has become a current research hotspot

However, the current control method still has problems such as low compensation accuracy, weak anti-interference ability, and dependence on the precise model of the system.

Images