Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Global Sliding Mode Control Method for Active Power Filters Based on Double Hidden Layer Recurrent Neural Networks

A regression neural network, power filter technology, applied in the field of global sliding mode control of active power filter based on double hidden layer regression neural network, can solve the problems of low robustness, system instability, inconvenience, etc. Training speed, powerful fitting and expression capabilities, and the effect of accelerating system response

Active Publication Date: 2022-04-01
HOHAI UNIV CHANGZHOU
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the robustness of adaptive control to external disturbances is very low, and it is easy to make the system unstable.
[0004] This shows that above-mentioned existing active power filter obviously still has inconvenience and defective in use, and urgently needs to be further improved
In order to solve the problems existing in the use of existing active power filters, relevant manufacturers have tried their best to find a solution, but no suitable design has been developed for a long time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Global Sliding Mode Control Method for Active Power Filters Based on Double Hidden Layer Recurrent Neural Networks
  • A Global Sliding Mode Control Method for Active Power Filters Based on Double Hidden Layer Recurrent Neural Networks
  • A Global Sliding Mode Control Method for Active Power Filters Based on Double Hidden Layer Recurrent Neural Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to more clearly illustrate the technical solutions of the present invention, but cannot limit the protection scope of the present invention with this.

[0091] Such as figure 1 is the basic circuit topology diagram of the three-phase three-wire parallel voltage-type active power filter, v s1 ,v s2 ,v s3 is the grid voltage, i s1 ,i s2 ,i s3 is the supply current, i L1 ,i L2 ,i L3 is the load current, v 1 ,v 2 ,v 3 is the voltage at the common connection point, i 1 ,i 2 ,i 3 is the filter output compensation current, C is the DC side capacitance, v dc is the DC side capacitor voltage, i dc is the DC side capacitor voltage, L c is the AC side inductance, R c is the equivalent resistance.

[0092] The values ​​of the center vector and the base width in the two hidden layers of the fully-adjusted regression neural netwo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a global sliding mode control method of an active power filter based on a double-hidden layer regression neural network, which is characterized in that it comprises the following steps: 1) establishing a mathematical model of an active power filter; The global sliding mode controller of the active power filter with the hidden layer regression neural network is designed, and the control law is used as the control input of the active power filter; 3) Based on the Lyapunov function theory, the adaptive law is designed, and the dual-based Stability of Global Sliding Mode Controllers for Active Power Filters with Hidden Layer Recurrent Neural Networks. Advantages: improve the approximation accuracy and generalization ability of the network, reduce the number of network parameters and weights, and speed up network training; can store more information and have better approximation effects; can improve the existence of active power filter systems Compensation current tracking accuracy and system robustness in case of parameter perturbation and external disturbance.

Description

technical field [0001] The invention relates to a control method of an active power filter, in particular to a global sliding mode control method of an active power filter based on a double-hidden layer regression neural network. Background technique [0002] With the popularization and application of modern power electronic technology, there are more and more various power electronic devices, harmonics, reactive power, unbalance, etc. have had a great impact on the power system, seriously affecting the quality of power supply, reducing the power generation The working performance and service life of equipment and electrical equipment, and even endanger the safety of the power system. Currently, external filters are mainly used for treatment. Filters are divided into passive filters and active filters. Since the passive filter can only compensate specific harmonics and other defects, the current research on the control of electric energy problems mainly focuses on the activ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 储云迪费峻涛王欢冯治琳
Owner HOHAI UNIV CHANGZHOU
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products