Adaptive neural inversion control method for three-phase shunt active filter
An inversion control and self-adaptive technology, applied in active power filtering, AC network to reduce harmonics/ripples, etc., can solve problems such as the inability to obtain mathematical models, achieve excellent dynamic and static characteristics, improve adaptability and Good fault tolerance and stability
Active Publication Date: 2017-02-15
NAN TONG HUAWEI POWER EQUIP CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the complexity, nonlinearity, time deformation, uncertainty and other factors in the actual system, it is impossible to obtain an accurate mathematical model, and the traditional control theory can no longer meet the requirements of industrial development, so advanced control theory has been proposed and developed
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0073] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.
[0074] Such as figure 1 As shown, the system is an adaptive neural inversion control system, and the controlled object is a three-phase parallel active power filter. Its mathematical model can be written as form. To design an inversion controller for an active power filter control system, the virtual control function is constructed first, and then the actual control law is constructed. Using the learning function of the neural network, the approximation of the unknown function f(x) in the inversion controller can be realized. At the same time, in order to ensure the global stability, a supervision term u is added to the control law s , so that the design of the adaptive neural inversion cont...
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
Login to View More Abstract
The invention discloses a method for self-adaptive neural inversion control of a three-phase parallel connection type active filter. To overcome the shortcomingsin inversion control law design, RBF neural network approximation and a self-adaptive control method are adopted, a self-adaptive neural inversion controller is designed to be used for approaching a switch function of the three-phase parallel connection type active filter, and accordingly an active filter main circuit switch is controlled to be on or off. According to the method for self-adaptive neural inversion control of the three-phase parallel connection type active filter, an inversion control method, a self-adaptive algorithm and an RBF neural network are integrated, harmonic waves in a power current can be detected and tracked from time to time, and the goal of eliminating the harmonic wave and improving electric energy quality is achieved by generating compensating currents equal in size and opposite in directions. The self-adaptive law is designed on the basis of a lyapunov function, the weight of the neural network can be adjusted on line, and a system has stability and robustness.
Description
technical field [0001] The invention relates to an adaptive neural inversion control method for a three-phase parallel active filter, belonging to the technical field of active power filter control. Background technique [0002] With the application of a large number of nonlinear loads, the harmonic content in the power grid is increasing day by day, resulting in worse and worse power quality. Harmonics can cause a series of hazards such as overheating of equipment, increased loss, and excessive current, which must be suppressed. Compared with the passive power filter, the active power filter (APF) can more effectively deal with the harmonics and power factor of the changing load. "The most effective means. [0003] The control technology of APF is one of the key technologies of APF. The control effect of APF depends to a large extent on the performance of its controller. With the development of industrial technology, the design requirements for control systems are increas...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H02J3/01
CPCY02E40/20
Inventor 王哲费峻涛
Owner NAN TONG HUAWEI POWER EQUIP CO LTD