PID parameter setting system of digital power supply based on machine learning and control method

A technology of machine learning and digital power supply, applied in the direction of electric controllers, controllers with specific characteristics, control/regulation systems, etc., can solve time-consuming and labor-intensive problems, power system is difficult to work stably, and PID parameters are not ideal values and other issues to achieve the effect of ensuring accuracy, saving time and energy, and simple operation
CN113285595APending Publication Date: 2021-08-20AMICRO SEMICON CORP
7 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
AMICRO SEMICON CORP
Publication Date
2021-08-20

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a PID parameter setting system of a digital power supply based on machine learning and a control method. The system comprises a machine learning module, a digital controller module and a power supply circuit module, wherein the machine learning unit is used for adjusting PID parameters of the digital controller module according to voltage difference change information and adjustment records sent by the digital controller module; the load disturbance module is used for generating a disturbance signal so as to enable the voltage output by the power supply circuit module to be changed; the digital controller module is used for outputting a corresponding pulse signal according to a voltage difference value between the voltage output by the power supply circuit module and the reference voltage of the digital controller module and according to the adjusted PID parameters; and the power supply circuit module outputs corresponding voltage according to pulse signals sent by the digital controller module. The system can quickly and accurately set PID parameters according to different application requirements, so that the digital power supply system always operates in the optimal state.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of digital power supply controllers, in particular to a machine learning-based PID parameter setting system and control method for digital power supplies. Background technique

[0002] Digital power supply refers to the external characteristics of switching power supply. Using DSP (digital signal processor) or MCU (microcontroller) to take the digital power driver as the control object can realize functions such as control, management, and monitoring of power supply. Digital power supply has the advantages of high integration, small size, strong anti-interference ability, strong stability and reliability, flexible control mode and easy intelligence, etc. It is an important development direction in the field of power supply. The digital controller is the core module of the digital power supply, which is responsible for generating the control signals of the switching power supply. Its performance directly affe...

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