PID self-tuning method based on deep learning and LOGFA

A deep learning and self-tuning technology, applied in the field of PID self-tuning based on deep learning and LOGFA, can solve problems such as complex system identification process, many control parameters, and unsatisfactory results

Inactive Publication Date: 2019-08-02
XIANGTAN UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this kind of tuning method has certain shortcomings, such as high dependence on the mathematical model of the controlled object, many control parameters, or complex identification process and difficult calculation of the system, and the effect is not satisfactory.

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
  • PID self-tuning method based on deep learning and LOGFA
  • PID self-tuning method based on deep learning and LOGFA
  • PID self-tuning method based on deep learning and LOGFA

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be described in detail below in conjunction with accompanying drawings and utilizing various technologies.

[0042] Step 1: Build the mathematical model of the asynchronous motor speed control system.

[0043] In the asynchronous motor speed control system, it is very difficult to analyze its mathematical model, because the real system is dynamically transformed and is a high-order multivariable nonlinear system. Therefore, in order to reduce the difficulty of our analysis, the following processing is generally done: regardless of the core loss of the motor and the influence of magnetic saturation, regardless of the interference of external conditions (such as temperature) on the motor parameters, assuming a three-phase The stator windings of the motor are symmetrical to each other, and its magnetomotive force and flux conform to a sinusoidal distribution.

[0044] After processing, the asynchronous motor model is transformed into a DC motor ...

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 provides a PID self-tuning method based on deep learning and LOGFA. The method comprises the following steps that firstly, the principle of a LOGDA algorithm is simply introduced, the DBN is combined with the LOGFA, a LOGFA-DBN tuning algorithm is provided, the LOGFA-DBN tuning algorithm can achieve parameter tuning offline operation, the algorithm is not limited by a controlled object, and parameter tuning speed is accelerated. The asynchronous motor is used as a simulation model to carry out a simulation experiment, and experimental results show that compared with a genetic algorithm and an FA algorithm, the tuning speed of the algorithm is faster and more stable. According to the invention, the problem that the PID is difficult to tune is solved.

Description

technical field [0001] The invention relates to PID parameter tuning. When the dynamic environment changes, the characteristic parameters of the online controller are adapted to the change, especially a PID self-tuning method based on deep learning and LOGFA. This algorithm can adjust parameters offline Guarantee the set speed under the premise. Background technique [0002] In modern industrial control, the earliest control method is the PID control method. With its simple operation, easy implementation, easy understanding and good control effect, the PID control method has become the mainstream control method in the industrial field. The parameters of the controller determine the setting and running state of the system, but the acquisition of the optimal PID parameters has always been an urgent problem in industrial control. [0003] However, in actual application scenarios, most of the time, the optimal parameters of PID are obtained through manual parameter adjustment. ...

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 Applications(China)
IPC IPC(8): G05B11/42
CPCG05B11/42
Inventor 易灵芝徐秀肖伟红赵健刘月杨先勇
Owner XIANGTAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products