Indirect decoupling method of multi variable system based on nerve network reverse idontification and reverso control

Abstract

An indirect decouple method of multivariable system based on neural network inverse identification and inverse control includes containing couple influence by the other two phase control signal to this phase current in each inverse phase identification, series ¿C connecting each phase neural network model as inverse controller model to each phase electrode for forming three decoupled independent pseudo linear objects, designing and debugging out three independent linear regulators based on three said objects for forming three independent regulation loops to realize accurate control on three phase coupled system.

Description

technical field [0001] The invention belongs to the technical field of complex system intelligent modeling and decoupling control, and in particular relates to an indirect decoupling method of a multivariable system based on neural network inverse identification and inverse control. Background technique [0002] The control of multi-variable complex process control systems faces two major difficulties: one is that it is difficult to use traditional theories and methods to model the system in real time and online because of the complexity and serious uncertainty of the system; Deterministic, it is difficult to decouple it with decoupling theory based on analytical models. Although the research papers of many scholars have conducted in-depth and systematic research and discussion on the decoupling control of multivariable process control systems, these theories are all based on a premise: that is, it is necessary to write an accurate analytical model of the multivariable proce...

AI Technical Summary

Problems solved by technology

[0002] The control of multi-variable complex process control systems faces two major difficulties: one is that it is difficult to use traditional theories and methods to model the system in real time and online because of the complexity and serious uncertainty of the system; Deterministic, it is difficult to decouple it with analytical model-based decoupling theory

Although the research papers of many scholars have conducted in-depth and systematic research and discussion on the decoupling control of multivariable process control systems, these theories are all based on a premise: that is, it is necessary to write an accurate analytical model of the multivariable process system, and this It is almost impossible to do this in reality, especially for the process control system that changes from time to time with the operating conditions, the system structure and parameters are seriously uncertain, nonlinear, hysteresis, many disturbances and other factors, it is impossible to write its analytical model

Images