Multi-axle numerical servo-control system model identification method

Abstract

The invention discloses a multi-axle numerical servo-control system model identification method. The method improves the modeling precision of a system model by making comprehensive use of a plurality of interdisciplinary advanced theories and methods of a support vector machine, granular computing, system identification, immune algorithm and particle swarm optimization algorithm, and identifies the model structure of a numerical servo-control system by adopting the idea of combining two-dimensional search algorithm with the support vector machine. In such a way, the identification precision of the model structure is improved. The model parameters of the numerical servo-control system are identified by adopting a method based on the information granule support vector machine. Meanwhile, the parameters of the information granule support vector machine are optimized by adopting an immune particle swarm optimization algorithm based on intersection and variation functions so as to improve the identification effect. The method disclosed by the invention can effectively improve the identification precision of the system and provides a precise control model for independent axle servo-control and multi-axle linked servo-control of the numerical control system.

Description

technical field [0001] The invention belongs to the technical field of numerical control, in particular to a method for establishing and identifying a control model applied to a servo control system of a multi-axis numerical control system, specifically a method for identifying a model of a multi-axis numerical control servo control system. Background technique [0002] When using modern control theory methods to control, it is necessary to know exactly the system model of the controlled object of the CNC servo control system. Usually, there are mainly three methods for establishing the system model of the controlled object: theoretical modeling method, system identification method and hybrid modeling method. Even if the system model is established with the same theoretical method, due to the uncertainty of the structure, parameters and environment of the controlled object, it is affected by factors such as the specific environment. In different environments, the specific st...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problems of low precision and poor repeatability existing in the existing multi-axis numerical control servo control system model, and to invent a comprehensive application of support vector machine, granularity calculation, system identification, immune algorithm, genetic algorithm and particle A variety of cross-disciplinary new multi-axis CNC servo control system model modeling and identification methods such as group optimization algorithm provide more accurate control models for CNC system independent axis servo control and multi-axis linkage servo control

Images