Intelligent regulation and control method for high-speed motorized spindle water cooling system

Abstract

The invention discloses an intelligent regulation and control method for a high-speed motorized spindle water-cooling system, and the method comprises the steps: building a structure of an RBF neural network, building a four-layer GA-GRNN neural network structure frame and a four-layer generalized regression neural network (GRNN) structure on the improvement of the RBF neural network, and carrying out the global search of a generalized regression neural network smooth factor sigma through a genetic algorithm so that the global minimum value is simply and accurately found; initializing a generalized regression neural network smooth factor sigma by adopting a random population initialization mode; constructing a fitness function of a genetic algorithm (GA), calculating individual fitness, establishing a high-speed motorized spindle thermal characteristic regulation and control cooling medium flow model, so that it is better that the predicted output is closer to an actual value, and adopting the predicted temperature characteristic of a GRNN model to construct the fitness function; performing natural selection operation on the population, and performing selection, crossover and mutation operation on individuals to evolve the population; and repeatedly selecting the fitness function to establish the model and operating the population and the individuals until the precision is met or the maximum number of iterations is met. According to the method, global optimal search is performed on the smooth factor sigma of the GRNN by using the genetic algorithm, so that the prediction precision and generalization ability of the GRNN are improved, and the training precision and robustness of the GRNN are improved.

Description

technical field [0001] The invention relates to the field of regulation and control of a high-speed electric spindle water cooling system, in particular to a GRNN high-speed electric spindle intelligent control cooling medium flow method based on genetic algorithm optimization. Background technique [0002] Now in the actual operation of the high-speed electric spindle, the internal heat of the spindle is large, the temperature rises, and the speed is fast, which leads to the thermal deformation of the spindle and affects the machining accuracy of the electric spindle. The thermal characteristics of the electric spindle are not only related to the heating of the internal heat source of the spindle. The performance of the electric spindle cooling system is also inseparable. Among the electric spindle related technologies, the electric spindle cooling technology can be said to be an extremely important part, which directly affects the processing performance and service life of...

AI Technical Summary

Problems solved by technology

Shigenoriando and Narashino of Japan proposed a centralized cooling and lubrication system, which opened a cooling channel inside the main shaft to directly cool the bearings, and opened another channel to lubricate the bearings. Experiments have proved that the lubrication and cooling effect is better, but the overall cooling has limitations. and higher cost

Images