GRNN motorized spindle thermal error modeling method based on genetic algorithm optimization

Abstract

The invention discloses a GRNN motorized spindle thermal error modeling method based on genetic algorithm optimization, and the method comprises the steps: building a four-layer generalized regression neural network (GRNN) structure, carrying out the global search of a generalized regression neural network smooth factor sigma through a genetic algorithm, and simply and accurately finding a global minimum value; 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, executing natural operation on a population, and selecting, crossing and inheriting individuals; establishing a GRNN framework, training samples, so population evolution gradually reaches the training precision, and finally, verifying the generalization of a generalized regression neural network (GA-GRNN) optimized by a genetic algorithm by adopting experimental data of different rotating speeds. According to the method, global optimal search is carried out on the smooth factor sigma of the GRNN by using the genetic algorithm, and the prediction precision and generalization ability of the GRNN are improved.

Description

technical field [0001] The invention relates to the field of thermal error analysis of a high-speed electric spindle, in particular to a GRNN electric spindle thermal error modeling method based on genetic algorithm optimization. Background technique [0002] The genetic algorithm was first proposed in 1967. Bagley, a student of Professor Holland, mentioned "Genetic Algorithm" (GA for short) in his doctoral thesis. Genetic Algorithm (GA) is an adaptive global optimization search algorithm proposed for simulating the genetic and evolutionary process of organisms in the natural environment. The genes of poorer individuals fade away. Selection, crossover and mutation are the main operation algorithms of genetic algorithm. [0003] General Regression Neural Network (GRNN for short) was proposed by Dr. Specht in 1991, which is another deformation form of radial basis network. GRNN is based on non-parametric regression, takes the sample data as the posterior condition, performs...

AI Technical Summary

Problems solved by technology

Since the least squares fitting uses the minimum square of the distance for fitting, this algorithm is very sensitive to some outlier noise points, especially for point sets with large outliers, their weight is very large, resulting in The desired straight line is pulled off

[0007] 2. Gray GM (1, 1) modeling, this model has a strong dependence on historical data, and does not consider the relationship between various factors, the error is large

However, the BP neural network has slow convergence speed, long training time, and low efficiency. It may converge to a local minimum, which affects model accuracy and real-time performance, and is not conducive to real-time compensation of machine tool thermal errors.

Images