Machine tool machining precision retaining ability prediction method based on rough set theory and least squares support vector machine

Abstract

The invention relates to a machine tool machining precision retraining ability prediction method based on a rough set theory and a least squares support vector machine. Generally, complex and great data error are generated if error data is required to be measured in a long term and detection and analysis are required to be carried out on the machining precision within the specified time for multiple times. The invention provides a machining procession retaining ability prediction method on the basis of the error data, which comprises the steps of firstly establishing a spatial error model of the overall machine tool on the basis of a topological structure of the machine tool by using an exponential matrix mode of a screw theory so as to carry out topological structure based screw theory error modeling and carry out measurement on the error data; secondly, carrying out reduction on the error data based on the rough set (RS) theory, and then carrying out machining precision retaining ability prediction based on a least squares support vector machine (LS-SVM) method; and finally, proving the effectiveness of the prediction method provided by the invention by using a simulation method.

Description

technical field [0001] The invention provides a method for predicting the maintenance of machine tool machining accuracy based on rough set theory and least square support vector machine, which belongs to the field of machine tool precision design. Background technique [0002] For machine tools, machining accuracy is an important indicator for evaluating the performance and characteristics of machine tools. In modern production, machine tools play an important role in modern manufacturing due to high metal removal rate, shortened machining time, high productivity and short workpiece setup time. However, there are many factors that affect the machining accuracy of machine tools, among which geometric errors and thermal errors account for about 60% of the total machining errors. Due to the repeatability, randomness and measurability of these errors, error prediction and compensation is an effective way to improve the machining accuracy of machine tools. In addition to geome...

AI Technical Summary

Problems solved by technology

From the above analysis, we can see that, so far, although a series of time series prediction research results have been obtained, in practical applications, artificial neural network prediction methods and traditional statistical analysis methods are widely used. Although these methods The prediction accuracy has been greatly improved, but it is difficult to meet the requirements of real-time and prediction accuracy in practical applications.

Images