An Intelligent Identification Method of Milling Chatter Based on Theoretical Model Including Milling Angle

Abstract

The invention provides a milling chatter intelligent identification method based on a theoretical model including milling angle. In the industrialized milling process, a dynamic equation including milling angle is established according to the actual milling machine structure and tool parameters. Through milling Various parameters were measured in the force test. Afterwards, the neural network is trained using industrialized big data, and the threshold function for judging whether flutter occurs is fitted. In the real-time industrial production process, the microphone is used to measure the sound signal, and the singular spectrum is decomposed after short interception. The characteristic components are selected according to the relationship between the KL divergence and the Pearson coefficient, and the judgment index is constructed through the weighted permutation entropy. According to the size relationship between the index and the threshold function, the intelligent prevention of chattering phenomenon is realized.

Description

technical field [0001] The invention relates to the field of industrial milling, in particular to an intelligent identification method for milling chatter based on a theoretical model including milling angles. Background technique [0002] Chatter is a problem that needs to be avoided in industrial high-speed milling. Chatter is a bad consequence caused by the continuous aggravation of self-excited vibration. If it is not controlled, it will cause a series of serious problems affecting workpieces, cutting tools and milling machines. Chatter will affect the efficiency and quality of industrial production, causing huge economic losses to the factory. Therefore, it is of great significance to study the chatter problem at the moment when the production efficiency is continuously increasing and the demand for product quality is continuously improving. At present, many engineers are devoting themselves to the scientific research on machining chatter, and some related methods hav...

AI Technical Summary

Problems solved by technology

[0004] At the existing technical level, the above three solutions all have certain deficiencies

The first type of scheme lacks the adaptability of chatter identification and cannot be adjusted according to changing processing conditions, and the existing theoretical model does not take into account the influence of milling angle on chatter, which is different from the actual working conditions; the second type of research It tends to be triggered only from signals, and lacks the principle research on the milling process itself; the third type of research relies on deep learning models, but the amount of data required for such model training is too large, and the current situation is that it is not suitable for actual industrial production. There are limitations

Images