Machine tool cutter vibration monitoring and analyzing method based on artificial intelligence and big data

Abstract

The invention discloses a machine tool cutter vibration monitoring and analyzing method based on artificial intelligence and big data. According to the method, on the premise of big data, artificial intelligence methods such as machine learning and deep learning are combined to perform feature extraction, feature transformation and feature learning on vibration signals generated by key devices soas to monitor and analyze the key devices. The beneficial effects of the invention are that the vibration analysis is simple in feature extraction, is convenient to install and deploy, and does not damage the structure of a measured object body.

Description

technical field [0001] The invention relates to the field, in particular to a method for monitoring and analyzing machine tool tool vibration based on artificial intelligence and big data. Background technique [0002] With the development of science and technology, problems caused by vibration and dynamic characteristics of equipment have attracted great attention from all walks of life. For example: the vibration of mechanical processing equipment directly affects the accuracy and effectiveness of processing; the vibration signal of large rotating machinery directly reflects the main information of equipment operation. Therefore, the analysis technology of vibration signal is one of the important branches of mechanical dynamics, and it is an extremely common aspect of mechanical dynamics engineering application. With the development of equipment toward automation and high speed, the problems caused by vibration are more prominent, and the problems that need to be solved a...

AI Technical Summary

Problems solved by technology

[0003] Traditional key component monitoring and analysis technologies are based on acoustic emission, current, power, torque and other technologies. Generally speaking, the sensors used are large in size, expensive, low in accuracy, limited in installation, and interfered in processing.

The extracted feature signals often have low sensitivity, high delay, and high signal-to-noise ratio

Traditional analysis methods are often based on overly simple combination judgments or overly complex mathematical modeling, which have poor versatility and applicability for characteristic signal processing, and have a high threshold for processing complex problems.

Images