Tool breakage monitoring method based on SAEs and K-means

Abstract

The invention discloses a tool breakage monitoring method based on an SAEs and K-means. The method comprises the following steps: 1, collecting a current signal sample set; 2, inputting current signals subjected to arrangement treatment into the SAEs as an input sample set, reconstructing and extracting features of original current signals, and outputting an encoding vector which is last obtained through SAEs training as a feature vector; 3, treating the feature vector as an input layer of K-means clustering, and classifying all input data; 4, outputting a sample clustering result, and conducting fine adjustment on K-means parameters and SAEs parameters according to a clustering effect; and 5, outputting the clustering effect, and judging whether a tool is broken or not according to the clustering effect.

Description

technical field [0001] The invention belongs to the related field of tool detection technology, and more specifically relates to a tool damage monitoring method based on SAEs and K-means. Background technique [0002] CNC machine tool tool monitoring means that during the product processing process, the computer judges and predicts whether the tool is damaged by detecting the signal changes of various sensors. The essence of the tool damage monitoring process is an analog recognition process. A complete tool damage monitoring system consists of research objects (tools), processing conditions, sensor networks, signal processing modules, feature extraction modules, and pattern recognition modules. [0003] Due to the inevitable damage of the tool during the processing, the damage of the tool will directly affect the utilization rate of the machine tool and the processing quality of the workpiece. The light one will cause the quality of the processed workpiece to decline, and t...

AI Technical Summary

Problems solved by technology

After decades of development, tool monitoring technology has reached a certain level in breadth and depth, but so far has not found a method that can be applied to different processing conditions and monitor various tools

The scope of use of various existing monitoring methods is limited, and it is far from meeting the requirements of automation and intelligence; there are still certain limitations in practical applications, mainly reflected in the need for a large number of signal processing technologies and diagnostics Combined with engineering practice to manually select fault features; only use the shallow features selected by traditional methods to identify the tool health status; the entire intelligent diagnosis process requires manual participation, artificially supervised extraction of features from the signal one by one, Heavy workload, low efficiency and high cost

Images