Machine vision-based cutter type discrimination and geometric parameter detection method and system

Abstract

The invention discloses a machine vision-based cutter type discrimination and geometric parameter detection method and system. The method specifically comprises the following steps of: performing detection initialization; installing a cutter on a machine tool spindle, and recording coordinates of the cutter under a machine tool coordinate system; acquiring a cutter dynamic image; identifying the acquired cutter dynamic image by adopting a cutter identification model trained by a convolutional neural network, and judging the type of the current cutter; measuring a geometric dimension of the identified cutter; when the geometric dimension of the cutter is measured, the geometric parameters of the common cutter are mainly measured, the obtained cutter type and the obtained geometric dimension of the cutter are compared with the cutter type and the geometric dimension of the cutter in the current processing file, and corresponding early warning information is sent out when the cutter type or the geometric dimension of the cutter is inconsistent; the automation degree of the machine tool machining process is effectively improved, measurement is efficient and accurate, the problem of cutter replacement errors is solved, large losses are avoided, measurement of various common cutter parameters is considered, and the application range is wide.

Description

technical field [0001] The invention relates to the field of state monitoring of CNC machine tool tools, in particular to a machine vision-based tool type discrimination and geometric parameter detection method and system. Background technique [0002] With the rapid development of numerical control technology (CNC) and the rapid rise of flexible manufacturing system (FMS), the market demand for high-efficiency and low-cost automated processing continues to increase. In order to ensure the stable and automatic machining process, it is particularly important to monitor the performance indicators of various parts of the CNC machine tool, and the research on tool state detection technology is an important part of it. As a professional tool that directly affects the machining quality of machine tools, the physical state of cutting tools directly affects the machining accuracy of precision parts. [0003] In the CNC machining process of aeronautical structural parts, the materia...

AI Technical Summary

Problems solved by technology

[0004] At present, the detection of tool parameters is mainly manual detection. Compared with the current high-automation processing mode, manual detection of tool parameters greatly reduces the processing efficiency. It is found that it is very easy to cause the scrapping of workpieces, especially for large aeronautical structural parts, once scrapped, it will not only bring great economic losses to the enterprise, but also affect the production cycle of the aircraft

At present, some scholars are also researching the tool parameter detection method based on machine vision, but only for the parameter measurement of the integral end mill, and do not consider the fillet measurement of the tool nose and the parameter measurement of other types of tools commonly used in the processing process, such as the commonly used machine tools. Clamping tool, T-shaped knife, fast feed tool, etc.

Images