Unlock instant, AI-driven research and patent intelligence for your innovation.

Deep kernel extreme learning machine method and system for online monitoring of tool wear status

A nuclear extreme learning machine, tool wear technology, applied in the direction of manufacturing tools, measuring/indicating equipment, metal processing machinery parts, etc., can solve the problem of unreasonable single simple core, achieve the effect of improving performance and increasing accuracy

Active Publication Date: 2021-04-13
温州大学苍南研究院
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when using a classifier for classification, different physical field signals are suitable for different kernel functions, and it is not reasonable to use a single simple kernel for mapping

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Deep kernel extreme learning machine method and system for online monitoring of tool wear status
  • Deep kernel extreme learning machine method and system for online monitoring of tool wear status
  • Deep kernel extreme learning machine method and system for online monitoring of tool wear status

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention is described in further detail below in conjunction with accompanying drawing:

[0051] Such as figure 1 As shown, in the embodiment of the present invention, a deep kernel extreme learning machine method for on-line monitoring of tool wear status is proposed, including the following steps:

[0052] S1. Model training; the specific steps are as follows:

[0053] S11. Collect signals related to tool wear status of multiple channels through sensors. It mainly includes:

[0054] Acquisition of multi-channel signals (X j ,Y j ), there is a total of J-type physical fields, taking the j-th type of physical field as an example, the mathematical form of the time-domain signal is:

[0055] x j =x ij (n) (1)

[0056] In formula (1), X j ={x 1j ,x 2j ,...,x mj} T ∈ R m×n is the collected m×n order original signal sample matrix, where: n is the number of signal sampling points, i=1, 2,..., m is the number of signal sampling.

[0057] Y j ={y 1j ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a deep kernel extreme learning machine method and system for on-line monitoring of tool wear status. Firstly, multiple sensors are used to collect multi-channel signals of the tool under different wear status; processing, and calculate its multiple statistical characteristic parameters; then construct a data-driven deep kernel function, map the sample signal to the deep kernel space, form a training sample and store it in RAM; finally, during online monitoring, calculate the collected multi-channel signal Features, and mapped to the deep kernel space to form test samples and training samples stored in RAM are simultaneously input to the extreme learning machine for classification, output the wear state of the current signal, and realize online monitoring of tool wear state.

Description

technical field [0001] The invention relates to the field of manufacturing process monitoring, in particular to a deep kernel extreme learning machine method and system for online monitoring of tool wear status. Background technique [0002] With the continuous development of modern manufacturing, the degree of automation of manufacturing systems directly affects the production efficiency of enterprises, and the degree of automation of CNC machine tools is an integral part of most manufacturing systems. As one of the most vulnerable parts of CNC machine tools, the wear degree of cutting tools is closely related to product quality and production efficiency. According to statistics, the downtime of machine tools due to tool breakage accounts for nearly 20% of the total downtime of machine tools. Therefore, it is very valuable and practical to monitor the wear state of the tool in real time in order to detect the abnormal state early. [0003] Since it is difficult to realize...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): B23Q17/09
CPCB23Q17/0957
Inventor 周余庆雷芝向家伟
Owner 温州大学苍南研究院