Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A detection method for the passivation state of grinding acoustic grinding wheel based on hdp-hsmm

A passivation state and detection method technology, applied in the field of machining, can solve the problems of occupation, inability to respond to different passivation states, large computing resources, etc., to achieve low experimental cost, less grinding acoustic emission data, and improved processing efficiency Effect

Active Publication Date: 2020-04-21
NANJING UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This requires a lot of time and experimental costs, takes up a lot of computing resources, and can only be learned for a few selected grinding wheels in a specific state, and cannot reflect the different passivation states that appear in a complete passivation cycle of the grinding wheel

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
  • A detection method for the passivation state of grinding acoustic grinding wheel based on hdp-hsmm
  • A detection method for the passivation state of grinding acoustic grinding wheel based on hdp-hsmm
  • A detection method for the passivation state of grinding acoustic grinding wheel based on hdp-hsmm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings.

[0020] The HDP-HSMM-based grinding sound grinding wheel passivation state detection system of the present invention includes a sensor signal acquisition module, a signal preprocessing and feature extraction module, an HDP-HSMM learning module, and a grinding wheel state judgment module, such as figure 1 shown. The sensor signal acquisition module collects the grinding acoustic emission signal, preprocesses it through the signal preprocessing and feature extraction module, conducts training and learning through the HDP-HSMM learning module, determines the parameters of the learning module, trains the HDP-HSMM, and pre-processes the signal After preprocessing by the processing and feature extraction module, the passivation state of the grinding wheel is judged by the grinding wheel state judgment module through the trained HDP-HSMM.

[0021] The sensor signal acquisitio...

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 method for detecting blunt states of acoustic emission of a grinding wheel based on HDP-HSMM. Firstly, acoustic emission signals of a processing site are collected by an acoustic emission sensor in real time; then a wavelet soft threshold denoising method is used to denoise; then framing is performed on the denoised acoustic emission signals, 8 statistical features of each frame of the signals are extracted to form a 8-dimensional acoustic emission data set; finally, and the 8-dimensional acoustic emission data set is used to train the HDP-HSMM; the trained HDP-HSMM is used to predict the blunt state, represented by an acoustic emission signal, of the grinding wheel in a new processing process. The method based on the HDP-HSMM is an unsupervised learning method. Compared with the prior art, the method does not require prior knowledge of the blunt states of the grinding wheel, automatically aggregates the collected acoustic emission signals for effective division of blunt degrees of the grinding wheel so as to further obtain the state of the grinding wheel in the whole processing process. The method can accurately identify different blunt states of the grinding wheel in the grinding process, and can quantitatively classify the blunt degrees of the grinding wheel, thereby greatly reducing the dependence on skilled workers, improving the processing efficiency, and having extremely important industrial application value.

Description

technical field [0001] The invention and a detection method in the field of mechanical processing are specifically a detection method for the passivation state of a grinding acoustic grinding wheel based on a layered Dirichlet process-hidden semi-Markov model (HDP-HSMM). Background technique [0002] In mechanical processing, grinding is an important processing method, and the grinding lathe is the main tool for implementing this processing method. Traditionally, grinding machine processing requires more skilled workers to judge whether the tool (ie, grinding wheel) is passivated based on work experience. Due to the existence of human factors, processing efficiency and quality are often affected, and may cause unnecessary damage to workpieces and tools. In order to realize the automation of production, engineers have proposed various intelligent detection methods for the passivation status of grinding wheels. [0003] However, although these methods can detect the state of...

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): G01N29/14G01N29/44
CPCG01N29/14G01N29/449G01N2291/2696
Inventor 杨京钟利民王绪隆张仲宁程建春
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com