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

Product key part state classification method for class imbalance data

A technology for balancing data and state classification, applied in computer parts, neural learning methods, instruments, etc., to achieve high-precision prediction, improve prediction accuracy, and powerful data mining capabilities

Active Publication Date: 2021-01-22
ZHEJIANG UNIV
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, in the process of CNC machine tool processing, if you want to measure the wear of the tool, you need to interrupt the current operation and use tools such as microscopes for measurement, which is unacceptable in actual production

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
  • Product key part state classification method for class imbalance data
  • Product key part state classification method for class imbalance data
  • Product key part state classification method for class imbalance data

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0049] S1. Acquisition and preprocessing of source and auxiliary datasets:

[0050] First, the labeled industrial imbalance data is obtained as the source training set. In this example, C1, C4, and C6 are labeled, but considering that a test set is required to test and verify the method of the present invention, C1 and C6 are used as source training sets, and C4 is used as a test set for the algorithm. Among them, the existence of the test set is only for evaluating the proposed method, which is not necessary in the actual application process.

[0051] Then, a large amount of unlabeled sensor data in the same scene is obtained as an auxiliary training set. In this example, C2, C3, and C5 do not have corresponding labels, so they are used as auxiliary training sets. Table 2 shows the division of the dataset.

[0052] Finally, make predictions on the above data. In this instance, missing value handling and data standardization are required for the dataset. Among them, the m...

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 product key part state classification method for class imbalance data. The method comprises the steps of: obtaining and preprocessing an auxiliary training set and a source training set; performing N times of undersampling processing on the majority class samples in the source training set to obtain N relatively balanced sub-data sets; training N SVM classifiers in parallel by using the N sub-data sets, and selecting by using a voting method to obtain a final prediction result; taking out a minority of auxiliary data in a final prediction result and adding the minority of auxiliary data to the source training set; constructing a deep learning classification model and supervising training by using the reconstructed source training set; and performing detection processing on to-be-predicted sensor data. According to the method, label data in the source training set and unlabeled data in the auxiliary data set are fully utilized, a weak supervised learning methodis utilized for processing, the imbalance proportion of class imbalance data can be reduced, and the prediction effect of the classification model is improved.

Description

technical field [0001] The invention belongs to a weakly supervised learning classification method in the field of industrial unbalanced data processing, and in particular relates to a method for classifying the status of key product components for unbalanced data. Background technique [0002] Key components of products such as cutting tools, gears, bearings, etc. are widely used in modern industry, and the performance of a large number of industrial systems is related to the normal operation of key components. The working status of key components has great significance for the reliability and effectiveness of industrial systems. With the development of Internet technology, advanced sensing technology and storage technology, a large amount of valuable sensor data is collected and stored in modern industrial production. Analyzing the working status of key components of products through sensor data has also received extensive attention from industry and academia. However, t...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/23G06F18/2411G06F18/214Y02P90/30
Inventor 刘振宇刘惠郏维强张朔张栋豪谭建荣
Owner ZHEJIANG 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