Wood defect recognition and classification method based on multi-features

A technology of defect identification and classification method, which is applied in the field of wood defect identification and classification based on multi-features, can solve problems such as inability to judge defects, and achieve the effects of convenient and flexible implementation, saving instrument costs, and high reliability

Inactive Publication Date: 2017-11-03
ZHEJIANG FORESTRY UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current stress wave wood nondestructive testing technology and micro-drilling resistance wood testing technology can only qualitatively determine whether there are defects, the size of the defects, and the location of the defects in the wood, but cannot determine the specific type of defects, which leads to the maintenance and reputation of ancient buildings. In the process of protecting ancient trees, it is difficult to select different measures for specific defects for post-processing

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
  • Wood defect recognition and classification method based on multi-features
  • Wood defect recognition and classification method based on multi-features
  • Wood defect recognition and classification method based on multi-features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0057] Embodiment: choose pine as the wood experiment sample, collect 20 groups of sample data containing void defects, sample data containing crack defects, sample data containing decay defects, and sample data without defects, and use the support vector machine method to carry out classification experiments in MATLAB software , refer to Figure 6 It can be seen that there are 20 data in the classification set, 19 of which are correctly classified, and the classification accuracy can reach 95%; refer to Figure 7 , Figure 7 It is a histogram of classification accuracy rate for pine sample identification, which shows the classification accuracy rate of four types of defects, among which the classification accuracy rate of void defects is 100%, the classification accuracy rate of crack defects is 100%, and the classification accuracy rate of decay defects is 100%. The classification accuracy rate reaches 80%, the classification accuracy rate of no defect type, that is, the in...

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 wood defect recognition and classification method based on multi-features. Firstly, the experimental sample data is selected; then the stress wave propagation velocity data is collected; then the resistance value is collected; and then the stress wave propagation velocity data and the resistance value are data processed; Then, several groups of sample data of each type of wood defects are divided into training group data and classification group data, and finally the support vector machine method is used for training and classification. Using the stress wave wood non-destructive tester to collect the data characteristics of the stress wave propagation velocity and the micro-drilling resistance meter to collect the characteristics of the resistance value can better characterize the global characteristics of the wood cross section. Using these two wood data features and the support vector machine method Identifying and classifying the defects inside the wood can accurately classify the types of wood defects, and has high reliability, and the method is convenient and flexible to implement, and can save instrument costs.

Description

technical field [0001] The invention belongs to the technical field of wood non-destructive testing, and in particular relates to a multi-feature-based wood defect recognition and classification method. Background technique [0002] Facing the current situation of scarcity of wood resources, how to improve the utilization rate of wood and promote the sustainable development of my country's forestry modernization has become the focus of forestry workers. Stress wave wood nondestructive testing technology and micro-drilling resistance wood testing technology are widely used in wood nondestructive testing because of their own characteristics. However, the current stress wave wood nondestructive testing technology and micro-drilling resistance wood testing technology can only qualitatively determine whether there are defects, the size of the defects, and the location of the defects in the wood, but cannot determine the specific type of defects, which leads to the maintenance and...

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): G01N29/07G01N29/44
Inventor 李光辉王再超冯海林
Owner ZHEJIANG FORESTRY UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap