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

Method for identifying and classifying wood defects based on multiple features

A defect identification and classification method technology, 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 effect of convenient and flexible implementation, high reliability, and saving instrument costs

Inactive Publication Date: 2015-08-19
ZHEJIANG FORESTRY UNIVERSITY
View PDF6 Cites 5 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
  • Method for identifying and classifying wood defects based on multiple features
  • Method for identifying and classifying wood defects based on multiple features
  • Method for identifying and classifying wood defects based on multiple 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 Image 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 int...

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 identifying and classifying wood defects based on multiple features. The method comprises the following steps of firstly, selecting experiment sample data; then, collecting stress wave propagation speed data; collecting resistance value; performing data processing on the stress wave propagation speed data and the resistance value; separating a plurality of groups of sample data of each wood defect type into training group data and classifying group data; finally, adopting a support vector machine method to train and classify; using a stress wave wood non-destructive detection instrument to collect the feature of the stress wave propagation speed data, and using a micro-drill resistance instrument to collect the feature of the resistance value, so as to well represent the global feature of the cross section of the wood; identifying and classifying the interior defect of the wood according to the features of the two types of wood data and the support vector machine method, so as to accurately classify the type of the wood defect. The method has the advantages that the reliability is higher, the implementing is convenient and flexible, and the cost of the instruments is reduced.

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 Applications(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 Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products