Method for identifying grade of wood for Chinese zither panel through near infrared spectrum based on neural network

A near-infrared spectroscopy and neural network technology, applied in the field of high-level testing, can solve the problems of decreasing year by year, the subjective influence of the discriminator on the number of relevant practitioners, and the long discrimination time, so as to achieve a low misjudgment rate and more objective discrimination results. , the effect of high accuracy

Active Publication Date: 2019-01-22
NORTHEAST FORESTRY UNIVERSITY +1
View PDF11 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the existing problems such as long discrimination time, judgment results easily subject to the subjective influence of judges, and the number of releva

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 grade of wood for Chinese zither panel through near infrared spectrum based on neural network
  • Method for identifying grade of wood for Chinese zither panel through near infrared spectrum based on neural network
  • Method for identifying grade of wood for Chinese zither panel through near infrared spectrum based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0024] Specific embodiment 1: This embodiment provides a method for identifying the grade of paulownia wood for guzheng panels based on neural network near infrared spectroscopy, such as figure 1 As shown, the method includes the following steps:

[0025] Step (1): Perform Savitzky-Golay convolution smoothing, first-order derivative preprocessing and principal component analysis on N groups of near-infrared spectroscopy data of different bands containing wood for guzheng panels of different grades. The infrared spectrum data is randomly grouped, and n groups of data are used as the training sample set, and Nn groups of data are used as the test sample set.

[0026] Step (2): Construct an improved BP neural network model, which includes an input layer, a hidden layer, and an output layer. The Softmax function is used as the classification function of the model. The specific construction steps are as follows:

[0027] (1) Initialize the chaotic sequence generated by the one-dimensional...

Example Embodiment

[0034] Specific embodiment two: this embodiment is a further description of specific embodiment one. The specific implementation steps of this embodiment are as follows:

[0035] (1) Collect near-infrared spectroscopy data of the wood used for the guzheng panel to be tested.

[0036] (2) Spectral data analysis:

[0037] (2a) Observing the original spectrum curve, it is found that the spectrum overlaps and the spectrum peaks overlap. This embodiment combines the improved BP neural network algorithm to extract the spectrum features. Observing the original spectrum, we can find that the wood has a wave number of 10000cm -1 To 7100cm -1 The absorption is the smallest near the area, at the wave number 6806cm -1 Up to 5192cm -1 Area absorption is slightly higher, at wave number 4400cm -1 Up to 4016cm -1 The highest area near the district;

[0038] (2b) Reference Figure 4 , The spectral data is at 6806cm -1 , 5804cm -1 , 5602cm -1 , 5192cm -1 , 4760cm -1 , 4400cm -1 , 4286cm -1 , 4016cm -1...

Example Embodiment

[0056] Specific implementation mode 3: In this embodiment, three grades of paulownia wood suitable for wood for guzheng panels and three wood samples of unknown grade for panels are used as analysis objects.

[0057] Such as figure 1 As shown, the near-infrared-based method for identifying wood grades for guzheng panels in this embodiment uses Savitzky-Golay convolution smoothing and first-order derivative methods to preprocess the data set, perform principal component analysis operations, and analyze spectra to determine the absorption of certain chemical bonds. Peak position, determine the band data sent to the neural network model, and divide it into a training sample set and a test sample set. Using the improved BP neural network model, send the feature vector to the Softmax classifier, adjust the number of hidden layer nodes and participate For the experimental bands, the best results of the plate grade classification of the training sample set are obtained, and the final spe...

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 the grade of wood for a Chinese zither panel through the near infrared spectrum based on a neural network. The method comprises the steps of: (1), performing Savitzky-Golay convolution smoothing, first-order derivative pre-processing and principal component analysis on near infrared spectrum data including the wood for the Chinese zither panel in different grades; (2), constructing an improved BP neural network model; (3), training the improved BP neural network model; and (4), classifying the near infrared spectrum data of the wood for the Chinese zither panel by utilizing the trained improved BP neural network model, so that grade identification of the wood for the Chinese zither panel is realized. According to the method in the invention,judgement is carried out based on the near infrared spectrum data covering chemical substances of the wood for the Chinese zither panel in different grades; data measurement is rapid; the cost is low; the judgement time is short; the calculation data volume is effectively reduced; the subjective assume is not doped; the stability is relatively high; and the method is relatively robust.

Description

technical field [0001] The invention belongs to the technical field of grade identification of zither panels, and relates to a method for grading identification of wood used in zither panels, in particular to a method based on identifying information such as compound characteristic peaks in the near-infrared spectrum band of the panel and extracting feature vectors by neural networks, thereby identifying Test methods for their grades. Background technique [0002] With the rapid development of my country's economy and the continuous improvement of living standards, people's demand for high-grade zither products is also increasing, and people's requirements for the sound quality of zither are also getting higher and higher. High-quality zither products have very high performance value. Vibration is caused by plucking the strings, which is transmitted to the panel through the zither code, thereby producing a beautiful melody. It can be seen that in the case of other materials ...

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): G01N21/359G01N21/3563G06N3/08
CPCG06N3/084G01N21/3563G01N21/359
Inventor 黄英来孟诗语苗红曲玉利于鸣温馨
Owner NORTHEAST 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