Non-Destructive Testing of Mechanical Properties of Solid Wood Panel Based on Partial Least Squares Structural Equation Modeling Transfer Method
Calibration transfer between near infrared (NIR) spectrometers is a subtle issue in the chemometrics and process industry. Similar instruments may generate strongly different spectral responses, and regression models developed on a first NIR system can rarely be used with spectra collected by a seco...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
North Carolina State University
2023-04-01
|
Series: | BioResources |
Subjects: | |
Online Access: | https://ojs.cnr.ncsu.edu/index.php/BRJ/article/view/22315 |
_version_ | 1797794796593479680 |
---|---|
author | Dapeng Jiang Yizhuo Zhang Jinhao Chen |
author_facet | Dapeng Jiang Yizhuo Zhang Jinhao Chen |
author_sort | Dapeng Jiang |
collection | DOAJ |
description | Calibration transfer between near infrared (NIR) spectrometers is a subtle issue in the chemometrics and process industry. Similar instruments may generate strongly different spectral responses, and regression models developed on a first NIR system can rarely be used with spectra collected by a second apparatus. In this work, two novel methods based on Structural Equation Modeling (SEM), called Enhanced Feature Extraction Approaches for factor analysis (EFEA-FA) and Enhanced Feature Extraction Approaches for spectral space transformation (EFEA-SST), were proposed to perform calibration transfer between NIR spectrometers. They were applied to a NIR nondestructive testing model for solid wood panels mechanical properties. Four different standardization algorithms were evaluated for transferring solid wood panels quality databases between a portable NIRS (InGaAs)-array spectrometer (NIRquest512) and a HSI Camera (SPECIM FX17). The results showed that EFEA-SST yielded the best model evaluation metrics (R2 and Root Mean Square Error of Prediction (RMSEP)) values for tensile strength (RMSEP=11.309, R2=0.865) parameters, while EFEA-FA gave the best fit for flexural strength (RMSEP=10.653, R2=0. 912). These results suggest the potential of two novel quality parameters prediction methods based on spectral databases transferred between diverse NIRS spectrometers. |
first_indexed | 2024-03-13T03:07:29Z |
format | Article |
id | doaj.art-d0529466993e46c1a0e274c4222f4e39 |
institution | Directory Open Access Journal |
issn | 1930-2126 |
language | English |
last_indexed | 2024-03-13T03:07:29Z |
publishDate | 2023-04-01 |
publisher | North Carolina State University |
record_format | Article |
series | BioResources |
spelling | doaj.art-d0529466993e46c1a0e274c4222f4e392023-06-26T18:59:24ZengNorth Carolina State UniversityBioResources1930-21262023-04-0118236203641317Non-Destructive Testing of Mechanical Properties of Solid Wood Panel Based on Partial Least Squares Structural Equation Modeling Transfer MethodDapeng Jiang0Yizhuo Zhang1Jinhao Chen2College of Computer Science and Artificial Intelligence, Changzhou UniversityCollege of Computer Science and Artificial Intelligence, Changzhou UniversityCollege of Mechanical and Electrical Engineering, Northeast Forestry UniversityCalibration transfer between near infrared (NIR) spectrometers is a subtle issue in the chemometrics and process industry. Similar instruments may generate strongly different spectral responses, and regression models developed on a first NIR system can rarely be used with spectra collected by a second apparatus. In this work, two novel methods based on Structural Equation Modeling (SEM), called Enhanced Feature Extraction Approaches for factor analysis (EFEA-FA) and Enhanced Feature Extraction Approaches for spectral space transformation (EFEA-SST), were proposed to perform calibration transfer between NIR spectrometers. They were applied to a NIR nondestructive testing model for solid wood panels mechanical properties. Four different standardization algorithms were evaluated for transferring solid wood panels quality databases between a portable NIRS (InGaAs)-array spectrometer (NIRquest512) and a HSI Camera (SPECIM FX17). The results showed that EFEA-SST yielded the best model evaluation metrics (R2 and Root Mean Square Error of Prediction (RMSEP)) values for tensile strength (RMSEP=11.309, R2=0.865) parameters, while EFEA-FA gave the best fit for flexural strength (RMSEP=10.653, R2=0. 912). These results suggest the potential of two novel quality parameters prediction methods based on spectral databases transferred between diverse NIRS spectrometers.https://ojs.cnr.ncsu.edu/index.php/BRJ/article/view/22315solid wood panelcalibration transfernear infraredhyperspectralmechanical property |
spellingShingle | Dapeng Jiang Yizhuo Zhang Jinhao Chen Non-Destructive Testing of Mechanical Properties of Solid Wood Panel Based on Partial Least Squares Structural Equation Modeling Transfer Method BioResources solid wood panel calibration transfer near infrared hyperspectral mechanical property |
title | Non-Destructive Testing of Mechanical Properties of Solid Wood Panel Based on Partial Least Squares Structural Equation Modeling Transfer Method |
title_full | Non-Destructive Testing of Mechanical Properties of Solid Wood Panel Based on Partial Least Squares Structural Equation Modeling Transfer Method |
title_fullStr | Non-Destructive Testing of Mechanical Properties of Solid Wood Panel Based on Partial Least Squares Structural Equation Modeling Transfer Method |
title_full_unstemmed | Non-Destructive Testing of Mechanical Properties of Solid Wood Panel Based on Partial Least Squares Structural Equation Modeling Transfer Method |
title_short | Non-Destructive Testing of Mechanical Properties of Solid Wood Panel Based on Partial Least Squares Structural Equation Modeling Transfer Method |
title_sort | non destructive testing of mechanical properties of solid wood panel based on partial least squares structural equation modeling transfer method |
topic | solid wood panel calibration transfer near infrared hyperspectral mechanical property |
url | https://ojs.cnr.ncsu.edu/index.php/BRJ/article/view/22315 |
work_keys_str_mv | AT dapengjiang nondestructivetestingofmechanicalpropertiesofsolidwoodpanelbasedonpartialleastsquaresstructuralequationmodelingtransfermethod AT yizhuozhang nondestructivetestingofmechanicalpropertiesofsolidwoodpanelbasedonpartialleastsquaresstructuralequationmodelingtransfermethod AT jinhaochen nondestructivetestingofmechanicalpropertiesofsolidwoodpanelbasedonpartialleastsquaresstructuralequationmodelingtransfermethod |