|
|
|
|
|
|
Surface Defects Detection of Solid Wood Board Using Near-Infrared Spectroscopy Based on Bayesian Neural Network |
LIANG Hao1, CAO Jun1, LIN Xue2, ZHANG Yi-zhuo1* |
1. Northeast Forestry University, College of Mechanical and Electrical Engineering, Harbin 150040, China
2. Northeast Forestry University, Material Science and Engineering College, Harbin 150040, China |
|
|
Abstract Surface defects of solid wood boards directly affect their mechanical properties and product grade, therefore, to achieve rapid detection of surface defects has important practical significance for online sort of solid wood boards. In view of the low recognition rate of the surface defect of the solid wood boards, a new method for the detection of 900~1 900 nm was proposed.by using a portable near infrared spectrometer First of all, the experiment collected absorption spectra of 180 samples with size of 200 mm×10 mm×10 mm, consisting of 60 samples with live knots, 60 samples with dead knots and 60 defect-free samples. Half of the samples were selected randomly as the training set, and the rest of samples were test set. Secondly, the the collecting NIR spectra of solid wood boards were preprocessed with Gaussian smoothing filter, piecewise multiplicative scatter correction and De-trending to reduce the spectral noise and eliminate the influence of the scattering spectrum; Afterwards, the improved genetic algorithm was utilized to select characteristic waves from the processed spectrum for building a model of defects recognition and classification; Finally, a model for recognizing and classifying the defects of solid wood boards was built through the improved neural network based on Bayesian neural network. The experiments used three types, containing live knots, dead knots and defects free, of solid wood board samples to train and test the model, the results showed that the model of based on Bayesian neural network was able to accurately identify three kinds of them, and the recognition rates were 92.20%, 94.47% and 95.57%, respectively. This study demonstrates that the type of solid wood boards surface defects with its near-infrared absorption spectra are closely related, and the article provides a rapid approach to achieve the accurate positioning of solid wood board defects which is as the next step.
|
Received: 2016-01-26
Accepted: 2016-04-21
|
|
Corresponding Authors:
ZHANG Yi-zhuo
E-mail: nefuzyz@163.com
|
|
[1] Ruz G A, Estevez P A, Ramirez P A. International Journal of Systems Science,2009, 40(2): 163.
[2] Satoru T, Kobori H. Journal of Wood Science, 2015, 61: 213.
[3] Alves A, Santos A, Rozenberg P, et al. Wood Science and Technology, 2012, 46: 157.
[4] Sundaram J, Mani S, Kandala C V K, et al. American Journal of Analytical Chemistry, 2015, 6:923.
[5] Rousset P, Davrieux F, Macedo L, et al. Biomass and Bioenergy, 2011, 35: 1219.
[6] Jones P D, Schimleck L R, Petter G F, et al. Wood Science and Technology, 2006, 40: 709.
[7] ZHANG Hui-juan, LI Yao-xiang, ZHANG Hong-fu, et al(张慧娟, 李耀翔, 张鸿富, 等). Journal of Northeast Forestry University(东北林业大学学报), 2011, 39(4): 83.
[8] LIU Ya-na, YANG Zhong, LÜ Bin, et al(刘亚娜, 杨 忠, 吕 斌, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(3): 648.
[9] LYT 2053—2012, Standard Method for Near Infrared Qualitative Analysis of Wood(木材的近红外光谱定性分析方法). Beijing: Standars Press of China(北京: 中国标准出版社), 2012.
[10] Lauret P, Fock E, Randrianarivony R N, et al. Energy Conversion and Management, 2008, 49(5): 1156.
[11] Lutsiva V P. Journal of Optical Technology, 2015, 82(8): 499. |
[1] |
WANG Wen-xiu, PENG Yan-kun*, FANG Xiao-qian, BU Xiao-pu. Characteristic Variables Optimization for TVB-N in Pork Based on Two-Dimensional Correlation Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(07): 2094-2100. |
[2] |
LE Ba Tuan1, 3, XIAO Dong1*, MAO Ya-chun2, SONG Liang2, HE Da-kuo1, LIU Shan-jun2. Coal Classification Based on Visible, Near-Infrared Spectroscopy and CNN-ELM Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(07): 2107-2112. |
[3] |
LIU Jin, LUAN Xiao-li*, LIU Fei. Near Infrared Spectroscopic Modelling of Sodium Content in Oil Sands Based on Lasso Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(07): 2274-2278. |
[4] |
YU Hui-ling1, MEN Hong-sheng2, LIANG Hao2, ZHANG Yi-zhuo2*. Near Infrared Spectroscopy Identification Method of Wood Surface Defects Based on SA-PBT-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(06): 1724-1728. |
[5] |
XU Wei-jie1, WU Zhong-chen1, 2*, ZHU Xiang-ping2, ZHANG Jiang1, LING Zong-cheng1, NI Yu-heng1, GUO Kai-chen1. Classification and Discrimination of Martian-Related Minerals Using Spectral Fusion Methods[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(06): 1926-1932. |
[6] |
LI Ying1, LI Yao-xiang1*, LI Wen-bin2, JIANG Li-chun3. Model Optimization of Wood Property and Quality Tracing Based on Wavelet Transform and NIR Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(05): 1384-1392. |
[7] |
DU Jian1, 2, HU Bing-liang1*, LIU Yong-zheng1, WEI Cui-yu1, ZHANG Geng1, TANG Xing-jia1. Study on Quality Identification of Macadamia nut Based on Convolutional Neural Networks and Spectral Features[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(05): 1514-1519. |
[8] |
HAN Guang, LIU Rong*, XU Ke-xin. Extraction of Effective Signal in Non-Invasive Blood Glucose Sensing with Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(05): 1599-1604. |
[9] |
WANG Li-shuang, ZHANG Wen-bo*, TONG Li. Studies on Dimensional Stability of Wood under Different Moisture Conditions by Near Infrared Spectroscopy Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(04): 1066-1069. |
[10] |
HUANG Hua1, WU Xi-yu2, ZHU Shi-ping1*. Feature Wavelength Selection and Efficiency Analysis for Paddy Moisture Content Prediction by Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(04): 1070-1075. |
[11] |
LI Hao-guang1,2, YU Yun-hua1,2, PANG Yan1, SHEN Xue-feng1,2. Study of Maize Haploid Identification Based on Oil Content Detection with Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(04): 1089-1094. |
[12] |
PENG Cheng1, FENG Xu-ping2*, HE Yong2, ZHANG Chu2, ZHAO Yi-ying2, XU Jun-feng1. Discrimination of Transgenic Maize Containing the Cry1Ab/Cry2Aj and G10evo Genes Using Near Infrared Spectroscopy (NIR)[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(04): 1095-1100. |
[13] |
XIA Ji-an1, YANG Yu-wang1*, CAO Hong-xin2, HAN Chen1, GE Dao-kuo2, ZHANG Wen-yu2. Classification of Broad Bean Pest of Visible-Near Infrared Spectroscopy Based on Cloud Computing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(03): 756-760. |
[14] |
MAO Ya-chun, WANG Dong, WANG Yue, LIU Shan-jun*. A FeO/TFe Determination Method of BIF Based on the Visible and Near-Infrared Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(03): 765-770. |
[15] |
LAI Tian-yue1, CAI Feng-huang1*, PENG Xin2*, CHAI Qin-qin1, LI Yu-rong1, 3, WANG Wu1, 3. Identification of Tetrastigma hemsleyanum from Different Places with FT-NIR Combined with Kernel Density Estimation Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(03): 794-799. |
|
|
|
|