基于降噪处理的蒙古栎木材气干密度NIRS定标模型

doi:10.3969/j.issn.1000-2006.2016.06.023

国家林草科技领军期刊
中国精品科技期刊
中国高校百佳科技期刊
江苏省新闻出版政府奖期刊奖
RCCSE林学权威期刊（A+）
CSCD核心期刊
Scopus数据库收录期刊
中文核心期刊
SCD核心期刊

作者加群：102861116

微信公众号：南京林业大学学报

高级检索

南京林业大学学报（自然科学版） ›› 2016, Vol. 59 ›› Issue (06): 148-156.doi: 10.3969/j.issn.1000-2006.2016.06.023

基于降噪处理的蒙古栎木材气干密度NIRS定标模型

李颖¹,李耀翔^1*,徐浩凯¹,姜立春²

1.东北林业大学工程技术学院,黑龙江哈尔滨 150040;
2.东北林业大学林学院,黑龙江哈尔滨 150040

出版日期:2016-12-18 发布日期:2016-12-18
基金资助:
基金项目:中央高校基本科研业务费专项资金项目(DL12EB07-2); 国家自然科学基金项目(31170591)
第一作者:李颖(864455702@qq.com)。
*通信作者:李耀翔(yaoxiangli@nefu.edu.cn),教授。
引文格式:李颖,李耀翔,徐浩凯,等. 基于降噪处理的蒙古栎木材气干密度NIRS定标模型[J]. 南京林业大学学报(自然科学版),2016,40(6):148-156.

Model calibrating for NIRS-based oak wood air-dry density prediction with denoising pretreatment

LI Ying¹, LI Yaoxiang^1*, XU Haokai¹, JIANG Lichun²

1.College of Engineering and Technology, Northeast Forestry University, Harbin 150040, China;
2. College of Forestry, Northeast Forestry University, Harbin 150040, China

Online:2016-12-18 Published:2016-12-18

摘要/Abstract

摘要： 分别采用卷积平滑法、小波变换法对蒙古栎木材近红外光谱(NIRS)做去噪处理,并讨论两者混合去噪时,处理顺序变化对光谱去噪效果的影响,最后应用偏最小二乘法(partial least squares regression,PLS)和主成分回归法建立蒙古栎木材气干密度近红外定标模型。结果表明,当平滑点数为3,db5小波分解层数为2时,以平滑+小波方式去噪效果最好,其信噪比(SNR)为18.546,均方根误差为0.04。平滑+小波去噪后,基于PLS的蒙古栎木材密度近红外校正模型决定系数由0.767提高到0.902,校正均方根误差降低了35.32%,预测集决定系数为0.860,内部交叉验证和预测均方根误差分别达到最低,剩余预测偏差为2.67。因此,近红外光谱技术可实现蒙古栎木材气干密度快速预测,合理选择处理参数和建模方法可以有效提高模型精度。

Abstract: Savitzky-Golay smoothing and wavelet transform were applied to the near infrared spectrum(NIRS)of oak(Quercus mongolica Fisch. ex Ledeb)wood for the noise elimination. Denoising effects were discussed by switching the pretreatment order of the two methods. Partial least squares regression(PLS)and principal component regression(PCR)were used for model development of oak wood air-dry density prediction. The results showed that the best denoising effects were associated with spectrum pretreatment of SG smoothing followed by wavelet transform with three smoothing points and two db5 wavelet decomposition layers. The signal to noise ratio(SNR)was 18.546 and the root mean square error of calibration was 0.04. For the calibration model of NIR-based oak wood air-dry density prediction developed with PLS, the determination coefficient(R²)was 0.902 for the calibration model with correct root mean square error reduced by 35.32% compared to the model developed with raw spectrum. R² for prediction was 0.860 with residual prediction deviation of 2.67. This study indicated that NIR could be used for rapid determination of oak wood air-dry density, and determination of reasonable processing parameters as well as modeling methods could effectively improve the model accuracy.

中图分类号:

S781.31

李颖,李耀翔,徐浩凯,等. 基于降噪处理的蒙古栎木材气干密度NIRS定标模型[J]. 南京林业大学学报（自然科学版）, 2016, 59(06): 148-156.

LI Ying, LI Yaoxiang, XU Haokai, JIANG Lichun. Model calibrating for NIRS-based oak wood air-dry density prediction with denoising pretreatment[J].Journal of Nanjing Forestry University (Natural Science Edition), 2016, 59(06): 148-156.DOI: 10.3969/j.issn.1000-2006.2016.06.023.

参考文献

[1] 叶华俊,刘立鹏,夏阿林,等. 在线近红外光谱分析仪的研制及应用[J]. 仪器仪表学报,2009,30(3):531-535. Ye H J, Liu L P, Xia A L, et al. Development and application of on-line near infrared spectroscopy analyzer[J]. Chinese Journal of Scientific Instrument, 2009, 30(3): 531-535.
[2] 宁井铭,宛晓春,张正竹,等. 近红外光谱技术结合人工神经网络判别普洱茶发酵程度[J]. 农业工程学报,2013,29(11):255-260. Ning J M, Wan X C, Zhang Z Z, et al. Discriminating fermentation degree of Pu'er tea based on NIR spectroscopy and artificial neural network[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(11): 255-260.
[3] 葛晓雯,王梦,李耀翔. 近红外技术在土壤化学组分预测中的应用研究综述[J]. 森林工程,2013,29(6):72-76. Ge X W, Wang M, Li Y X. Review on the NIR-based modeling of soil chemical constituents[J]. Forest Engineering, 2013, 29(6): 72-76.
[4] 李旭东,张根明. 近红外光谱分析技术的发展与应用研究[J]. 重庆科技学院学报(自然科学版),2008,10(2):33-35. Li X D, Zhang G M. The progress and application research of near infrared spectroscopy analytical technique[J]. Journal of Chongqing University of Science and Technology(Natural Science Edition), 2008, 10(2): 33-35.
[5] Chen H, Tan C, Wu T, et al. Discrimination between authentic and adulterated liquors by near-infrared spectroscopy and ensemble classification[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2014, 130: 245-249.
[6] 黄秀玲,郑加强,赵茂程. 水果分级支撑技术的研究进展[J]. 南京林业大学学报(自然科学版),2007,31(2):123-126.Doi:10.3969/j.issn.1000.2006.2007.02.028. Huang X L, Zheng J Q, Zhao M C. Review on fruit grading supporting technology[J]. Journal of Nanjing Forestry University(Natural Sciences Edition), 2007, 31(2): 123-126.
[7] Kainerstorfer J M, Sassaroli A, Hallacoglu B, et al. Practical steps for applying a new dynamic model to near-infrared spectroscopy measurements of hemodynamic oscillations and transient changes: implications for cerebrovascular and functional brain studies[J]. Academic Radiology, 2014, 21(2): 185-196.
[8] Raymond C A, Poke F S. Predicting extractives, lignin, and cellulose contents using near infrared spectroscopy on solid wood in Eucalyptus globulus[J]. Journal of Wood Chemistry and Technology, 2006, 26(2): 187-199.
[9] 刘镇波,孙凤亮,Wang X M,等. 基于近红外光谱法的人工林杨木木质素含量预测[J]. 南京林业大学学报(自然科学版),2013,37(6):121-126.Doi:10.3969/j.issn.1000-2006.2013.06.024. Liu Z B, Sun F L, Wang X M, et al. Prediction of lignin content of plantation poplar using near infrared spectroscopy method[J]. Journal of Nanjing Forestry University(Natural Sciences Edition), 2013, 37(6): 121-126.
[10] Rousset P, Davrieux F, Macedo L, et al. Characterisation of the torrefaction of beech wood using NIRS: combined effects of temperature and duration[J]. Biomass and Bioenergy, 2011, 35(3): 1219-1226.
[11] Inagaki T, Schwanninger M, Kato R, et al. Eucalyptus camaldulensis density and fiber length estimated by near-infrared spectroscopy[J]. Wood Science and Technology, 2012, 46(1-3): 143-155.
[12] Alves A, Santos A, Rozenberg P, et al. Common near infrared—based partial least squares regression model for the prediction of wood density of Pinus pinaster and Larix&#215;eurolepis[J]. Wood Science and Technology, 2012, 46(1-3): 157-175.
[13] 赵荣军,霍小梅,上官蔚蔚,等. 近红外光谱法预测粗皮桉木材气干密度的影响因素分析[J]. 光谱学与光谱分析,2011, 31(11):2948-2951. Zhao R J, Huo X M, Shangguan W W, et al. Influence factor for prediction of air-dry density of Eucalyptus Pellita by near infrared spectroscopy[J]. Spectroscopy and Spectral Analysis, 2011, 31(11): 2948-2951.
[14] 李耀翔,徐浩凯. 榆树木材基本密度近红外模型优化的研究[J]. 云南大学学报(自然科学版),2015,37(1):155-162. Li Y X, Xu H K.A study on the optimization of the model of NIR-based elm wood density [J]. Journal of Yunnan University(Natural Science Edition), 2015, 37(1): 155-162.
[15] 王学顺,戚大伟,黄安民. 基于小波模极大值的木材近红外光谱去噪[J]. 林业科学,2008,44(10):109-112. Wang X S, Qi D W, Huang A M,Denoising of near infrared spectroscopy in wood based on wavelet transform modules maximum[J]. Scientia Silvae Sinicae, 2008, 44(10): 109-112.
[16] 王学顺,戚大伟,黄安民. 木材近红外光谱小波阈值去噪方法[J]. 东北林业大学学报,2009,37(2):32-34. Wang X S, Qi D W, Huang A M. Threshold denoising of near infrared spectroscopy of wood based on wavelet transform[J]. Journal of Northeast Forestry University, 2009, 37(2): 32-34.
[17] 郝斯琪,宋博骐,李湃,等. 基于近红外光谱与 BP 神经网络预测落叶松木屑的含水率[J]. 森林工程,2012,28(4):9-11. Hao S Q, Song B Q, Li P, et al. Prediction of sawdust water content of Dahurian larch based on NIRS and BP neural network[J]. Forest Engineering, 2012, 28(4): 9-11.
[18] David C H. Technical Guide [Z]. Colorado: Analytical Spectral Devices, 1999.
[19] 葛哲学,沙威. 小波分析理论与MATLAB R2007实现[M]. 北京:电子工业出版社,2007:29-30.
[20] 曾九孙,刘祥官,罗世华,等. 主成分回归和偏最小二乘法在高炉冶炼中的应用[J].浙江大学学报(理学版),2009,36(1):33-36. Zeng J S, Liu X G, Luo S H,et al. Application of principal component regression and partial least square in blast furnace iron-making[J]. Journal of Zhejiang University(Science Edition), 2009, 36(1): 33-36.
[21] 邱素君,何雁,张国松,等. 近红外光谱快速测定柴胡总皂苷肠溶片包衣膜厚度研究[J]. 中国药学杂志,2013,48(24):2128-2133. Qiu S J, He Y, Zhang G S, et al. Fast determination of coating thickness of the total saponin of radix bupleuri enteric coated tablets by NIRS[J]. Chinese Pharmaceutical Journal, 2013, 48(24): 2128-2133.
[22] 张鹏. 基于小波变换的落叶松木材力学性质近红外模型研究[D]. 哈尔滨:东北林业大学,2014. Zhang P. Study of near infrared spectroscopy model for predicting mechanical properties of larch wood based on wavelet transform[D]. Harbin: Northeast Forestry University, 2014.
[23] 贺文明,薛崇昀,聂怡,等. 利用近红外光谱技术快速测定木材水分和气干密度的研究[J]. 中华纸业,2010,31(6):12-16. He W M, Xue C J, Nie Y, et al. The study of rapid prediction of moisture content and air-dried density of wood by using near infrared spectroscopy technology [J]. China Pulp & Paper Industry, 2010, 31(6): 12-16.
[24] 王玉荣,江泽慧,费本华,等. 近红外光谱预测棕榈藤藤条基本密度研究[J]. 光谱学与光谱分析,2008,28(10):119-120. Wang Y R, Jiang Z H, Fei B H, et al. Estimation of basic density of rattan canes by near infrared spectroscopy[J]. Spectroscopy and Spectral Analysis, 2008, 28(10):119-120.
[25] 林振兴,邬蓓蕾,王豪,等. PDS用于不同温度下的近红外光谱模型传递研究[J]. 分析测试学报,2008,27(12):1330-1333. Lin Z X, Wu B L, Wang H,et al. Study on near infrared spectroscopy model transfer by using piecewise direct standardization at different temperature[J]. Journal of Instrumental Analysis, 2008, 27(12): 1330-1333.
[26] 黄安民,费本华,江泽慧,等. 表面粗糙度对近红外光谱分析木材密度的影响[J]. 光谱学与光谱分析,2007,27(9):1700-1702. Huang A M, Fei B H, Jiang Z H,et al. Influence of sample surface roughness on mathematical model of NIR quantitative analysis of wood density[J]. Spectroscopy and Spectral Analysis, 2007, 27(9): 1700-1702.

基于降噪处理的蒙古栎木材气干密度NIRS定标模型

Model calibrating for NIRS-based oak wood air-dry density prediction with denoising pretreatment

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价

作者

读者

审稿