基于机器视觉的胶合性能测量技术研究进展

doi:10.11707/j.1001-7488.LYKX20230397

Abstract

Abstract:

Adhesives can make small-sized wood material unit into wood-based panels, plywood, and glued wood forms, which are used in engineering materials such as wood-frame buildings, load-bearing walls, decorative flooring, and bridges. The important basis for evaluating the gluing ability of adhesives is the gluing performance, which mainly includes the distribution of glue application, penetration ability, shear strength test, peeling test, wood breakage percentage measurement, and other indicators. With the popularization of machine vision technology, it has been applied as an important technique to assist in the evaluation of gluing performance. In order to have a more comprehensive understanding of the gluing performance measurement technology of machine vision, this paper outlines the image acquisition technology, image pre-processing technology, image segmentation technology, and calculation methods of machine vision technology on the basis of collecting domestic and foreign gluing performance measurement technology research literature. Secondly, it discusses the application of machine vision technology in the three aspects of adhesive sizing, adhesive permeability, and wood breakage percentage of glued surfaces. At the same time, the problem that machine vision technology can not segment digital image accurately, resulting in poor measurement accuracy is discussed. Finally, the optimization method of adhesive property measurement technology based on machine vision technology is summarized, and future research prospects are proposed: 1) to achieve accurate identification of adhesives and wood materials on adhesive joints, especially the identification of light-colored adhesives and substrates, especially the glue points and small wood units of particleboard and fiberboard; 2) Deeply explore the pixel-level unit characteristics of different measurement objects and the measurement mechanism of machine vision; 3) Research on scientific, sound and systematic evaluation mechanism based on machine vision technology; 4) Explore the influence mechanism of environmental factors such as illumination conditions, acquisition equipment and sample placement on image quality; 5) Establish a gluing performance evaluation database to provide data sources for deep learning or in-depth analysis of gluing performance.

Key words: adhesive, glue properties, machine vision, measurement

CLC Number:

TS653

Bin Yang,Jingxin Hao,Xianjun Li,Xinfeng Wu,Xinghua Wang. Research Progress of Machine Vision-Based Gluing Performance Measurement Technology[J]. Scientia Silvae Sinicae, 2024, 60(12): 177-190.

Figures/Tables 18

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Table 1

Table 2

Fig.7

Fig.8

Fig.9

Table 3

Table 4

Ocular measurements of WFP"

编号Number	参考文献References	基材Substrates	胶黏剂Adhesives
No. 1	陈国骏, 2021	云杉（温文杰等, 2022）-松-冷杉 Spruce-pine-fir (SPF) 定向结构刨花板 Construction oriented strand board (COSB)	水性高分子异氰酸酯 Emulsion polymer-isocyanate (EPI) 间苯二酚-甲醛树脂胶黏剂 Phenol resorcinol formaldehyde (PRF) 单组分聚氨酯 One-component polyurethane (PUR)
No.2	陆弘毅等，2021	杨木单板 Poplar Veneer	改性脲醛树脂(以聚乙烯亚胺和聚磷酸铵) Modified urea-formaldehyde resin(Polyethyleneimine(PEI); Ammonium polyphosphate(APP))
No.3	马苏等，2020	杨木木块（岳孔等, 2022） Poplar wood blocks	偏高岭土基地质聚合物木材胶黏剂(氢氧化钠\硅酸钠\苯丙乳液\KH-550 偶联剂) Kaolin base polymer wood adhesive (sodium hydroxide/sodium silicate/benzene emulsion/KH-550 coupling agent)
No.4	张希超, 2016	杨木单板 Poplar veneer	变性淀粉改性低毒脲醛树脂 low toxicity urea-formaldehyde resin modified by modified starch
No.5	岳孔等, 2015	速生杨木I-69 Fast-growing poplar	聚乙烯Polyethylene(PE) 聚丙烯Polypropylene(PP) 塑料合金片材Plastic alloy sheet
No.6	聂亚楠等, 2012	杨木径切单板 Poplar diameter-cut veneer	玉米淀粉胶黏剂Corn starch adhesive
No.7	任一萍等, 2012	枹栎 Quercus serrata	苯酚98%、甲醛含量37%、间苯二酚99%、氢氧化钠Phenol 98%, formaldehyde content 37%, resorcinol 99%, sodium hydroxide
No.8	卢克阳等, 2011	落叶松单板 Larch veneer	30-910环保型胶合板用低毒脲醛胶 30-910 Environmentally friendly low toxicity urea-formaldehyde glue for plywood
No.9	金淘, 2010	杨木单板 Poplar veneer	非木材植物碎料/粉末材料 Non-wood plant chips/powdered materials
No.10	胡飚, 2009	竹丝成型材/杨木单板 Reorganized bamboo/ poplar veneer	PUF共缩聚树脂PUF(phenol-modified urea-formaldehyde resin) co-condensation resin
No.11	叶克林, 1989	水曲柳（王思文等, 2019）、椴木（徐华东等, 2014）、柳桉（丘进清, 2007） Ash, basswood, willow	脲醛树脂Urea-formaldehyde resin(UF)

Table 4

Fig.10

Fig.11

Fig.12

Table 5

Fig.13

References 0

	边明明, 殷亚方, 宋坤霖, 等. 不同压缩加载速度对杉木微观结构和力学性能影响. 建筑材料学报, 2012, 15 (4): 575- 580. doi: 10.3969/j.issn.1007-9629.2012.04.028
	Bian M M, Yin Y F, Song K L, et al. Effect of loading rate on microstructure characteristics and mechanical properties of Chinese fir. Journal of Building Materials, 2012, 15 (4): 575- 580. doi: 10.3969/j.issn.1007-9629.2012.04.028
	陈兵兵. 2022. 金属离子与染料对大豆胶黏剂性能的影响与作用机制研究. 哈尔滨: 东北林业大学.
	Chen B B. 2023. Effects of metal ions and dyes on the propertiesof soybean adhesive and its interaction mechanism. Harbin: Northeast Forestry University. ［in Chinese］
	陈国骏. 2021. SPF/COSB混合结构正交胶合木尺寸稳定性和胶合性能研究. 南京: 南京林业大学.
	Chen G J. 2021. The bonding performance and dimensional stability of hybrid CLT fabricated with lumber and COSB. Nanjing: Nanjing Forestry University. ［in Chinese］
	陈　晓, 何发智, 潘一腾, 等. 基于纹理分布弱假设和正则化策略的自然图像抠图. 计算机辅助设计与图形学学报, 2016, 28 (10): 1672- 1678. doi: 10.3969/j.issn.1003-9775.2016.10.008
	Chen X, He F Z, Pan Y T, et al. Natural image matting based on weak assumptions and regularization strategy. Journal of Computer-Aided Design & Computer Graphics, 2016, 28 (10): 1672- 1678. doi: 10.3969/j.issn.1003-9775.2016.10.008
	董惟群. 2019. 竹木复合正交胶合木胶合工艺及力学性能评价. 南京: 南京林业大学.
	Dong W Q. 2019. Evaluation of bonding technology and mechanical properties of bamboo-wood composite cross-laminated timber. Nanjing: Nanjing Forestry University. ［in Chinese］
	范英琪, 李玉梅, 张　涛, 等. 基于机器视觉的井喷液柱高度测量方法研究. 激光杂志, 2023, 44 (1): 22- 26.
	Fan Y Q, Li Y M, Zhang T, et al. Research on the height measurement method of blowout liquid column based on machine vision. Laser Journal, 2023, 44 (1): 22- 26.
	高　帅, 刘永华, 高菊玲, 等. 基于YOLOv3算法与3D视觉的农业采摘机器人目标识别与定位研究. 中国农机化学报, 2022, 43 (12): 178- 183.
	Gao S, Liu Y H, Gao J L, et al. Research on target recognition and localization of agricultural picking robot based on YOLOv3 algorithm and 3D vision. Journal of Chinese Agricultural Mechanization, 2022, 43 (12): 178- 183.
	关明杰, 雍　宬, 赵　佳. 竹材/酚醛树脂胶合界面的荧光跟踪定位表征. 西南大学学报(自然科学版), 2012, 34 (9): 118- 122.
	Guan M J, Yong C, Zhao J. Fluorescent tracking characterization of glue interface between bamboo and phenol formaldehyde resin. Journal of Southwest University (Natural Science Edition), 2012, 34 (9): 118- 122.
	管雪梅, 郭明辉. 解剖构造对人工林樟子松单板染色效果的影响. 东北林业大学学报, 2012, 40 (8): 82- 85, 104. doi: 10.3969/j.issn.1000-5382.2012.08.019
	Guan X M, Guo M H. Influence of anatomical characteristics on dyeing effects of veneer from Pinus sylvestris var. mongolica plantations. Journal of Northeast Forestry University, 2012, 40 (8): 82- 85, 104. doi: 10.3969/j.issn.1000-5382.2012.08.019
	韩文霆, 张立元, 牛亚晓, 等. 无人机遥感技术在精量灌溉中应用的研究进展. 农业机械学报, 2020, 51 (2): 1- 14. doi: 10.6041/j.issn.1000-1298.2020.02.001
	Han W T, Zhang L Y, Niu Y X, et al. Review on UAV remote sensing application in precision irrigation. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51 (2): 1- 14. doi: 10.6041/j.issn.1000-1298.2020.02.001
	贺建民, 路　伟, 王立峰, 等. 碳纤维增强面板的制备及其力学性能. 森林工程, 2022, 38 (3): 63- 69, 76.
	He J M, Lu W, Wang L F, et al. Preparation and mechanical properties of carbon fiber reinforced panel. Forest Engineering, 2022, 38 (3): 63- 69, 76.
	何　拓, 刘守佳, 陆　杨, 等. iWood: 基于卷积神经网络的濒危珍贵树种木材自动识别系统. 林业科学, 2021, 57 (9): 152- 159. doi: 10.11707/j.1001-7488.20210915
	He T, Liu S J, Lu Y, et al. iWood: an automated wood identification system for endangered and precious tree species using convolutional neural networks. Scientia Silvae Sinicae, 2021, 57 (9): 152- 159. doi: 10.11707/j.1001-7488.20210915
	胡　飚. 2009. PUF共缩聚树脂的合成及其性能研究. 杭州: 浙江林学院.
	Hu B. 2009. Study on synthesis and properties of co-codensated PUF resin. Hangzhou: Zhejiang Forestry University. ［in Chinese］
	胡峻峰. 2008. 基于数字图像处理的人造板施胶效果分析. 哈尔滨: 东北林业大学.
	Hu J F. 2008. Analysis on the sizing efficiency of particle board based on digital image processing. Harbin: Northeast Forestry University. ［in Chinese］
	胡小霞, 陈　鹏, 徐正东, 等. 木材破坏率的影响因素及测定方法初探. 木材加工机械, 2011, (4): 15- 18, 46. doi: 10.3969/j.issn.1001-036X.2011.04.004
	Hu X X, Chen P, Xu Z D, et al. The influencing factors and measuring method of the rate of wood failure. Wood Processing Machinery, 2011, (4): 15- 18, 46. doi: 10.3969/j.issn.1001-036X.2011.04.004
	金　淘. 2010. 非木材植物碎料/粉末自胶合性能的研究. 长沙: 中南林业科技大学.
	Jin T. 2010. Study on the self-bonding property of non-wood plant-based particles/prowders. Changsha: Central South University of Forestry and Technology. ［in Chinese］
	寇素霞. 高性能预应力胶合木张弦梁长期受弯蠕变模型研究. 森林工程, 2023, 39 (1): 101- 106.
	Kou S X. Study on the bending creep model of prestressed glulam string beam. Forest Engineering, 2023, 39 (1): 101- 106.
	刘　波, 邬瑞东, 卢　芸, 等. 紫檀属木材荧光性能种间差异和心边材差异. 木材工业, 2019, 33 (3): 14- 17, 61.
	Liu B, Wu R D, Lu Y, et al. Interspecies differences and differences between heartwood and sapwood in wood fluorescence properties of Pterocarpus species. China Wood Industry, 2019, 33 (3): 14- 17, 61.
	陆弘毅, 张　隐, 张　帅, 等. PEI/APP改性脲醛树脂制备阻燃胶合板及性能. 林业工程学报, 2021, 6 (1): 44- 49.
	Lu H Y, Zhang Y, Zhang S, et al. Preparation of flame-retardant plywood by PEI/APP modified urea-formaldehyde resin and its properties. Journal of Forestry Engineering, 2021, 6 (1): 44- 49.
	卢克阳, 傅　峰, 蔡智勇, 等. 导电膜片叠层型电磁屏蔽胶合板的性能研究. 建筑材料学报, 2011, 14 (2): 207- 211, 233. doi: 10.3969/j.issn.1007-9629.2011.02.012
	Lu K Y, Fu F, Cai Z Y, et al. Study of porperties of electromagnetic shielding plywood laminated with conductive sheets. Journal of Building Materials, 2011, 14 (2): 207- 211, 233. doi: 10.3969/j.issn.1007-9629.2011.02.012
	马飞虎, 曾　聪, 金依辰, 等. 一种基于属性加权朴素贝叶斯算法的OTSU图像分割方法. 应用科学学报, 2022, 40 (2): 224- 232. doi: 10.3969/j.issn.0255-8297.2022.02.005
	Ma F H, Zeng C, Jin Y C, et al. An OTSU image segmentation method based on attribute weighted naive Bayesian algorithm. Journal of Applied Sciences, 2022, 40 (2): 224- 232. doi: 10.3969/j.issn.0255-8297.2022.02.005
	马红霞. 2009. 毛竹/杨木复合材料界面胶合性能及其影响因素研究. 北京: 中国林业科学研究院.
	Ma H X. 2009. Interface gullibility and its affecting factors of bamboo/poplar composite. Beijing: Chinese Academy of Forestry. ［in Chinese］
	马　苏, 甄　晋, 汪珈羽, 等. 苯丙乳液掺杂对地质聚合物木材胶黏剂性能的影响. 北京林业大学学报, 2020, 42 (7): 131- 139. doi: 10.12171/j.1000-1522.20200019
	Ma S, Zhen J, Wang J Y, et al. Effects of styrene-acrylic emulsion doping on the properties of geopolymer wood adhesives. Journal of Beijing Forestry University, 2020, 42 (7): 131- 139. doi: 10.12171/j.1000-1522.20200019
	聂亚楠, 田孝才, 吴　凯, 等. 玉米淀粉胶粘剂的增强及耐水改性研究. 中国胶粘剂, 2012, 21 (11): 15- 18.
	Nie Y N, Tian X C, Wu K, et al. Study on modified corn starch adhesive in reinforcing and water-resistance. China Adhesives, 2012, 21 (11): 15- 18.
	庞晓娜, 杨　祥, 李贤军, 等. 碱蚀改善毛竹条孔隙及染液渗透性研究. 林业工程学报, 2021, 6 (6): 44- 50.
	Pang X N, Yang X, Li X J, et al. Improvement of porosity and dye permeability of moso bamboo splints by alkali etching. Journal of Forestry Engineering, 2021, 6 (6): 44- 50.
	秦理哲. 2014. 柳杉木材胶合与胶合界面表征. 南宁: 广西大学.
	Qin L Z. 2014. Study on bonding technology of cryptomeria fortunel hooibenk and the characterization of glue-wood interface. Nanning: Guangxi University. ［in Chinese］
	秦理哲. 2017. 木材胶合界面的微纳结构对其力学性能的影响机制. 北京: 中国林业科学研究院.
	Qin L Z. 2017. Influencing mechanism of micro- and nano- structure of wood bonding interphase on interfacial mechanical properties. Beijing: Chinses Academy of Forestry ［in Chinese］
	丘进清. 闽北柳桉种源/家系的试验研究. 中南林业科技大学学报, 2007, 27 (3): 33- 36. doi: 10.3969/j.issn.1673-923X.2007.03.008
	Qiu J Q. Provenance-family trial of Eucalyptus saligna in northern Fujian. Journal of Central South University of Forestry & Technology, 2007, 27 (3): 33- 36. doi: 10.3969/j.issn.1673-923X.2007.03.008
	任一萍, 王　正, 常　亮. 低间苯二酚含量树脂的研制. 木材加工机械, 2012, (3): 22- 25. doi: 10.3969/j.issn.1001-036X.2012.03.009
	Ren Y P, Wang Z, Chang L. Research of low-resorcinol-content PRF. Wood Processing Machinery, 2012, (3): 22- 25. doi: 10.3969/j.issn.1001-036X.2012.03.009
	沈　亮. 2019. 复杂天气条件下水天场景图像增强技术研究. 武汉: 华中科技大学.
	Shen L. 2019. A thesis submitted in partial fulfillment of the requirements for the degree for the master of engineering. Wuhan: Huazhong University of Science & Technology. ［in Chinese］
	宿恒硕, 吕　军, 丁志平, 等. 基于改进残差神经网络的木材识别算法. 林业科学, 2021, 57 (12): 147- 154.
	Su H S, Lü J, Ding Z P, et al. Wood identification algorithm based on improved residual neural network. Scientia Silvae Sinicae, 2021, 57 (12): 147- 154.
	王　洁, 沈　洋, 包艳霞, 等. 最小移动二乘抠图. 电视技术, 2015, 39 (19): 24- 27, 31.
	Wang J, Shen Y, Bao Y X, et al. Moving least square matting. Video Engineering, 2015, 39 (19): 24- 27, 31.
	王思文, 卫　星, 李虹谕, 等. 水曲柳轻基质容器苗菌根化生长效应. 林业科学, 2019, 55 (2): 173- 181. doi: 10.11707/j.1001-7488.20190218
	Wang S W, Wei X, Li H Y, et al. Effect of mycorrhizae on the growth of Fraxinus mandshurica container seedlings in light culture media. Scientia Silvae Sinicae, 2019, 55 (2): 173- 181. doi: 10.11707/j.1001-7488.20190218
	王志军, 肖欢畅, 吴　简. 高速成像拖尾畸变校正方法研究. 激光杂志, 2020, 41 (5): 91- 95.
	Wang Z J, Xiao H C, Wu J. The study of tailing distortion correction method for high-speed imaging. Laser Journal, 2020, 41 (5): 91- 95.
	温文杰, 王冬梅. 青海黄土高寒区4种典型人工林树木叶片碳氮磷含量及化学计量特征. 林业科学, 2022, 58 (1): 22- 31. doi: 10.11707/j.1001-7488.20220103
	Wen W J, Wang D M. Content and stoichiometric characteristics of carbon, nitrogen, and phosphorus in leaves of four typical plantation species in the alpine zone of the Loess Plateau in Qinghai. Scientia Silvae Sinicae, 2022, 58 (1): 22- 31. doi: 10.11707/j.1001-7488.20220103
	夏　雪, 多化琼, 丁安宁, 等. 机器视觉在单板缺陷检测中的应用. 世界林业研究, 2022, 35 (6): 69- 74.
	Xia X, Duo H Q, Ding A N, et al. Application of machine vision to veneer defect detection. World Forestry Research, 2022, 35 (6): 69- 74.
	徐华东, 王立海, 宋世全. 原木内部孔洞缺陷二维超声图像构建. 林业科学, 2014, 50 (8): 126- 130.
	Xu H D, Wang L H, Song S Q. Two dimensional image construction of ultrasonic wave for detecting internal hole defect in log. Scientia Silyae Sinicae, 2014, 50 (8): 126- 130.
	许金山, 李　松, 帅永辉, 等. 一种基于计算机控制的抛物面型聚光系统的自动调校方法. 太阳能学报, 2017, 38 (7): 1741- 1748.
	Xu J S, Li S, Shuai Y H, et al. A computer-based parabolic dish concentrator alignment method. Acta Energiae Solaris Sinica, 2017, 38 (7): 1741- 1748.
	杨　滨, 郝景新, 刘拓宇, 等. 基于Matlab图像处理的CLT木破率测量方法. 西北林学院学报, 2023a, 38 (1): 199- 204.
	Yang B, Hao J X, Liu T Y, et al. Method of measuring wood failure percentage based on Matlab image processing. Journal of Northwest Forestry University, 2023a, 38 (1): 199- 204.
	杨　滨, 郝景新, 刘拓宇, 等. 基于灰度与彩色图像处理的木破率测量法. 建筑材料学报, 2023b, 26 (3): 289- 298.
	Yang B, Hao J X, Liu T Y, et al. Wood failure percentage measurement method based on grayscale and color image processing. Journal of Building Materials, 2023b, 26 (3): 289- 298.
	杨　滨. 2023. 基于机器视觉的集成材胶合面木破率数字图像测量技术研究. 长沙: 中南林业科技大学.
	Yang B. 2023. Research on digital images measurement technology of wood failure percentage of glued laminated timber adhesive bonded joints based on machine vision. Changsha: Central South University of Forestry and Technology. ［in Chinese］
	杨　军, 王连甲. 结合位置关系卷积与深度残差网络的三维点云识别与分割. 西安交通大学学报, 2023, 57 (5): 182- 193.
	Yang J, Wang L J. Recognition and segmentation of 3D point cloud through positional relation convolution in combination with deep residual network. Journal of Xi’an Jiaotong University, 2023, 57 (5): 182- 193.
	杨建华, 闫　磊, 于　航, 等. 基于表面主要缺陷的锯材外观质量量化评价方法. 林业科学, 2019, 55 (8): 128- 135. doi: 10.11707/j.1001-7488.20190814
	Yang J H, Yan L, Yu H, et al. Quantitative evaluation method for the appearance quality of sawn timber based on main surface defects. Scientia Silvae Sinicae, 2019, 55 (8): 128- 135. doi: 10.11707/j.1001-7488.20190814
	杨思瑞, 柳金章, 张云奎, 等. 蓝变杨木重组木尺寸稳定性及胶合界面微观表征. 中南林业科技大学学报, 2018, 38 (12): 136- 141.
	Yang S R, Liu J Z, Zhang Y K, et al. Study on dimensional stability and microscopic characterization of bonding interface of blue-stained poplar scrimber. Journal of Central South University of Forestry & Technology, 2018, 38 (12): 136- 141.
	阳　伟, 甘　涛, 兰　刚. 基于纹理聚类的抠图算法. 计算机应用, 2013, 33 (11): 3213- 3216. doi: 10.3724/SP.J.1087.2013.03213
	Yang W, Gan T, Lan G. Texture clustering matting algorithm. Journal of Computer Applications, 2013, 33 (11): 3213- 3216. doi: 10.3724/SP.J.1087.2013.03213
	叶克林. 胶合板胶合强度与厚度结构关系的研究. 木材工业, 1989, 3 (3): 13- 19.
	Ye K L. A study on the reiationship between the tensile strength and the thickness structure in plywood. China Wood Industry, 1989, 3 (3): 13- 19.
	岳　孔, 程秀才, 夏　蛟, 等. 木塑层合板的制备工艺及抗弯性能. 农业工程学报, 2015, 31 (22): 301- 307. doi: 10.11975/j.issn.1002-6819.2015.22.041
	Yue K, Cheng X C, Xia J, et al. Processing and bending behavior of wood-plastic laminated timber. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31 (22): 301- 307. doi: 10.11975/j.issn.1002-6819.2015.22.041
	岳　孔, 陆　栋, 胡文杰, 等. 高温中木材顺纹弦面抗剪强度. 林业科学, 2022, 58 (1): 111- 118. doi: 10.11707/j.1001-7488.20220112
	Yue K, Lu D, Hu W J, et al. Parallel-to-grain tangential shear strength of wood at elevated temperatures under oxygen-free conditions. Scientia Silvae Sinicae, 2022, 58 (1): 111- 118. doi: 10.11707/j.1001-7488.20220112
	张希超. 2016. 变性淀粉改性低毒脲醛树脂的制备及性能研究. 哈尔滨: 东北林业大学.
	Zhang X C. 2016. Performance and preparation of low toxicity urea-formaldehyde resin modified by modified starch. Harbin: Northeast Forestry University. ［in Chinese］
	张　颖. 2010. 胶黏剂在单板上的分布与胶合强度关系的研究. 北京: 北京林业大学.
	Zhang Y. 2010. The research about the relationship between distribution of adhesive on veneer and the bonding strength. Beijing: Beijing Forestry University. ［in Chinese］
	赵明华, 程丹妮, 都双丽, 等. 改进融合策略下透明度引导的逆光图像增强. 中国图象图形学报, 2022, 27 (5): 1554- 1564. doi: 10.11834/jig.210739
	Zhao M H, Cheng D N, Du S L, et al. An improved fusion strategy based on transparency-guided backlit image enhancement. Journal of Image and Graphics, 2022, 27 (5): 1554- 1564. doi: 10.11834/jig.210739
	赵子宇, 杨霄霞, 郭　慧, 等. 基于卷积神经网络模型的木材宏、微观辨识方法. 林业科学, 2021, 57 (6): 134- 143. doi: 10.11707/j.1001-7488.20210615
	Zhao Z Y, Yang X X, Guo H, et al. Recognition method of wood macro-and micro-structure based on convolution neural network. Scientia Silvae Sinicae, 2021, 57 (6): 134- 143. doi: 10.11707/j.1001-7488.20210615
	周海宾, 刘晓娜, 韩刘杨, 等. 胶黏剂和指接接头对胶合木性能的影响. 建筑材料学报, 2017, 20 (5): 752- 757. doi: 10.3969/j.issn.1007-9629.2017.05.016
	Zhou H B, Liu X N, Han L Y, et al. Influence of adhesive type and finger joint on properties of glulam. Journal of Building Materials, 2017, 20 (5): 752- 757. doi: 10.3969/j.issn.1007-9629.2017.05.016
	周海宾, 孙华林, 张俊珍, 等. 结构用胶合木性能若干影响因素. 建筑材料学报, 2014, 17 (3): 553- 558. doi: 10.3969/j.issn.1007-9629.2014.03.033
	Zhou H B, Sun H L, Zhang J Z, et al. Factors influencing strength properties of structural glulam. Journal of Building Materials, 2014, 17 (3): 553- 558. doi: 10.3969/j.issn.1007-9629.2014.03.033
	Abrahão C P, Alves V C A, Carvalho P F D A D, et al. Quantificação da falha na madeira em juntas coladas utilizando técnicas de visão artificial. Revista Á rvore, 2003, 27 (1): 71- 78.
	Alade A A, Naghizadeh Z, Wessels C B. A new method for estimating wood failure percentage in adhesive-bonded shear specimens. International Journal of Adhesion and Adhesives, 2022, 112, 103028. doi: 10.1016/j.ijadhadh.2021.103028
	Bejtka I. 2011. Cross (CLT) and diagonal (DTL) laminated timber as innovative material for beam elements. KIT Scientific Publishing.
	Betti M, Brunetti M, Lauriola M P, et al. Comparison of newly proposed test methods to evaluate the bonding quality of cross-laminated timber (CLT) panels by means of experimental data and finite element (FE) analysis. Construction and Building Materials, 2016, 125, 952- 963. doi: 10.1016/j.conbuildmat.2016.08.113
	Dugmore M, Nocetti M, Brunetti M, et al. Bonding quality of cross-laminated timber: Evaluation of test methods on Eucalyptus grandis panels. Construction and Building Materials, 2019, 211, 217- 227. doi: 10.1016/j.conbuildmat.2019.03.240
	Gagnon S, Pirvnu C. 2011. CLT handbook: cross-laminated timber. Canada: FPInnovations.
	Han Y, Park Y, Chang Y S, et al. Improvement of shear strength, wood failure percentage and wet delamination of cross-laminated timber (CLT) panels made with superheated steam treated (SHST) layers of larch wood. Holzforschung, 2017, 71 (11): 873- 879. doi: 10.1515/hf-2017-0008
	Kariz M, Sernek M. Determination of the percentage of wood failure by 3D scanning of the adhesive bondline. European Journal of Wood and Wood Products, 2014, 72 (4): 551- 553. doi: 10.1007/s00107-014-0806-8
	Kläusler O, Hass P, Amen C, et al. Improvement of tensile shear strength and wood failure percentage of 1C PUR bonded wooden joints at wet stage by means of DMF priming. European Journal of Wood and Wood Products, 2014, 72 (3): 343- 354. doi: 10.1007/s00107-014-0786-8
	Knorz M, Torno S, van de Kuilen J W. Bonding quality of industrially produced cross-laminated timber (CLT) as determined in delamination tests. Construction and Building Materials, 2017, 133, 219- 225. doi: 10.1016/j.conbuildmat.2016.12.057
	Künniger T. 2007. Automatische Bestimmung des prozentualen Faserbruchanteils bei der industriellen Klebfestigkeitsprüfung. Empa Materials Science and Technology.
	Künniger T. A semi-automatic method to determine the wood failure percentage on shear test specimens. Holz Als Roh- und Werkstoff, 2008, 66 (3): 229- 232. doi: 10.1007/s00107-008-0236-6
	Li M Y, Zhang S B, Gong Y C, et al. Gluing techniques on bond performance and mechanical properties of cross-laminated timber (CLT) made from Larix kaempferi. Polymers, 2021, 13 (5): 733- 741. doi: 10.3390/polym13050733
	Lin L Y, He S, Fu F, et al. Detection of wood failure by image processing method: influence of algorithm, adhesive and wood species. European Journal of Wood and Wood Products, 2015, 73 (4): 485- 491. doi: 10.1007/s00107-015-0907-z
	Mihulja G, Bogner A, Banči D. A new method for the determination of the proportion of wood failure area on the glue bond. Drvna Industrija, 2008, 58 (4): 193.
	Miller D G, Tardif Y, Bergin E G. Video wood-failure evaluator. Forest Products Journal, 1973, 23 (4): 21- 26.
	Nguyen N, Ozarska B, Fergusson M, et al. Comparison of two dye uptake measurement methods for dyed wood veneer assessment. European Journal of Wood and Wood Products, 2018, 76 (6): 1757- 1759. doi: 10.1007/s00107-018-1344-6
	Oliveira R F, Lopes D J V, Entsminger E D. 2022. Automated means for assessing wood failure. Proceedings of the American Wood Protection Association 118 Annual Meeting May, Charleston, South Carolina, USA, 47–52.
	Qin L Z, Lin L Y, Fu F. Microstructural and micromechanical characterization of modified urea-formaldehyde resin penetration into wood. BioResources, 2015, 11 (1): 182- 194.
	Rosenfield K. 2012. The case for tall wood buildings. Creative Commons, 1−240.
	Santos P, Correia J R, Godinho L, et al. Bonding quality assessment of cross-layered Maritime pine elements glued with one-component polyurethane adhesive. Construction and Building Materials, 2019, 211, 571- 582. doi: 10.1016/j.conbuildmat.2019.03.064
	Scott C T, Hernández R, Frihart C, et al. Method for quantifying percentage wood failure in block-shear specimens by a laser scanning profilometer. Journal of ASTM International, 2005, 2 (8): 1- 10.
	Steiger R, Gülzow A, Czaderski C, et al. Comparison of bending stiffness of cross-laminated solid timber derived by modal analysis of full panels and by bending tests of strip-shaped specimens. European Journal of Wood and Wood Products, 2012, 70 (1): 141- 153.
	Tannert T, Vallée T, Müller A. Critical review on the assessment of glulam structures using shear core samples. Journal of Civil Structural Health Monitoring, 2012, 2 (1): 65- 72. doi: 10.1007/s13349-012-0016-1
	Tao J Q, Gong H T, Wang F, et al. Deep learning based automated segmentation of air-void system in hardened concrete surface using three dimensional reconstructed images. Construction and Building Materials, 2022, 324, 126717. doi: 10.1016/j.conbuildmat.2022.126717
	Yang B, Hao J X, Li X J, et al. Dyeing adhesives as binders in wood/bamboo biocomposites for improve the measurement accuracy of wood failure percentage by machine vision technology. Industrial Crops and Products, 2024, 221, 119250. doi: 10.1016/j.indcrop.2024.119250
	Yang B, Wu X F, Hao J X, et al. Deep learning methods for wood composites failure predication. Polymers, 2023a, 15 (2): 295. doi: 10.3390/polym15020295
	Yang B, Wu X F, Hao J X, et al. Estimation of wood failure percentage under shear stress in bamboo-wood composite bonded by adhesive using a deep learning and entropy weight method. Industrial Crops and Products, 2023b, 197, 116617. doi: 10.1016/j.indcrop.2023.116617
	Yang Y, Gong M, Chui Y H. A new image analysis algorithm for calculating percentage wood failure. Holzforschung, 2008, 62 (2): 248- 251. doi: 10.1515/HF.2008.041
	Yusoh A S, Tahir P M, Uyup M K A, et al. Effect of wood species, clamping pressure and glue spread rate on the bonding properties of cross-laminated timber (CLT) manufactured from tropical hardwoods. Construction and Building Materials, 2021, 273, 121721. doi: 10.1016/j.conbuildmat.2020.121721
	Zhang Z. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22 (11): 1330- 1334. doi: 10.1109/34.888718
	Zink A G, Kartunova E. Wood failure in plywood shear samples measured with image analysis. Forest Products Journal, 1998, 48 (4): 69- 74.

图像分割 Image segmentation	学习方式 Learning styles	分割依据 Basis for segmentation	分类模型 Partition model	模型特点 Model features	参考文献 Reference
阈值分割 Threshold segmentation		阈值 Threshold	大津算法Otsu	自适应阈值Adaptive thresholds	杨滨等，2023b
			迭代法Iterative method	迭代法阈值Iteration threshold	Abrah?o et al., 2003
			贝叶斯算法Bayesian	直方图双峰法Histogram bimodal method	Abrah?o et al., 2003
边缘检测 Edge detection		边缘 Edge	Roberts	局部差分算子local difference operator (LDO)	胡峻峰，2008
			Prewitt	一阶微分算子（平均波数） First-order differential operator (average wavenumber)
			Sobel	一阶微分算子（加权平均波数）First-order differential operator (weighted average wavenumber)
			Laplacian	像素值差分法Pixel value difference method
			Canny	多级检测算法Multi-level detection algorithms
			LoG	二阶导数算子Second-order derivative operator (math.)
			Laplace	二阶微分线性算子 Second-order differential linear operator
聚类算法 Clustering algorithms	无监督学习 Unsupervised learning	聚类 Clustering	K-means	像素点之间的距离、相似性 Distance between pixel points, similarity	Lin et al., 2015

图像分割 Image segmentation	学习方式 Learning styles	模型 Model	扩大感受野的形式 Expanded forms of receptive field	全卷积语义分割模型 Fully convolutional semantic segmentation model
深度学习 Machine learning	监督学习 Supervised learning	UNet FCN SegNet	最大池化（提取纹理信息） Maximum pooling （extract texture information）	基于全卷积的对称网络语义分割模型 Full convolution-based semantic segmentation model for symmetric networks
		PSPNet	平均池化（保留背景信息） Average pooling (background information preserved)	基于全卷积的残差网络语义分割模型 Full convolution-based semantic segmentation model for residual networks
		DeepLabRefineNet	空洞卷积（捕获多尺度上下文信息） Dilated convolution (capturing background information at multiple scales)	基于全卷积的扩张卷积语义分割模型 Full convolution-based semantic segmentation model for dilation convolution

国家Country	标准Standard	参考标准Reference standards
中国China	LY/T 2720—2016	GB/T 18259—2018; GB/T 50329—2012; GBJ 5—88; GB/T 26899—2011
美国America	ASTM D5266.2003	ASTM D905.2021; ASTM D906.2003; ASTM D2559.2003; ASTM D4688.2003; ASTM D5572.2003; ASTM D5751.2003; ANSIHPVA HP-1-2009.2003; ANSI A190.1-2012.2003
欧洲Europe	BS EN 386.2001	BS EN 301.1992; BS EN 385.2001; BS EN 391.2001; BS EN 392.1995; prEN 14081-1:2000.2003; prEN14081-2:2000.2003; prEN14081-3:2000.2003

参考文献 reference	胶黏剂 Adhesives	被黏接物 Bonded material	染色剂 Staining reagents	染色效果展示 Dyeing effect show
Künniger et al., 2007	PUR热熔胶 Polyurethane reactive	云杉 Picea asperata	碘化钾/硫代硫酸钠 Potassium iodide/ Sodium thiosulfate
Santos et al., 2019	单组份聚氨酯 One-component polyurethane	海松、澳大利亚黑木 Pinus koraiensis, Acacia melanoxylon	间苯三酚无水溶液盐酸溶液 Benzenethiol anhydrous solution hydrochloric acid solution
Künniger et al., 2008	三聚氰胺-尿素甲醛/三聚氰胺-甲醛Melamine-urea formaldehyde/melamine formaldehyde	云杉 Picea asperata	通用染色剂 Universal stain
Künniger et al., 2007	RPF (Resorcinol-phenol- formaldehyde resin)	落叶松 Larix gmelinii	孔雀石绿 Malachite green
Mihulja et al., 2008	聚氨酯 Polyurethane	山毛榉 Fagus longipetiolata	红花红色素 Carthamin
杨思瑞等，2018.	酚醛树脂 Phenol-formaldehyde resin	意大利杨 Populus euramevicana cv. ‘I-214’	甲苯胺蓝 Toluidine blue
关明杰等，2012	酚醛树脂 Phenol-formaldehyde resin	竹片 Bamboo slice	甲苯胺蓝 Toluidine blue
杨滨, 2023	异氰酸酯 Methylene diphenyl diisocyanate	落叶松、竹片 Larix gmelinii, bamboo slice	FC法采色素 Pigment

[1]	Yang Qu,Qin Guo,Xuegang Huang,Tian Li,Manzhu Liang,Jingjing Qin,Qiaozhen Zhang,Hongzhi Liu,Qiang Wang. Preparation and Characterization of Hot-Pressed Peanut Meal and Cold-Pressed Peanut Meal Protein-Based Adhesives for Plywood [J]. Scientia Silvae Sinicae, 2024, 60(7): 158-164.
[2]	Min Liang,Jianfeng Xu,Ru Liu,Ling Long. Preparation and Properties of Coated Decorative Base Paper for Formaldehyde-Free Impregnated Paper [J]. Scientia Silvae Sinicae, 2024, 60(6): 120-127.
[3]	Xiaorong Liu,Zhenyu Yu,Kaili Wang,Youming Dong,Yanjun Li,Xianxu Zhan,Jianzhang Li. Effect of Epoxidized Natural Rubber on the Performance of Soybean Meal Adhesives [J]. Scientia Silvae Sinicae, 2024, 60(6): 128-135.
[4]	Jianfeng Yao,Xuzhan Guo,Liyong Fu,Xuefeng Wang,Xiangdong Lei,Jun Lu,Yili Zheng,Xinyu Song. Indirect Measurement of Wood Density by Micro Drill Resistance Method [J]. Scientia Silvae Sinicae, 2022, 58(9): 138-147.
[5]	Bochao Cui,Jianghua Zheng,Zhongjun Liu,Tao Ma,Jianglong Shen,Xuemi Zhao. YOLOv3 Mouse Hole Recognition Based on Remote Sensing Images from Technology for Unmanned Aerial Vehicle [J]. Scientia Silvae Sinicae, 2020, 56(10): 199-208.
[6]	Yan Lei, Gao Xiang, Wang Tengyu, Pang Lei, Su Lin, Kang Yongzhen. A Measurement Method of Log Diameter for Rotary Cutting Machines Based on Image Processing [J]. Scientia Silvae Sinicae, 2019, 55(5): 125-133.
[7]	Zhang Ruike, Chen Meixiang, Li Ming, Yang Xinting, Wen Junbao. Method of Extracting Forewings Angle of 3D Pose for the Moth Based on Machine Vision [J]. Scientia Silvae Sinicae, 2017, 53(11): 120-130.
[8]	Wang Xuefeng;Hirafuji Masayuki. Modeling the Relationship between Yellow Horn Seedling Growth and Soil Moisture Content [J]. Scientia Silvae Sinicae, 2013, 49(4): 70-76.
[9]	Zhang Yadong;Gu Jiyou;Zheng Zhifeng;Huang Yuanbo. Preparation and Characterization of Isocyanate Adhesive Based on Soybean Oil for Wood Bonding [J]. Scientia Silvae Sinicae, 2013, 49(4): 110-116.
[10]	Wang Xuefeng, Li Xiaodong, Hirafuji Masayuki. Orange Brix’s Nondestructive Analysis Based on Color Image [J]. Scientia Silvae Sinicae, 2013, 49(10): 88-92.
[11]	Gao Zhenhua;Gu Jiyou. Water Resistant Wood Adhesives Prepared with Phenolated Soy Flours [J]. Scientia Silvae Sinicae, 2011, 47(9): 129-134.
[12]	Liu Meijuan;Wen Zuomin. System and Method of Accounting Measurement for Forest Natural Capital [J]. Scientia Silvae Sinicae, 2011, 47(3): 161-169.
[13]	Liu Qianli;Li Chunyou;Meng Ping;Liu Ruiwu;Zhang Jinsong;Gao Jun. Forest Measurement Method and Data Analysis of Multi-Baseline Digital Close-Range Photogrammetry System [J]. Scientia Silvae Sinicae, 2010, 46(2): 166-170.
[14]	Liu Meijuan;Wen Zuomin. Review of Research on Fair Value Measurement for Forest Natural Capital [J]. Scientia Silvae Sinicae, 2009, 12(9): 130-137.
[15]	Gao Zhenzhong;Liao Feng;Deng Shibing;Zheng Zhenjie. Preparation and Properties of PMUF Resin Adhesive [J]. Scientia Silvae Sinicae, 2009, 12(8): 124-128.

Research Progress of Machine Vision-Based Gluing Performance Measurement Technology

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 18

References 0

Related Articles 15

Recommended Articles

Metrics

Comments