- Scopus
- Chinese Science Citation Database (CSCD)
- A Guide to the Core Journal of China
- CSTPCD
- F5000 Frontrunner
- RCCSE
| Citation: |
Guo Jialun, Zhong Haomin, Zhao Junbo, Chen Yao. Deresination rate prediction of Masson pine wood based on support vector regression (SVR)[J]. Journal of Beijing Forestry University, 2025, 47(3): 151-161. DOI: 10.12171/j.1000-1522.20240359
|
Deresination treatment is an important method for improving the performance of pine wood products. However, traditional methods for detecting deresination rate are both time-consuming and destructive to samples. This paper aims to explore a rapid and non-destructive method for detecting the deresination rate based on changes in wood surface color and using support vector regression (SVR) to construct a deresination rate prediction model.
Pinus massoniana wood was treated with ammonia gas and water vapor under high-temperature conditions. The effects of different conditions on wood surface color parameters and deresination rate were analyzed, and their correlations were investigated. Three different kernel functions (polynomial kernel function, Sigmoid kernel function, and radial basis function) were used to construct SVR-based deresination rate prediction models, and the optimal model was selected through comparison.
After deresination by ammonia gas-water vapor heat treatment, the surface lightness (L*) and yellow-blue index (b*) of Masson pine wood were lower than those of untreated wood, while the red-green index (a*) was higher than that of untreated wood. With increasing ammonia mass fraction and treatment temperature, L*, a*, and b* showed a gradual downward trend, the total color difference (ΔE*) increased gradually, and the deresination rate improved accordingly. Under treatment conditions of 180 °C and a higher ammonia mass fraction, ΔE* reached its maximum value of 58.89, and the deresination rate achieved its highest value of 70.00%. The color parameters showed a local quadratic relationship with deresination rate, with the highest correlation coefficient being 0.713. In SVR model with radial basis function as kernel function, the root mean square errors for predicting lipid content and deresination rate were 0.523 and 4.315, respectively, and the coefficients of determination were 0.847 and 0.823, respectively. This prediction model can be applied to preliminary screening in deresination rate detection.
This study successfully constructs a deresination rate prediction model for Masson pine wood based on SVR. The model has certain application value in preliminary screening of deresination rate detection, and can achieve rapid, convenient, and non-destructive detection to some extent. This research provides a new method for improving the efficiency and quality of deresination rate detection in Masson pine wood.
| [1] |
张文梁, 曹金珍. 松脂及松木脱脂技术研究进展[J]. 林产工业, 2021, 58(10): 60−64.
Zhang W L, Cao J Z. Research progress on pine resin and degreasing technology of pine[J]. China Forest Products Industry, 2021, 58(10): 60−64.
|
| [2] |
国家技术监督局. 造纸原料有机溶剂抽出物含量的测定: GB/T 2677.6—1994[S], 北京: 中国标准出版社, 1994.
The State Bureau of Quality and Technical Supervision. Fibrous raw material determination of solvent extractives: GB/T 2677.6−1994[S]. Beijing: Standards Press of China, 1994.
|
| [3] |
Matsumura J, Booker R E, Ridoutt B G, et al. Impregnation of radiata pine wood by vacuum treatment (II): effect of pre-steaming on wood structure and resin content[J]. Journal of Wood Science, 1999, 45(6): 456−462. doi: 10.1007/BF00538953
|
| [4] |
杨少春, 王克奇, 戴天虹, 等. 基于直方图的木材表面颜色分类研究[J]. 森林工程, 2008, 24(1): 34−36. doi: 10.3969/j.issn.1001-005X.2008.01.009
Yang S C, Wang K Q, Dai T H, et al. A study of color classification on wood surface based on histogram[J]. Forest Engineering, 2008, 24(1): 34−36. doi: 10.3969/j.issn.1001-005X.2008.01.009
|
| [5] |
Hazir E, Ozcan T, Koç H K. Prediction of adhesion strength using extreme learning machine and support vector regression optimized with genetic algorithm[J]. Arabian Journal for Science and Engineering, 2020, 45(8): 6985−7004. doi: 10.1007/s13369-020-04625-0
|
| [6] |
Yang H, Cheng W, Han G. Wood modification at high temperature and pressurized steam: a relational model of mechanical properties based on a neural network[J]. BioResources, 2015, 10(3): 5758−5776.
|
| [7] |
李腊梅, 谢桂军, 李兴伟, 等. 蒸汽热处理红锥木材颜色变化及其材性预测[J]. 森林工程, 2023, 39(5): 92−104. doi: 10.3969/j.issn.1006-8023.2023.05.011
Li L M, Xie G J, Li X W, et al. Color change and timber property prediction of Castanopsis hystrix wood after steam heat-treated[J]. Forest Engineering, 2023, 39(5): 92−104. doi: 10.3969/j.issn.1006-8023.2023.05.011
|
| [8] |
Zhang L L, Liu M H, Liu Y X, et al. Evaluation of the colour parameters on hygroscopicity and dimensional stability of thermally modified Populus tomentosa Carr.[J]. Industrial Crops & Products, 2023, 205(1): 285−297.
|
| [9] |
Liu M H, Zhang L L, Chen J, et al. Response relationships between the color parameters and chemical compositions of heat-treated wood[J]. Holzforschung, 2024, 78(7): 387−401. doi: 10.1515/hf-2023-0086
|
| [10] |
Vahid N, Hamidreza F, Arezoo F, et al. Prediction of mechanical properties of artificially weathered wood by color change and machine learning[J]. Materials, 2021, 14(21): 6314. doi: 10.3390/ma14216314
|
| [11] |
Chen S, Wang J P, Liu Y X, et al. The relationship between color and mechanical properties of heat-treated wood predicted based on support vector machines model[J]. Holzforschung, 2022, 76(11−12): 994−1002. doi: 10.1515/hf-2022-0075
|
| [12] |
Xin Z B, Ke D F, Zhang H J, et al. Non-destructive evaluating the density and mechanical properties of ancient timber members based on machine learning approach[J]. Construction and Building Materials, 2022, 341: 127855. doi: 10.1016/j.conbuildmat.2022.127855
|
| [13] |
Fu Z Y, Zhou F, Gao X, et al. Assessment of mechanical properties based on the changes of chromatic values in heat treatment wood[J]. Measurement, 2020, 152: 107215. doi: 10.1016/j.measurement.2019.107215
|
| [14] |
Nasir V, Nourian S, Avramidis S, et al. Classification of thermally treated wood using machine learning techniques[J]. Wood Science and Technology, 2019, 53(1): 275−288. doi: 10.1007/s00226-018-1073-3
|
| [15] |
Tominaga S. Color classification of natural color images[J]. Color Research & Application, 1992, 17(4): 230−239.
|
| [16] |
刘小生, 章治邦. 基于改进网格搜索法的SVM参数优化[J]. 江西理工大学学报, 2019, 40(1): 5−9.
Liu X S, Zhang Z B. Parameter optimization of support vector machine based on improved grid search method[J]. Journal of Jiangxi University of Science and Technology, 2019, 40(1): 5−9.
|
| [17] |
Açikkar M. Fast grid search: a grid search-inspired algorithm for optimizing hyperparameters of support vector regression[J]. Turkish Journal of Electrical Engineering and Computer Sciences, 2024, 32(1): 68−92. doi: 10.55730/1300-0632.4056
|
| [18] |
Stanciu D M, Sova D, Savin A, et al. Physical and mechanical properties of ammonia-treated black locust wood[J]. Polymers, 2020, 12(2): 377. doi: 10.3390/polym12020377
|
| [19] |
陈宣宗, 张爱文, 陈李璨, 等. 高温水热处理对马尾松木材颜色变化的影响[J]. 浙江林业科技, 2018, 38(6): 1−7. doi: 10.3969/j.issn.1001-3776.2018.06.001
Chen X Z, Zhang A W, Chen L C, et al. Effect of hydrothermal treatment on color of Pinus massoniana wood[J]. Zhejiang Forestry Science and Technology, 2018, 38(6): 1−7. doi: 10.3969/j.issn.1001-3776.2018.06.001
|
| [20] |
李任杰, 韩裕龙, 李俊源, 等. 木材变色机理研究进展[J]. 世界林业研究, 2024, 37(2): 66−73.
Li R J, Han Y L, Li J Y, et al. Research progress on wood discoloration mechanism[J]. World Forestry Research, 2024, 37(2): 66−73.
|
| [21] |
平立娟, 刘君良, 王喜明. 高温高湿处理对樟子松脱脂率及微观结构的影响[J]. 木材工业, 2020, 34(4): 38−42.
Ping L J, Liu J L, Wang X M. Effect of high-temperature and high humidity treatment on extraction rate and micro-structure of Mongolian Scotch pine (Pinus sylvestris var. mongolica Litv.)[J]. China Wood Industry, 2020, 34(4): 38−42.
|
| [22] |
张志文, 陈广元. 高温高湿处理对落叶松锯材树脂脱除及分布影响分析[J]. 森林工程, 2011, 27(3): 61−63. doi: 10.3969/j.issn.1001-005X.2011.03.016
Zhang Z W, Chen G Y. Effect of high temperature and humidity treatment on the moving and distribution of pine resin[J]. Forest Engineering, 2011, 27(3): 61−63. doi: 10.3969/j.issn.1001-005X.2011.03.016
|
| [23] |
彭万喜. 人工速生工业林木材增值利用——人工林松木脱脂新技术研究[D]. 长沙: 中南林业科技大学, 2003.
Peng W X. Value-added utilization of wood from plantation fast-growing industrial forests: research on new technology of pine wood degreasing in plantation forests[D]. Changsha: Central South University of Forestry and Technology, 2003.
|
| [24] |
Ivan I, Romman T, Nataliya S, et al. The additive input-doubling method based on the SVR with nonlinear kernels: small data approach[J]. Symmetry, 2021, 13(4): 612. doi: 10.3390/sym13040612
|
| [25] |
Wang Y G, Wu J R, Hu Z H, et al. A new algorithm for support vector regression with automatic selection of hyperparameters[J]. Pattern Recognition, 2029, 133: 108989.
|
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: