The machining processing of wood-plastic composites (WPCs) has some technological gaps in the field of surface damage mechanism and surface quality monitoring. In this study, orthogonal cutting tests were used to investigate the mechanisms of surface damage and the degree of chip (the material cutting off by cutting tool) curling of WPCs with various tool rake angles (from 5 ° to 40 °) and cutting depths (from 0.1 to 1 mm). Based on observations of the processed surface micromorphology, a surface damage model is proposed to describe the temperature-dependent reduction in adhesion force between polyethylene and wood flour. Chip curling was quantified by the point curvature in the side view. The curvature data for each chip point were negatively correlated with the depth of cut, but the relationship with the tool rake angle was less pronounced. The surface damage mechanism of WPCs during machining was revealed, providing a theoretical basis for improving surface quality through material formulation. The analysis of chip curvature offers theoretical support for the dynamic observation of chip morphology and elucidates the relationship between chip morphology, cutting depth, and tool rake angle. These findings can serve as a foundation for monitoring cutting precision in practical production.

The milling performance of thermally modified wood is an essential step in its actual processing and production. Accurate prediction of milling performance of thermally modified wood is significantly meaningful for subsequent parameter optimization to improve product surface quality and increase product competitiveness. Hence, based on machine learning, four models, Random Forest (RF), Support Vector Machine (SVM), Gaussian Process Regression (GPR) and Multilayer Perceptron (MLP), were established to predict two milling parameters of thermally modified wood. In addition, four characteristics factors were set up to evaluate the cutting force (F) and the surface roughness (Ra): the modification temperature (T) of thermally modified wood, the depth of cut (h), the feed rate (u), and the spindle speed (n) of the tool during the milling process. In order to reflect the scientific nature of the research process, normal distribution analysis was additionally used as a dataset preprocessing step. The final comparison found the GPR model to be the best fitting and most accurate method for predicting milling performance.

Vibrational methods, which are widely recognized non-destructive testing (NDT) techniques for timber, have garnered significant attention due to their ease of use, broad applicability, and reliable data output. These methods analyze the vibrational response of wood to external stimuli to assess its mechanical properties and internal structure. With advancements in sensor technology, signal processing, and computer simulation, the role of the vibrational methods in timber inspection has been largely expanded, enhancing both the scientific application and quality assurance of timber. This paper provides a comprehensive review of applications of vibrational methods in timber performance evaluation, focusing on its vibrational characteristics, underlying principles, and utility in detecting the physical and mechanical properties as well as internal defects of timber. Furthermore, potential future trends are discussed. Through analysis and research, valuable insights into the evolution of non-destructive timber testing technology are aimed to be provided by this review, and technological innovation in the timber industry is encouraged.

Accurate identification of wood surface defects is crucial for improving the quality and utilization of wood products. To address the low efficiency and accuracy of traditional manual inspection methods, this study collected near-infrared spectroscopy (NIRS) data from Brich and Fir surfaces, including defect-free samples and three typical defect types. The effectiveness of machine learning models in classifying wood surface defects was systematically investigated. Two feature dimensionality reduction methods, principal component analysis (PCA) and recursive feature elimination (RFE), were selected for comparison to screen out representative feature variables. Four classification models, namely, partial least squares discriminant analysis (PLS-DA), random forest (RF), support vector machine (SVM) and fully connected neural network (FCNN), were used to model and classify the wood defect samples. The results indicate that PCA outperforms RFE in enhancing model classification performance. Among the models, the FCNN achieved the best performance, with a highest classification accuracy of 98.85 %, and both recall and F1-score reaching 0.989. These findings demonstrate the superiority of deep learning methods in wood defect recognition tasks. This study systematically evaluated machine learning models based on near-infrared spectroscopy for the classification of wood surface defects, providing valuable insights for model selection and optimization in future research.

As a green building material, thermally modified timber's milling surface roughness significantly impacts processing quality, yet the influencing process parameters are complex and interdependent. This study predicted milling surface roughness using modification temperature, depth of cut, feed rate, and spindle speed as input features. Among the compared models, XGBoost outperformed Random Forest in prediction accuracy. The study further integrated Shapley value (SHAP) and local interpretable model-agnostic explanations (LIME) to analyse the model's interpretability. Results revealed that the depth of cut had the most significant impact on surface roughness, followed by feed rate, modification temperature, and spindle speed. Local interpretability analyses provided detailed insights into each parameter's contribution to single-sample predictions. This research demonstrates the value of SHAP and LIME in manufacturing, enabling transparency in machine learning models and offering theoretical support for process control in automated systems. The findings provide practical guidance for optimising timber processing parameters and advancing real-time monitoring and optimisation in smart manufacturing.

Wood moisture content is a critical indicator affecting its physical and mechanical properties. Accurate moisture prediction is essential for quality control and performance evaluation in wood processing. Addressing the limitations of traditional detection methods—such as time-consuming procedures, complex operations, and limited prediction accuracy—this study employs vibration signals for non-destructive moisture prediction in wood. Wood vibration signal data across varying moisture content gradients were collected using the CT1005L vibration signal acquisition system. Butterworth filters were applied for noise reduction to preserve effective feature information. Four predictive models—Support Vector Regression (SVR), Random Forest (RF), Gradient Boosting Regression (GBR), and Extreme Gradient Boosting (XGBoost)—were constructed and compared. Compared to other models, XGBoost demonstrated optimal performance in prediction accuracy and generalisation capability, with its R2 increasing from 0.8094 to 0.9413 and MSE decreasing from 0.0038 to 0.0015, indicating significantly improved predictive outcomes. Further interpretability analysis of the XGBoost model using the SHAP (Shapley Additive exPlanations) method clarified the importance and directional influence of different vibration features on the prediction results. The findings demonstrate that this approach achieves high-precision moisture content prediction while maintaining the advantages of non-destructive testing, providing a feasible solution for online monitoring and intelligent control in wood processing.

Tool condition monitoring (TCM) is essential for advancing the wood-based material processing industry, particularly in the context of rapid technological progress. Unlike metal cutting, wood-based material cutting presents unique challenges that require existing TCM systems to be carefully adapted. Despite its importance, research specifically targeting TCM in wood-based processing remains sparse, with most studies focusing on cutting mechanisms rather than monitoring solutions. This paper offers a comparative analysis, synthesizing insights from cutting mechanisms and TCM to address this gap. It further explores the broader integration of TCM into wood processing, highlighting current challenges and limitations. By bridging these knowledge gaps, the study provides a foundation for improving TCM applications in wood-based material cutting.

Abstract Efficient and nondestructive technology for identifying wood species facilitates the transition from digital forestry to smart forestry. While near-infrared spectroscopy applied to wood identification is well documented, the detailed mechanisms for chemometrics remain unclear. In this study, twelve wood species were identified by using near-infrared spectroscopy combined with six machine learning algorithms (support vector machine, logistic regression, naïve Bayes, k-nearest neighbors, random forest, and artificial neural network). Above all, isolated forest and local outlier factor were used to detect and exclude outliers. Then feature engineering strategies were developed from three perspectives to process feature matrices: feature selection, feature extraction, and feature selection combined with feature extraction. Next, the learning curve, grid search method, and K-fold cross-validation were used to optimize the model parameters. Finally, the accuracy, operation time, and confusion matrix were used to evaluate the model performance. When the local outlier factor was used to remove outliers and principal component analysis was used to extract features, the support-vector-machine-based wood-species identification model produced the most accurate results, with 98.24% accuracy. These results offer new avenues for constructing automatic wood-identification systems.

The illegal logging of valuable tree species is mainly motivated by the global market that consumes logs, lumber, veneers, and furniture. Rapid and reliable identification of the country of origin of protected timbers is one of the measures for combating illegal logging. There is a global need to create a wood origin identification system to ensure the integrity of wood supply and control the trade, exploitation, and smuggling of these products. Near-infrared spectroscopy (NIRS) is a promising technique for calibration-based and rapid species identification. In the present work, Near-Infrared Spectroscopy combined with machine learning techniques were used to discriminate six wood species (Pinus massoniana, Paulownia fortunei, Zelkova schneideriana, Tectona grandis, Tilia amurensis, Ailanthus altissima) originating from two regions. The initial step was to create a spectral dataset of tree origins by collecting spectral data on these six wood species from two distinct origins, each constituting a dataset. Then, reduce feature dimensionality to two dimensions to investigate the data distribution across datasets. Secondly, the high-dimensional spectral data were dimensionally reduced using principal component analysis and linear discriminant analysis, respectively, to improve the model's generalization and to compare the effects of the two techniques on the model's accuracy. Finally, six different machine learning, namely, Support vector machine, Logistic regression, K-Nearest neighbors, Naive Bayes, Random Forest, and Artificial neural network, were used to train these wood samples' spectra and assess their discrimination performance. The results showed that the highest accuracies of Pinus massoniana, Paulownia fortunei, Zelkova schneideriana, Tectona grandis, Tilia amurensis, Ailanthus altissimaare 98. 3%, 100%, 100%, 100%, 100%, 98.3%, and the fastest operation speed are 0.183, 0.182, 0. 181, 0.182, 11.424 and 12. 969 s respectively. We evaluated and compared the performance of six models based on different machine learning algorithms to predict the geographic origin of the wood. Compared to the other five models, the best results were obtained by the Artificial neural network approach, but its running time is more than other algorithms, and requires a higher number of tuned and optimized parameters. Moreover, both the linear and non-linear algorithms yielded positive results, but the non-linear models appear slightly better. The study revealed that applying NIRS assisted by machine learning technique is suitable for the rapid identification and discrimination of wood origin and can be an essential tool for tracing the origins of wood, contributing to a safe authentication method in a quick, relatively cheap, and non-destructive way.

The combination of computer technology and non-destructive testing technology can facilitate the development of forestry in a more intelligent direction. In this paper, a Shapley additive explanations (SHAP)-based method is used to analyse the importance of band features in the near-infrared spectrum of black walnut wood, which ranges from 900 to 1650 nm. The spectral data from the SHAP analysis are fed into an integrated framework of machine learning algorithms based on four different theories. In the comparison tests, three different pre-processed NIR spectral data are entered into the integrated framework. The result of the SHAP analysis shows that the wavelengths that are positively correlated with the air-dry density of black walnut are 1354.59, 1400.23, 1341.51, 1426.26, 1413.25 nm. The model predictions show that the SHAP-treated spectral data outperformed the other two treatments for each model. For the SHAP-treated spectral data, the KNN model gives the best results with an R 2 of 0.947 and an MSE of 0.0010.

Wood utilisation is an important factor affecting production costs, but the combined utilisation rate of wood is generally only 50 to 70%. During the production process, the rejection scheme of wood defects is one of the most important factors affecting the wood yield. This paper provides an overview of the main wood defects affecting wood quality, introduces techniques for detecting and identifying wood defects using different technologies, highlights the more widely used image recognition-based wood surface defect identification methods, and presents three advanced wood defect detection and identification equipment. In view of the relatively fixed wood defect recognition requirements in wood processing production, it is proposed that wood defect recognition technology should be further developed toward deep learning to improve the accuracy and efficiency of wood defect recognition.

The physical properties of wood, particularly the dimensional stability, are affected by the water content. Most wood properties can be detected by near infrared spectroscopy (NIRS), which is used as a nondestructive testing method. At different wavelengths, different absorption peaks are presented with the moisture absorbed by wood. According to this feature, the absorption peaks can be collected, and the data can be processed by partial least squares method combined with NIRS. In this study, softwood oak and hardwood ash tree specimens were studied. In the infrared spectrum range, the wood moisture absorption curve was noticeable and the curve trend was similar, although the tree species were different. After centralization, standardization, and derivative processing of the spectral data, the correlation coefficients of oak and ash tree validations were high, reaching 0.9021 and 0.9661, respectively. The wood moisture content was predicted using NIRS and an algorithm. The experiments showed that this method is feasible.

After flame retardant and enhancing treatment, fast-grown poplar face the problem of leaching of pharmacy, which affected the effective permanence of the retard and further use is limited. In this paper, we study the fixed effect of low molecule phenol-formaldehyde (PF) resin on nitrogen and phosphorus (N-P) inorganic flame retardant compositeunder the condition of high relative humidity. The change oflateralsizes and quality of the specimens were emphasized in the experiment. Results reveal that the greater the concentration of flame retardant was,the greater weight gain percentage of the samples was, and the more serious leach was in the test, after the specimen was modified with the flame retardant.When weight gain percentage of the specimens is same, the greater the concentration of PF resin test solution was,better effect of the leachresistant will be obtained with the concentration of PF test solution increased.The PF resin with 25% concentration had the best effect to reduce the leach of N-P inorganic composite retards. From the comparative analysis above, it was advisable to indicate the PF resin with 25% concentration had the best effect to reduce the leach of N-P inorganic composite retards.

Parallel strand lumber (PSL) was manufactured from the veneer strand cut from the poplar broken veneers of the plywood enterprises, by analyzing the influence of the size of veneer strands, the glue concentration and glue-applying time on the glue-absorbing amount of veneer strands, the influence of three different glue-applying was, hot-pressing time and temperature on the physical and mechanical properties of PSL was reviewed and the hot-pressing technology was optimized. The experiment results showed that the size of the veneer strands have not notableinfluence on the gluing-absorbing amount, and mainly affect the homogeneity and appearance quality of the product. The glue concentration is one main factor to affect theglue-absorbing amount of veneer strands and PF resin of 30% concentration was chosen. The glue-applying way is the main factor to affect the mechanical property of PSL. Thehot-pressing time and temperature have significant influence on physical and mechanical properties of PSL. Comprehensively considering, the physical and mechanical properties and homogeneity of products are better using the veneer strands with 100 mm length, theglue-spraying way and hot-pressing technology with the time 35 min and thetemperature of 150°C.

In this paper, wood-wool panel was prepared by steam pressing as opposed to the traditional cold-pressing and hot-pressing methods in order to eliminate the shortcomings of both methods. Cold pressed wood panels have low strength. The overall performance of heat pressed wood panel was poor. The water absorption of these two panels was too large. The steam pressing mechanism was studied by the means of X-ray diffraction and scanning electron microscope. The surface structure, moisture absorption and mechanical properties of wood-wool panel were investigated by experimental testing and numerical analysis. The surface structure of the wood-wool panel became stable, the moisture absorption was reduced, and the mechanical properties of the wood-wool panel were enhanced. The static bending strength of autoclaved wood-wool panel was 4% higher than that of cold-pressed wood-wool panel, and 7.4% higher than that of hot-pressed wood-wool panel. And the sound absorption coefficient increased by 6.3% and 5% respectively. The thermal conductivity was 2.4% lower than that of cold-pressed wood-wool panel.

木材弹性模量是表征其力学性能的重要指标之一,应力波因其操作简便、成本低、测量结果准确等特点广泛应用于木材弹性模量的测量.目前,应力波技术测量木材弹性模量主要通过应力锤激励法实现,事实上应力锤激励法在测量木材弹性模量时无法实时分析测试试件的振动状态,且敲击易造成应力集中,不适用于厚度较小且材质较轻的木材试件.基于此,依据振动理论并结合压电材料的压电效应,从激振源和信号处理方式两个方面,构建了一种基于压电晶片激振测量木材横向弯曲弹性模量的方法.通过比较不同激励频率下激振与响应信号的幅值,获取木材试件的固有频率,根据梁的横向振动方程计算出弹性模量,并对比应力锤共振法测量结果验证该方法的可行性.两种方法测量结果的相对误差在2.5％以内,平均误差仅为1.54％.实测数据表明,基于压电晶片激振法可以有效地测得木材的弹性模量,且该方法测量时使用压电晶片激振产生的振幅较小,更加满足弹性力学微小变形的假设.后期的信号处理方面克服了应力锤法不能有效处理一些突变和不平稳信号的不足,使得检测方式更加灵活,重复性较好.

目前林业信息化正由数字林业迈向智慧林业,高效、无损的木材树种识别技术有利于推动我国林业信息化、智能化发展的进程.为了满足市场对木材高效精准识别的需求,将木材树种识别问题转化为多分类问题,开发了一种基于支持向量机结合线性降维算法的木材树种识别模型.具体而言,首先采用无监督的主成分分析和有监督的线性判别分析,分别对木材近红外高维光谱数据进行降维处理;其次将降维后的特征输入支持向量机模型中,输出各个树种类别上的概率分布.借助网格搜索法并结合5折交叉验证法选取最优核函数和核函数参数,探讨了支持向量机不同核函数对于木材树种分类效果的影响.为了评价模型的识别能力,选取准确率、混淆矩阵和ROC曲线评价提出的模型,并进一步探讨了本木材树种识别方法的可行性.实验结果表明,利用近红外光谱特征的支持向量机模型能准确且高效地识别木材树种.其中,线性判别分析结合支持向量机的模型分类准确率可达97.54％,模型运行速率为6.53 s.

Magnesite-bonded wood wool panel (MWWP) is an inorganic-bonded panel product in which wood excelsior is bonded with magnesite. Lowering the hygroscopicity is one of the key measures to improve the quality of the panel. In this study, moisture absorption mechanism of MWWP and measures generally applied to lower its hygroscopicity were reviewed. Three methods were then experimented to improve the dimensional stability of the panel, including adjusting the molar ratio of raw materials, adding additives and optimizing the conditioning process. The results showed that satisfying dimensional stability could be achieved when the molar ratio of MgO to MgCl2 was 5:1, the No.2 composite additive (aluminum powder + NH4H2PO4 + ferric alum) was adopted and a constant temperature and humidity treatment was applied in the first stage of conditioning.

为提高粉尘火焰/火花检测的可靠性,基于钾元素发射光谱设计木粉尘火焰/火花检测装置.利用粉尘蕴含元素受热会激发光谱特征为理论依据,采用高精度光谱元件、高速数模转换和控制芯片搭建检测装置,通过网口协议稳定传输获取的实时光谱特征.结果表明:采用上述方法能够获得明显的钾元素光谱,具有显著的光谱特征,可作为检测装置的检测依据.所设计的装置能迅速准确获得实时粉尘光谱状态,且成本低、精度高、体积小,可为预防粉尘燃爆事故的发生提供技术支撑.

设计了一种智能地板系统,包括由地板组成的成员组件和负责主控的控制组件构成.将包含有NRF2401的ARM控制器嵌入地板中赋予地板近距离无线通信,配合贴合在地板表面的压力传感器感知地板表面物体的压力点并向控制组件发送相应位置信息实现室内近距离定位;将地板和其他智能传感器有机结合,以实现温度监控、环境光强检测等功能.实物研究结果表明:基于NRF2401的地板可用于地面局部领域的定位需要,可将室内地板有机串联成一个整体,为后续地板智能化发展提供先行经验.