This study proposed a high-precision, high-efficiency method for surface defect detection of particleboard that is suitable for practical industrial scenarios to address the problems of high missed detection rate, slow detection speed, and insufficient ability to identify complex defects associated with traditional detection methods in current particleboard production, thereby achieving a dual optimization of detection accuracy and real-time performance.

Based on RT-DETR-r18, ablation experiments were conducted using the control variable method to verify the effectiveness of the three key modules: ECG-CFNet, FSA, and MPCA. Several mainstream lightweight backbone networks, including Swin Transformer and VanillaNet, were substituted for comparison of their training performance. The improved model was further compared with SSD, Faster-RCNN, YOLO series, and the original RT-DETR to validate its superiority. Key indicators such as mAP@50 and GFLOPs were adopted, combined with performance curves, PR curves, and visualization results, to comprehensively evaluate the detection accuracy, efficiency, and industrial applicability of the model.

Comparison experimental results on standard defect image datasets show that the proposed improved algorithm achieves 91.9% in terms of mean detection accuracy (mAP@50), which is 2.9% higher than the original RT-DETR-r18 model. At the same time, the number of parameters of the model and the computational complexity are both decreased, which suggests that while guaranteeing the improvement of the detection accuracy, the detection efficiency is optimized as well. Specifically, in the detection of typical defect types such as cracks, shavings and black spots, both show higher recognition rates and lower false alarm rates.

The improved RT-DETR algorithm significantly improves the accuracy and real-time performance of particleboard surface defect detection while maintaining low computational resource consumption, and has strong industrial deployability and application prospects.

Oil tea cultivation offers significant economic and ecological benefits and has seen rapid growth in recent years. Traditional manual grafting of oil tea scions is costly, with low controllability of quality, while existing oil tea seedling grafting devices cause high mechanical damage to seedlings, limiting their application. This paper introduces a motor-driven automatic grafting and shaping device for oil tea seedlings with a low damage rate, propelling the continuous development of the oil tea industry.

The paper is grounded on an analysis of the grafting principle and selection of the grafting process. Key components such as clamping and fixing, cutting and shaving, and a centering apparatus are formulated based on geometrical parameters obtained from random samples of rootstocks and scions. To assess the design's validity, the Abaqus software simulates the dynamics of seedling centering during grafting. Furthermore, a response surface and a multi-objective optimization model were established using Design Expert software to optimize key parameters in the grafting process.

Dynamical simulation results indicated that the maximum deformation of rootstocks during grafting is 0.416 5 mm, with seedling clamp diameter ranging from 3.0-3.7 mm. The average offset of rootstocks post-centering is 0.066 7 mm, 2.7% of their axial diameter, demonstrating the device's excellent stability and grafting quality assurance. Optimal centering speed, grafting depth, and seedling opening angle of 30.52 mm/s, 53.55%, and 6.89° were identified, respectively.

The device designed in this study uses multiple electric cylinders to automate the grafting of oil tea seedlings, reducing the centering damage rate and providing technical support for the advancement of the oil tea industry. It also offers insights for the design of automated grafting devices for other agricultural and forestry plants.