Knot detection is an important aspect of timber grading. Reducing the false-positive frequency of knot detection will improve the accuracy of the predicted grade, as well as the utilization of the graded timber. In this study, a framework for timber knot detection was proposed. Faster R-CNN, a state-of-the-art defect identification algorithm, was first employed to detect timber knots because of its high true-positive frequency. Then, an overlapping bounding box filter was proposed to lower the false positive frequency achieved by Faster R-CNN, where a single knot is sometimes marked several times. The filter merges the overlapping bounding boxes for one actual knot into one box and ensures that each knot is marked only once. The main advantage of this framework is that it reduces the false positive frequency with a small computational cost and a small impact on the true positive frequency. The experimental results showed that the detection precision improved from 90.9% to 97.5% by filtering the overlapping bounding box. The framework proposed in this study is competitive and has potential applications for detecting timber knots for timber grading.

The noise corruption problem commonly exists in hyperspectral images (HSIs) and severely affects the accuracy of hyperspectral unmixing algorithms. The noise formulation existing in HSIs is relatively complex and would change in conjunction with different devices and imaging settings. For real applications, applying denoising approaches without accurate close-to-reality noise modeling before unmixing may not improve, but rather degrade the unmixing performance. This study proposes a robust hyperspectral unmixing method with practical learning-based hyperspectral image denoising. We formulated a close-to-reality noise model for hyperspectral data and provide a calibration approach for the noise parameters. On the basis of the calibrated noise model, synthetic data were generated and used for training a KST-based denoising network. The noisy hyperspectral data were firstly denoised by the trained denoising network and were then used to perform the unmixing process. A variety of unmixing algorithms can be integrated into our method to improve the accuracy of unmixing in noisy situations. In the experiments, several widely used unmixing algorithms were employed to verify the effect of the proposed method. The experimental results on both synthetic and real demonstrated that our proposed method can handle HSI data with various gain settings and helps to improve the unmixing performance effectively.

In recent years, the fast rise in number of studies on graph neural network (GNN) has put it from the theories research to the real-world application stage. Despite the encouraging performance achieved by GNN, less attention has been paid to the privacy-preserving training and inference over distributed graph data in the related literature. Due to the particularity of graph structure, it is challenging to extend the existing private learning frameworks to GNN. Motivated by the idea of split learning, we propose a server aided privacy-preserving GNN (SAPGNN) for the intra-graph node level task on the horizontally partitioned cross-silo scenario. It offers a natural extension of centralized GNN to the isolated graph with max/min pooling aggregation, while guaranteeing that all the private data involved in the computation still stays with local data holders. To further enhance the data privacy, a secure pooling aggregation mechanism is proposed. Theoretical and experimental results show that the proposed model achieves the same accuracy as the one learned over the combined data.

The present work is aimed at studying the effects of the magnetorheological finishing process, using a low-frequency alternating magnetic field, on the finishing performance of 6063 aluminum alloy. The study investigates the influence of key excitation parameters such as current, frequency, excitation gap, and iron powder diameter on the material removal and surface roughness (Ra) of the finished workpiece by experiments. This study employs a single-factor experimental method, and the finish surface is analyzed by a Zigo non-contact white light interferometer. The magnetic field strength in the processing area increases with the increase in the excitation current and decreases with the increase in the excitation gap. When the current frequency is set to 1 Hz, the circulation and renewal of abrasives in the magnetic cluster is most sufficient, resulting in the optimal surface roughness value for the workpiece. According to the experimental results of the excitation parameters, more suitable process parameters were selected for a two-stage finishing experiment. The surface roughness of 6063 aluminum alloy was improved from 285 nm to 3.54 nm. Experimental results highlighted that the magnetorheological finishing using a low-frequency alternating magnetic field is a potential technique for obtaining nano-scale finishing of the 6063 aluminum alloy.

This article proposes an improved model-free deadbeat predictive current control (MFCC) method for permanent magnet synchronous motors (PMSMs) based on the ultralocal model and H∞ norm. Firstly, the traditional deadbeat predictive current control (DPCC) method is introduced and a theoretical analysis is conducted on its sensitivity to parameters. Building upon this, the limitations of model dependence and the limited robustness of the deadbeat predictive current control method based on the extended state observer (ESO-DPCC) are theoretically analyzed. Furthermore, an improved MFCC method based on the ultralocal model is proposed, and the influence of the observer on MFCC is theoretically analyzed. This study combined the proposed method with the H∞ norm, and the optimal coefficients of the observer were tuned to enhance the robustness and dynamic performance of the current loop. Finally, the proposed algorithms were validated on a 400 W PMSM platform.