Sijie Yan

The production process of UPS Hall effect current sensors employs laser trimming, which utilizes a laser beam to physically cut the thick-film resistors to precisely adjust their resistance values. However, during this process, defects such as residual resistance, short circuits, serrations, and burrs can occur within the resistor kerf. These defects lead to poor long-term stability, increased noise, and reduced voltage withstand capability of the sensors. Regarding the inspection of thick-film resistor defects after laser trimming, the existing method relies on manual inspection using high-magnification microscopes. This approach faces challenges such as low efficiency, significant subjectivity, slow speed, operator fatigue, and the risk of false or missed detections. To address these issues, this study proposes an improved YOLO11-based detection method. Specifically, we introduce Space-to-Depth Convolution (SPDConv) to preserve fine-grained features and integrate an improved C3k2 module with the Dilation-wise Residual (DWR) module to capture multi-scale information. Furthermore, an additional P2 layer is designed utilizing the Four-head Adaptive Spatial Feature Fusion Head (FASFFHead) to enhance the perception of tiny targets. We term this model DIA-YOLO (Detail-Preservation, Interactive-Attention, Aggregation YOLO), an efficient object detection model specifically designed for micro-defect detection scenarios. In our experiments, we utilized Generative AI to generate defect images and compared the proposed method with mainstream models including YOLO11, Faster R-CNN, and RT-DETR. The proposed model achieved the highest mean Average Precision (mAP) of 95.2%, meeting the accuracy requirements for detecting surface kerf defects in UPS current sensing resistors. Furthermore, extensive validation on the public NEU-DET dataset demonstrates the strong generalization capability of the proposed method, where it achieves a precision of 0.802, a recall of 0.783, and an mAP@0.5 of 0.793, outperforming all baseline models. This study provides a novel approach for the defect detection of thick-film resistor kerfs.

The instantaneous contact zone in robotic abrasive belt grinding involves highly coupled thermo-mechanical interactions between abrasive grains and the workpiece material. Acoustic Emission (AE) signals generated during this process are inherently nonlinear and nonstationary, posing challenges for accurate process monitoring and mechanistic understanding. To address this, this study introduces an innovative AE signal processing framework designed to elucidate the robotic grinding mechanism for Ti-6Al-4V (TC4) titanium alloy. An improved Completely Complementary Ensemble Empirical Mode Decomposition (CCEEMD) algorithm, building upon Empirical Mode Decomposition (EMD), is developed to precisely extract intrinsic mode functions (IMFs) from raw AE data. Subsequently, a novel denoising algorithm utilizing noise statistical characteristics effectively removes invalid noise from the robotic machining system. Validation through robotic grinding experiments on TC4 workpieces successfully established quantifiable relationships between extracted AE features and the underlying grinding mechanism. Significantly, implementing this methodology contributed to extending the effective service life of a structured abrasive belt by approximately 20% while increasing machining efficiency by approximately 12%. This work presents a novel methodology combining improved CCEEMD and statistical denoising for AE analysis in robotic grinding, providing a robust link between AE signatures and material removal mechanisms, ultimately enabling quantitative process optimization.

Precise thickness measurement of multilayer coatings is essential for coating quality evaluation. Conventional terahertz-based thickness measurement methods rely on precalibrated refractive index, which are typically obtained from standard samples with known thicknesses. However, the assumption of a fixed refractive index overlooks batch-to-batch variations, leading to less reliable thickness estimation. To address this issue, a sample-free inversion method is proposed to jointly estimate coating thickness and refractive index. First, a multilayer THz reflection model is constructed, incorporating Rouard’s formalism and Debye dispersion, to relate refractive index and thickness to the theoretical signal. Then, a nonlinear optimization problem is formulated to minimize the discrepancy between the measured and theoretical signals in the time domain. To solve this problem, a Cluster-constrained Point-wise Optimization Framework (CPOF) is proposed, which combines perturbation-enhanced particle swarm optimization for global search and Gaussian mixture model clustering to regularize the solution space, achieving precise and stable inversion. Simulation and experimental results on coatings with one to three layers show a mean thickness deviation of 1.1%, with up to 95% RMSE reduction compared to single-point optimization. The proposed method reduces reliance on standard samples and ensures robust terahertz-based coating inspection under material variability.

Mobile robotic machining systems (MRMS) often suffer from limited overall motion accuracy due to the accumulation and coupling of pose errors among multi-units during operation. To address this issue, this study analyzes the motion transmission chain of MRMS, and decouples the geometric parameter errors and joint compliance errors using the nonsingular line representation method. Subsequently, the linear propagation-decoupling equations for generalized kinematic errors are derived, revealing the transmission mechanisms of different types of errors among various units across coordinate frames. On this basis, an information diffusion-based dataset augmentation method is developed to address the problem of limited sample data, and it is integrated with gradient boosting decision trees to predict the residual uncertainty errors. Furthermore, a hierarchical calibration method is proposed to progressively calibrate joint compliance errors, generalized geometric parameter errors, and residual uncertainty errors of MRMS. The effectiveness and superiority of the proposed method are validated through experiments.

A mobile robotic measurement system combined with a mobile tracker provides a promising solution for 3D full-field measurement because the measurement range can be flexibly enlarged by changing the tracker location multiple times. In such systems, the scanner poses can be calculated by capturing tracking markers with the tracker. To accurately align point clouds obtained from different tracker locations, the scanner-to-marker matrix (SMM) and tracker-to-tracker matrix (TTM) must be calibrated. To our knowledge, in existing calibration methods, SMM and TTM are separately calibrated using external markers, which leads to error accumulation and a complex calibration procedure. To address such problems, a coarse-to-fine calibration method for SMM and TTM is proposed. For coarse calibration, a closed-form model approximating AX = XB and a maker-based method calibrate SMM and TMM separately. Then, a simultaneous iterative optimization model based on Lie derivatives is adopted for fine calibration. Furthermore, to improve the calibration accuracy and robustness, the regularity term and Welsch robust kernel function are integrated into the optimization model. Finally, simulations and experiments are conducted to validate the proposed method. Both simulations and experiments demonstrate that the proposed calibration method has higher calibration accuracy and robustness compared with the existing calibration methods.

Accurate prediction of material removal depth and averaged surface roughness is crucial for evaluating the performance of robotic belt grinding (RBG). Nevertheless, the machining parameters of RBG across different spaces exhibit various data distributions, which often results in prediction shifts on unseen machining parameters when using conventional approaches. In this article, we introduce a pairwise domain adaptation-assisted dual-task learning (PW-DA-DTL) method for copredicting material removal depth and averaged surface roughness with regard to new RBG machining parameter spaces. The multigate mixture-of-experts method is employed as the foundational framework for dual-task learning, effectively capturing and modeling the relationships between material removal depth and average surface roughness by leveraging their inherent task interdependencies. The pairwise domain adaptation strategy is put forward to simultaneously enhance sample diversity and mitigate cross-domain data distribution discrepancy between the existing and new RBG machining parameter spaces. Comparative experiments are presented to demonstrate the effectiveness and superiority of the proposed PW-DA-DTL method.

In featureless point clouds, such as cylinder-ruled surfaces or shapes with lots of flattened areas, we observe that some classic iterative closest point variants, including point-to-point, point-to-plane, and symmetric metrics, are trapped in local minima. To explain the above phenomenons, we derive that the upper bounds error of landscapes (UBEL) of point-to-plane and symmetric metrics are nearly zero in the above scenes, resulting in slow convergence or local minima. To address the above challenges, we introduce a constrained registration method, which integrates geometry distance constraints (GDC) and weighted enhanced distance metric. Specifically, WED combines point-to-point and point-to-plane metrics, resulting in a steeper UBEL than point-to-plane and symmetric; GDCs constrain the transformation matrix into a feasible subset to escape local minima. Moreover, we introduce a dynamic slack of constraint algorithm to improve the stability of the linear perturbation in the constrained registration problem. Simulations and experiments are conducted on typical featureless objects, including a turbine blade, a cylinder-ruled surface, an outlet guide vane, and a rotor engine, to verify the effectiveness and efficiency of the presented registration framework.

Pose graph optimization (PGO) methods are extensively used in robotic inspection (RI) to estimate accurate 3-D scanner poses. However, some inaccurate pairwise relative measurements decrease the accuracy of PGO. In this article, we propose a new framework called robust constrained pose graph optimization (RCPGO) to achieve a robust and accurate RI. Specifically, some additional landmarks are utilized to construct a constrained pose graph (CPG) and improve the accuracy of PGO by CPG's spatial geometry consistency. Furthermore, the symmetric (SYMM) distance function is introduced to define the objective function of RCPGO, which has a higher D-optimality design metric upper bound and contributes to the robustness and accuracy of RCPGO. To solve the SYMM-RCPGO problem in $\boldsymbol{SE_{3}^{N}}$, we linearize the problem into a quadratically constrained quadratic program (QCQP) and solve the perturbation of $\boldsymbol{SE_{3}^{N}}$ by the interior-point method. Moreover, a dynamic constraints boundaries algorithm is proposed to prevent inaccurate linearization caused by large perturbation. To assess the effectiveness of SYMM-RCPGO, the comparative evaluations with traditional PGO methods are conducted on simulated cylinder surfaces, a high-speed train, and a rotor engine. The results validate the robustness and accuracy of SYMM-RCPGO and find that a few constraints can significantly reduce pose error.