The precision and stability of seam position detection are critical for single-square-groove weld seams formed using two thin metal plates. However, traditional methods, such as structured laser light imaging, struggle with narrow seams that lack misalignment and have high reflectivity, while non-structured light approaches are prone to welding light interference and speckle noise. To overcome these challenges, we propose a versatile optical design that leverages differential illumination to generate differential phase contrast (DPC) images. By processing images captured under differential illumination, the DPC method notably enhances seam edge contrast and suppresses welding light noise, improving the detection robustness and reliability. This approach provides a promising solution for high-precision weld seam detection in challenging environments.

We report herein the first visible light optical coherence tomography angiography (vis-OCTA) for human retinal imaging. Compared to the existing vis-OCT systems, we devised a spectrometer with a narrower bandwidth to increase the spectral power density for OCTA imaging, while retaining the major spectral contrast in the blood. We achieved a 100 kHz A-line rate, the fastest acquisition speed reported so far for human retinal vis-OCT. We rigorously optimized the imaging protocol such that a single acquisition takes <6 seconds with a field of view (FOV) of 3×7.8 mm ² . The angiography enables accurate localization of microvasculature down to the capillary level and thus enables oximetry at vessels < 100 μm in diameter. We demonstrated microvascular hemoglobin oxygen saturation (sO ₂ ) at the feeding and draining vessels at the perifoveal region. The longitudinal repeatability was assessed by <5% coefficient of variation (CV). The unique capabilities of our vis-OCTA system may allow studies on the role of microvascular oxygen in various retinal pathologies.

To address the limitations of low accuracy and poor reliability in traditional fatigue life estimation methods for metal structures with macroscopic fatigue cracks, a dual-modal data fusion approach integrating a finite element model and an LSTM (Long Short-Term Memory) network is proposed. First, a finite element model incorporating boundary conditions and cyclic loading is developed to simulate crack propagation. To enhance the model's accuracy, an improved particle filtering algorithm is employed to optimize high-sensitivity parameters, ensuring that the simulated strain and vibration modal data closely match the measured values, achieving an overall fatigue life fidelity of 97.7% for the calibrated finite element model. Furthermore, an LSTM network is introduced to refine the estimation of strain and vibration data based on the optimized finite element model, achieving an estimation error below 2% in crack length estimation. Experimental validation using a fatigue testing platform demonstrates an estimation error below 2% for fatigue life, surpassing single-modal methods by 4.6%. The results confirm the proposed method's effectiveness in addressing data incompleteness in traditional approaches while significantly improving estimation robustness and reliability.