Power semiconductor devices generate mechanical stress wave (MSW) signals during switching processes, which can be used for condition monitoring (CM) of these devices with the advantages of noninvasive and non-destructive monitoring. Existing MSW signal detection methods are susceptible to electromagnetic interference and environmental factors (such as high temperature, high voltage, confined spaces, or structural constraints), which limit their adaptability in complex working conditions. Bare fiber Bragg grating (FBG) sensors offer strong resistance to electromagnetic interference and excellent environmental adaptability. Therefore, this paper proposes a transient high-frequency MSW measurement method for power semiconductor devices based on high-sample-rate bare FBG sensors. The MSW signals generated during the switching process of power semiconductor devices are successfully captured based on high-sample-rate bare FBG sensors for the first time. Comparative signal measurements between single-ended acoustic emission (AE) sensors and bare FBG sensors demonstrate the electromagnetic interference resistance capability of bare FBG sensors. Moreover, this study expands the application range of MSW detection methods for power semiconductor devices and provides new technical support for investigating the generation and propagation mechanisms of MSW signals.

Active three-dimensional(3-D) thermography combines 3-D shape and active thermography. Thus, it enables the provision of the intuitive thermographic inspection results for composite parts with a complex geometry. However, conventional 3-D thermography acquires thermographic information and 3-D shape through at least two independent sensors and requires complex cross-modal image registration algorithm based on the keypoint detection and matching. In this article, an active 3-D thermography system is proposed using only one thermal camera for moving objects. This system does not require an independent 3-D sensor while the thermal camera acts as the 3-D sensor. Nature behind that is that a mathematical model is proposed to unify the line scanning thermography and laser triangulation in the dynamic scanning process, taking a line laser as both heat excitation for active thermography and spatial coding for 3-D reconstruction. Furthermore, the model enables the feature-free registration of thermogram sequence and 3-D shape, so that the registration is fast and robust without keypoint features. The experiments on standard height specimens, 3-D printing glass fiber composites, and carbon fiber intake tube have shown the error is calibrated within 0.25 mm in the range of 1 to 150 mm and evidenced the capability for subsurface defects detection. The ease and robustness of the proposed active 3-D thermography have a bright future for 3-D measurement, defects detection, and quality control in the production line.

Line scanning thermography (LST) is a fast non-destructive inspection (NDI) method for large-scale components. However, the current reconstruction algorithms for LST require the match between the frame rate and the scanning velocity. Moreover, these algorithms bring in spatial distortions. This paper proposes a non-orthogonal reconstructed space for LST. In such a space, the excitation motion in the line scanning process is described as a function of time delay, the moving velocity is estimated by the derived position map, and the reconstruction is achieved by image registration. The LST data are registered spatially by allowing the temporal misalignment among the pixels within the same reconstructed frame. The effectiveness of the proposed reconstruction algorithm is validated by both numerical simulations and experiments. The reconstruction results of experimental data indicate that the velocity is finely estimated so that the temporal alignment error is controlled within one pixel. Besides, no spatial distortions occur no matter how the frame rate and scanning velocity change. Furthermore, the Fourier phase image of the reconstructed LST reaches the diameter-to-depth ratio of 1.25 when inspecting a planar specimen with flat-bottom holes.

Water target recognition is a critical challenge for the perception technology of unmanned surface vessels (USVs). In the application of USV, detection accuracy and the inference time both matter, while it is tough to strike a balance and single-frame water target detection behaves unstable in the video detection. To solve these problems, many strategies are applied to increase YOLOv4’s performance, including network pruning, the focal loss function, blank label training, and preprocessing with histogram normalization. The optimized detection method achieves a mean average precision (mAP) of 81.74% and a prediction speed of 26.77 frames per second (FPS), which meets the USV navigation requirements. To build the integrated USV-based system for water target recognition, a water target dataset containing 9936 images is created from offshore USV experiments in which the human-in-the-loop annotation and mosaic data augmentation methods are used. The issues of miss detection and false alarm can be considerably mitigated by cascading the Siamese-RPN tracking network, and the major color of a water target can be retrieved using a local contrast saliency color detection scheme. The system being tested is called “ME120” includes an embedded edge computing platform (Nvidia Jetson AGX Xavier). Finally, online dataset learning demonstrates the improved YOLOv4 achieves an increase of 66.98% in FPS at the cost of a decrease of 0.79% in mAP when compared with the original YOLOv4 and offline navigation experiments validate that our system achieves high recognition capability while maintaining a high degree of robustness.

Recent advancements in machine learning (ML) have led to state-of-the-art performance in various domain-specific tasks, driving increasing interest in its application to non-destructive testing (NDT). Among NDT techniques, phased array ultrasonic testing (PAUT) is an advanced extension of conventional ultrasonic testing (UT). This article provides an overview of recent research advances in ML applied to PAUT, covering key applications such as phased array ultrasonic imaging, defect detection and characterization, and data generation, with a focus on multimodal data processing and multidimensional modeling. The challenges and pathways for integrating the two techniques are examined. Finally, the article discusses the limitations of current methodologies and outlines future research directions toward more accurate, interpretable, and efficient ML-powered PAUT solutions.