To address the challenges of underwater target detection, including complex background interference, light attenuation, severe occlusion, and overlap between targets, as well as the wide-scale variation in objects, we propose MAS-YOLOv11, an improved model integrating three key enhancements: First, we introduce the C2PSA_MSDA module, which integrates multi-scale dilated attention (MSDA) into the C2PSA module of the backbone, enhancing multi-scale feature representation via dilated convolutions and cross-scale attention. Second, an adaptive spatial feature fusion detection head (ASFFHead) replaces the original head. By employing learnable spatial weighting parameters, ASFFHead adaptively fuses features across different scales, significantly improving the robustness of multi-scale object detection. Third, we introduce a Slide Loss function with dynamic sample weighting to enhance hard sample learning. By mapping the loss weights nonlinearly to detection confidence, this mechanism effectively enhances the overall detection accuracy. The experimental results demonstrate that the improved model yields significant performance advancements on the DUO dataset: the recall rate is enhanced by 3.7%, the F1-score is elevated by 3%, and the mAP@50 and mAP@50-95 attain values of 77.4% and 55.1%, respectively, representing increases of 3.5% and 3.3% compared to the baseline model. Furthermore, the model achieves an mAP@50 of 76% on the RUOD dataset, which further corroborates its cross-domain generalization capability.

Rock bolts, as a type of reinforcing element, are widely adopted in underground excavations and civil engineering structures. Given the importance of rock bolts, the research outlined in this paper attempts to develop a portable non-destructive evaluation method for assessing the length of installed rock bolts for inspection purposes. Traditionally, piezoelectric elements or hammer impacts were used to perform non-destructive evaluation of rock bolts. However, such methods suffered from many major issues, such as the weak energy generated and the requirement for permanent installation for piezoelectric elements, and the inconsistency of wave generation for hammer impact. In this paper, we proposed a portable device for the non-destructive evaluation of rock bolt conditions based on a giant magnetostrictive (GMS) actuator. The GMS actuator generates enough energy to ensure multiple reflections of the stress waves along the rock bolt and a lead zirconate titantate (PZT) sensor is used to detect the reflected waves. A new integrated procedure that involves correlation analysis, wavelet denoising, and Hilbert transform was proposed to process the multiple reflection signals to determine the length of an installed rock bolt. The experimental results from a lab test and field tests showed that, by analyzing the instant phase of the periodic reflections of the stress wave generated by the GMS transducer, the length of an embedded rock bolt can be accurately determined.

Aiming at the problems of inaccurate segmentation and low detection efficiency caused by irregular tumor shape and large size differences in brain MRI images, this study proposes a brain tumor segmentation algorithm, YOLO-BT, based on YOLOv11. YOLO-BT uses UNetV2 as the backbone network to enhance the feature extraction ability of key regions through the attention mechanism. The BiFPN structure is introduced into the neck network to replace the traditional feature splicing method, realize the two-way fusion of cross-scale features, improve detection accuracy, and reduce the amount of calculations required. The D-LKA mechanism is introduced into the C3k2 structure, and the large convolution kernel is used to process complex image information to enhance the model’s ability to characterize different scales and irregular tumors. In this study, multiple sets of experiments were performed on the Figshare Brain Tumor dataset to test the performance of YOLO-BT. The data results show that YOLO-BT improves Precision by 2.7%, Recall, mAP50 by 0.9%, and mAP50-95 by 0.3% in the candidate box-based evaluation compared to YOLOv11. In mask-based evaluations, Precision improved by 2.5%, Recall by 2.8%, mAP50 by 1.1%, and mAP50-95 by 0.5%. At the same time, the mIOU increased by 6.1%, and the Dice coefficient increased by 3.6%. It can be seen that the YOLO-BT algorithm is suitable for brain tumor detection and segmentation.

The logging while drilling (LWD) electromagnetic weak signal detection model of a Duffing oscillator based on a one-dimensional nonlinear oscillator is established. The influences of noise on Duffing oscillator dynamic behavior of periodic driving force are discussed and evaluate the oscillator weak signal detection mechanism based on a phase change trajectory diagram. The improved Duffing oscillator is designed and applied to detect the electromagnetic logging signal resistivity at the drill bit using the time-scale transformation method. The simulation results show that the nonlinear dynamic characteristics of the Duffing oscillator are very noticeable, the Duffing circuit is very sensitive to detect the tested signal, and it has a reasonable level of immunity to noise. The smaller the amplitude of the tested signal, the more sensitive the circuit is to the signal, the better the antinoise system performance, and the lower the signal-to-noise ratio (SNR).