Micro-crack detection is an essential task in critical equipment health monitoring. Accurate and timely detection of micro-cracks can ensure the healthy and stable service of equipment. Aiming at improving the low accuracy of the conventional target detection model during the task of detecting micro-cracks on the surface of metal structural parts, this paper built a micro-cracks dataset and explored a detection performance optimization method based on Mask R-CNN. Firstly, we improved the original FPN structure, adding a bottom-up feature fusion path to enhance the information utilization rate of the underlying feature layer. Secondly, we added the methods of deformable convolution kernel and attention mechanism to ResNet, which can improve the efficiency of feature extraction. Lastly, we modified the original loss function to optimize the network training effect and model convergence rate. The ablation comparison experiments shows that all the improvement schemes proposed in this paper have improved the performance of the original Mask R-CNN. The integration of all the improvement schemes can produce the most significant performance improvement effects in recognition, classification, and positioning simultaneously, thus proving the rationality and feasibility of the improved scheme in this paper.

The use of static solution-assisted laser drilling can effectively improve hole roundness, decrease taper angle, and reduce recast layer thickness and hole wall slag adhesion. However, the enormous energy of the laser will evaporate the solution to form a suspension droplet and reduce the quality and efficiency of laser drilling. To deal with this defect, the mist-blowing method was used to reduce the influence of droplets on the taper angle and recast layer. In this work, the effect of wind speed on drilling quality was examined, and laser drilling in air, water, and NaCl solution was carried out to analyse the effect of solution composition on hole wall morphology. The results showed that a speed fan with a proper wind speed that disperses the droplets formed in the processing area can significantly reduce the refraction and scattering of the laser, and the taper angle and roundness of the drilling hole were also reduced by 15.6% and improved by 2.4%, respectively, under the wind speed of 2 m/s. The hole wall morphology showed a thicker recast layer and cracking in air, while it was thinner in water and there was little or no layer in the NaCl solution in the same current. When drilling in NaCl, the taper angle and roundness of the drilling hole were reduced by 4.13% and improved by 2.11%, respectively, compared to water. Due to the mechanical effect of the laser in the NaCl solution, the impact force on the material was much greater than that in water. The solution cavitation effect, generated by the absorption of laser energy, caused an explosive impact on the molten material adhered to the surface of the hole wall. Above all, drilling in the NaCl solution with a current of 200 A and a wind speed of 2 m/s was the optimal condition for obtaining the best processing quality.

During the rock-breaking process, severe vibration frequently leads to cutter system failures. The traditional cutter system is complicated in structure, and the cutter-changing operation is highly dependent on the manual operation, resulting in a low construction efficiency and a high risk. Thus, this paper designed an integrated cutter system with a simple structure, which lays a theoretical foundation for popularizing the cutter-changing robot. In the statics performance experiment, we built an integrated cutter system finite element model, calculated the stress value under a nominal load; manufactured the scaled cutter system based on the similarity principle, obtained the measured stress value through the load experiment; and verified the accuracy of this cutter system’s finite element model. In the dynamics experiment, we calculated the cutter system and each components dynamic response based on the concentrated mass method and the Newmark method, obtained the measured vertical vibration displacement through a scaled loading experiment and verified the correctness of the vertical dynamics model, and set the real disc cutter linear cutting load as the external excitation to verify the feasibility of the new cutter system design scheme.

Due to the harsh environment of high humidity and dust in tunnel construction, the vision measurement system needs to be equipped with an explosion-proof glass protective cover. The refractive effect of the plate glass window invalidates the pinhole model. This paper proposes a comprehensive solution for addressing the issue of plane refraction. First, the imaging model for non-parallel plane refraction is established based on dynamic virtual focal length and the Rodriguez formula. Further, due to the failure of the epipolar constraint principle in binocular vision systems caused by plane refraction, this paper proposes the epipolar constraint model for independent refractive plane imaging. Finally, an independent refraction plane triangulation model is proposed to address the issue of triangulation failure caused by plane refraction. The RMSE of the depth of field errors in the independent refraction plane triangulation model is 2.9902 mm before correction and 0.3187 mm after correction. The RMSE of the positioning errors before and after correction are 3.5661 mm and 0.3465 mm, respectively.

Detecting metal surface crack defects is of great significance for the safe operation of industrial equipment. However, most existing mainstream deep-object detection models suffer from complex structures, large parameter sizes, and high training costs, which hinder their deployment and application in frontline construction sites. Therefore, this paper optimizes the existing YOLO series head structure and proposes a lightweight detection head structure, ZoomHead, with lower computational complexity and stronger detection performance. First, the GroupNorm2d module replaces the BatchNorm2d module to stabilize the model’s feature distribution and accelerate the training speed. Second, Detail Enhanced Convolution (DEConv) replaces traditional convolution kernels, and shared convolution is adopted to reduce redundant structures, which enhances the ability to capture details and improves the detection performance for small objects. Next, the Zoom scale factor is introduced to achieve proportional scaling of the convolution kernels in the regression branch, minimizing redundant computational complexity. Finally, using the YOLOv10 and YOLO11 series models as baseline models, ZoomHead was used to replace the head structure of the baseline models entirely, and a series of performance comparison experiments were conducted on the rail surface crack dataset and NEU surface defect database. The results showed that the integration of ZoomHead effectively improved the model’s detection accuracy, reduced the number of parameters and computations, and increased the FPS, achieving a good balance between detection accuracy and speed. In the comparative experiment of the SOTA model, the addition of ZoomHead resulted in the model having the smallest number of parameters and the highest FPS, while maintaining the same mAP value as the SOTA model, indicating that the ZoomHead structure proposed in this paper has better comprehensive detection performance.

The tunnel construction area poses significant challenges for the use of vision technology due to the presence of nonhomogeneous haze fields and low-contrast targets. However, existing dehazing algorithms display weak generalization, leading to dehazing failures, incomplete dehazing, or color distortion in this scenario. Therefore, an adversarial dual-branch convolutional neural network (ADN) is proposed in this paper to deal with the above challenges. The ADN utilizes two branches of the knowledge transfer sub-network and the multi-scale dense residual sub-network to process the hazy image and then aggregate the channels. This input is then passed through a discriminator to judge true and false, motivating the network to improve performance. Additionally, a tunnel haze field simulation dataset (Tunnel-HAZE) is established based on the characteristics of nonhomogeneous dust distribution and artificial light sources in the tunnel. Comparative experiments with existing advanced dehazing algorithms indicate an improvement in both PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity) by 4.07 dB and 0.032 dB, respectively. Furthermore, a binocular measurement experiment conducted in a simulated tunnel environment demonstrated a reduction in the relative error of measurement results by 50.5% when compared to the haze image. The results demonstrate the effectiveness and application potential of the proposed method in tunnel construction.