An Adversarial Dual-Branch Network for Nonhomogeneous Dehazing in Tunnel Construction.

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.

Fretting Fatigue Life Prediction of Dovetail Structure Based on Plastic Effect and Sensitivity Analysis of Influencing Factors.

Micro relative sliding exists on the contact surface of the main primary equipment's surface structures, resulting in serious fretting fatigue. The plastic effect causes serious fatigue to the structure under alternating loads. Existing fatigue life prediction models fail to fully consider the shortcomings of fretting and plastic effects, which causes the prediction results to be significantly different to real-lifeworld in engineering situations. Therefore, it is urgent to establish a fretting damage fatigue life prediction model of contact structures which considers plastic effects. In this study, a plastic fretting fatigue life prediction model was established according to the standard structural contact theory. The location of dangerous points was evaluated according to a finite element simulation. The cyclic load maximum stress value was compared with the fretting fatigue test data to confirm the error value, and the error between the proposed fretting fatigue life model and the test value was within 15%. Concurrently, we combined this with mass data analysis and research, as it is known that the contact zone parameters have an impact on fretting fatigue and affect the structural lifespan. With the help of ABAQUS, the fretting numerical calculation of the dovetail tenon model was carried out to analyze the sensitive factors affecting the fretting fatigue life of the dovetail tenon structure. By keeping the fretting load unchanged, the contact area parameters such as contact surface form, contact area width and friction coefficient were changed in order to calculate the fretting stress value, σfretting and the dovetail structure was improved to extend its fretting fatigue life. Finally, it was concluded that fretting fatigue was most sensitive to the width and contact form of the contact area. In actual engineering design, multiple factors should be considered comprehensively to determine a more accurate and suitable width and form of the contact area. For the selection of friction coefficient, on the premise of saving costs and meeting the structural strength requirements, the friction coefficient should be as small as possible, and the problem can also be solved through lubrication during processing.

An Improved Mask R-CNN Micro-Crack Detection Model for the Surface of Metal Structural Parts.

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.

Vision Measurement Method Based on Plate Glass Window Refraction Model in Tunnel Construction.

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.