For the maintenance of weathering steel structure facilities, it is necessary to evaluate the corrosion grade of the rust layer on the surface regularly. At present, corrosion grade classification of weathering steel is mainly based on visual inspection with the human eye. In this paper, a deep learning method using a convolutional neural network (CNN) to evaluate the corrosion grade of weathering steel is proposed to save time and manpower. Firstly, the image dataset of the corrosion steel plate was established using salt spray tests. Then, a CNN architecture named VGG-Corrosion was designed to evaluate the corrosion grade of the corroded steel plate. The effects of the learning rate, transfer learning, and batch size were also investigated to clarify the best hyperparameter configurations to train a powerful corrosion grade classification model. Under the best combination of considered hyperparameters, the mean average accuracy for the corrosion grade evaluation of the test results is 90.96%. The test results indicated that the CNN-based corrosion grade recognition for weathering steel plate is prospective, which would be helpful for safety evaluation of steel structures.

The paper established a computational model of aerodynamic noises for 3-train formation including 3 trains, 6 bogies and 2 windshields. Based on Lighthill acoustic theories, a wideband noise source model was used to recognize the aerodynamic noise source of the high-speed train. Aerodynamic pressures of the high-speed train were extracted and compared with experimental results. The change trends and values presented a good consistency, which indicated that the computational model in this paper was effective. Large Eddy Simulation (LES) and FW-H acoustic model was then used to conduct numerical simulation of aerodynamic noises of the high-speed train. Aerodynamic noise characteristics in the far field of the high-speed train were analyzed. Analyzed results showed that when the high-speed train was running at the speed of 250 km/h, main energy was concentrated within 1250-3150 Hz, and the noise was a wideband noise in the analyzed frequency. The longitudinal observation point was 25 m away from the track center line and 25 m away from the nose tip, and its sound pressure level reached the maximum value of 89.7 dBA, while the sound pressure level around six bogies reached local maximum. With the larger distance from the track center line, the sound pressure level at horizontal observation points presented a smaller attenuation. Incoming flow had a larger impact on aerodynamic noises around the train than the tail flow. The main noise sources of a high-speed train were located at nose tip and pilot of head train, the second noise source was bogies, and the third noise source was located at train connections.

In this paper, a series of numerical experiments are carried out on the anti-scour device combined with perforated baffle and ring-wing plate. In addition, the optimal dimensions and location of the combined device are obtained: The perforated ratio of the baffle is S = 20%, the distance from the center of the bridge pier is L = 2d (d is the diameter of the bridge pier), and the ring-wing plate is located at H = 1/3h (h is the water depth). To verify the effect of the anti-scour device, the scour characteristics and flow field are further investigated. Compared with single pier and single ring-wing plate, the results revealed that the combined device with the optimal dimensions is of great anti-scour performance. Moreover, the maximum scour depth at the front and side of the pier reduced by 84.20% and 78.95%, which is better than the single ring-wing plate and other combined conditions in the orthogonal experiments. Due to the diversion of perforated baffle and ring-wing plate, the flow velocity at the pier side near the bed surface decreases by 30.7%, and the down-flow is almost eliminated on the vertical plane. Furthermore, the turbulent kinetic energy at different horizontal and vertical planes is reduced due to the reduction in horseshoe vortex and wake flow. Based on the investigation presented herein, the combined device is a promising tool for mitigating scour around the bridge pier.

In order to reduce the local scour before the antiscour device of piers, this paper proposed an improvement on a “V‐type” device. That was to say, wing plates were set on the surface of the “V‐type” device to enhance the diversion and reduce the local scour. To explore the protection effect of the modified device, the inclination angles of the wing plates were set to three angles, and the scour characteristics around the device were studied through the flume scour test and numerical simulation test. The results showed that the wing plates can reduce the impact force of the diving flow which was at the front end of the protective device. Besides, they could also disturb the flow around both sides of the device and weaken its sediment carrying capacity. Thus, the local scour around the device was effectively reduced. Especially, when the wing plates were 30°, the performance of reducing the local scour was the best.

Based on the engineering background of a new type of segmental-assembled steel temporary beam buttress, the fatigue strength evaluation method of the steel box girders with open longitudinal ribs was taken as the research objective. The fatigue stress calculation analysis and the full-scale fatigue loading test for the steel box girder local component were carried out. The accuracy of the finite-element model was verified by comparing it with the test results, and the rationality of the fatigue strength evaluation methods for welded joints was deeply explored. The results indicate that the maximum nominal stress occurs at the weld toe between the transverse diaphragm and the top plate at the edge of the loading area, which is the fatigue-vulnerable location for the steel box girder local components. The initial static-load stresses at each measuring point were in good agreement with the finite-element calculation results. However, the static-load stress at the measuring point in the fatigue-vulnerable position shows a certain decrease with the increase in the number of cyclic loads, while the stress at other measuring points remains basically unchanged. According to the finite-element model, the fatigue strengths obtained by the nominal stress method and the hot-spot stress method are 72.1 MPa and 93.8 MPa, respectively. It is reasonable to use the nominal stress S-N curve with a fatigue life of 2 million cycles at 70 MPa and the hot-spot stress S-N curve with a fatigue life of 2 million cycles at 90 MPa (FAT90) to evaluate the fatigue of the welded joints in steel box girders with open longitudinal ribs. According to the equivalent structural stress method, the fatigue strength corresponding to 2 million cycles is 94.1 MPa, which is slightly lower than the result corresponding to the main S-N curve but within the range of the standard deviation curve. The research results of this article can provide important guidance for the anti-fatigue design of welded joints in steel box girders with open longitudinal ribs.

At present, the level of bridge crack detection is not high. In order to solve the problems of weak robustness of traditional image processing methods and time-consuming and laborious manual detection, a pixel level detection algorithm of bridge cracks based on adding residual block is proposed, which provides more intuitive and accurate detection results for bridge health assessment. Firstly, the concrete beam slab crack data set with a certain amount of data is built to train and test the model. After comparing and analyzing the four learning rates, 2×10⁻⁴ is chosen as the initial learning rate. Finally, in the aspect of fracture segmentation, the model proposed in this paper has good performance and good crack identification effect. It can accurately and efficiently locate, classify and identify fractures, which has certain practical application value.