Abstract:To study the temperature field distribution and structural damage characteristics of hollow slab channel bridges under oil pool fire scenarios, FDS was used to analyze the temperature field distribution at the bottom of hollow slab channel bridge under different oil pool fire scenarios. ABAQUS was used to conduct heat conduction analysis on the most unfavorable hollow slab girder in all fire scenarios, and the internal temperature field of the girder was obtained. Finally, based on the equivalence principle of cross sectional virtual layer due to the reduction of the strength, the fire damage degree was calculated. The results showed that the smaller the span of hollow slab channel bridge, the larger the bridge vertical clearance and the larger the area of the oil pool, the higher the temperature at the girder bottom.The influence of girder bottom width on temperature field of girder bottom is not significant. When the wind speed is small, the maximum temperature at the girder bottom will increase, but when the wind speed is too large, the flame will be blown out of the channel bridge, resulting in lower temperature at the girder bottom. Meanwhile, according to the damage data of steel strands, steel bars and concrete virtual layers, the prediction formula of flexural capacity retention rate of hollow slab girder under oil pool fire is established in stages. The research results can provide reference for the post-disaster assessment, formulation of plans to reinforcement and repair, and fire prevention measures research of the channel bridges.

Abstract:To address the parameter optimization problem in the three-bench excavation method for tunnels in shallow-buried soft surrounding rock (Class V), the following influencing factors were selected: the ratio of bench advance to half-span R, cohesion, internal friction angle, elastic modulus of the surrounding rock, and Poisson's ratio. Through multi-level orthogonal finite element analysis and design, the crown settlement values corresponding to different parameter combinations were obtained. An adaptive particle swarm optimization (APSO algorithm) was applied to optimize the surrounding rock parameters, ultimately establishing an optimized relationship between surrounding rock settlement and the advance length per stage in the three-bench excavation method. Using Poisson's ratio as an influencing factor, multi-level orthogonal finite element analysis was employed to determine the crown settlement values under various parameter combinations. An APSO-optimized support vector regression (SVR) model was developed to construct a prediction model for crown settlement during three-bench excavation. A comparative analysis was conducted using a conventional SVR model. Furthermore, an APSO-SVR model was established with crown settlement as the input and the strength ratio R, cohesion, internal friction angle, elastic modulus, and Poisson's ratio as outputs, enabling the inversion of ratio R. Based on an actual engineering case, multi-level orthogonal finite element analysis was applied for inversion analysis. Using the same project, Midas software was utilized to validate the accuracy of the limiting advance distance parameters in the sequential excavation process. The results show: the APSO-SVR model has lower error and higher accuracy than the SVR model, validating its optimization. Midas inversion shows a 0.72% difference between the simulated and specified arch top settlement values, confirming the optimized parameter scheme's accuracy. The inversion optimization model based on APSO-SVR for three-bench excavation has high accuracy and can guide similar project safety construction.

Abstract:On curved slopes covered with water, snow or ice, vehicles are prone to skidding and losing control during braking, which is a critical traffic safety issue that needs to be addressed in rainy or cold regions. The characteristics of tire-road friction capacity demand of vehicles on low-friction curved slopes were first analyzed. Based on this, the geometric design parameters of highway horizontal alignment, vertical alignment, and cross slope—were integrated with driving mechanical factors such as road friction coefficient, tire rolling resistance, and aerodynamic drag to derive the relationship between vehicle speed and maximum achievable braking deceleration. Considering the braking slip ratio, a predictive model for the minimum braking distance on low-friction curved slopes was proposed, and the model was validated through CarSim-based vehicle dynamics simulations. The study can provide a reference for the coordinated optimization of speed and braking deceleration of autonomous vehicles on low-friction curved slopes, and also offer support for car-following safety assessment and risk warning on interchange ramps in rainy or snowy regions.

Abstract:Aiming at the problems of low efficiency, high cost and poor real-time performance of traditional pavement detection vehicles, a lightweight edge real-time detection method for low-grade pavement distresses is proposed. This method adopts a novel YOLO-Trip model to efficiently extract color and spatial features, and integrates TensorRT technology to achieve real-time detection on the edge. For the existing mileage measurement challenge, an IMU and GNSS self-calibrated high-frequency odometer is designed, combined with Kalman filter and linear interpolation algorithm to realize ultra-high-frequency mileage measurement. A low-power onboard edge computing platform is built to collect and detect road surface images in real time without additional power supply. In the mileage measurement comparison experiment, the maximum sampling error of the system is only 0.9% different from that of the wheel encoder in the speed range of 0~40 km/h, which is significantly better than the single GNSS scheme. The model comparison experiment shows that the YOLO-Trip model leads the benchmark model by in recall rate and average precision, while the parameter quantity and the computational load are reduced, which alleviates the edge computing pressure. The system can detect transverse cracks, longitudinal cracks, alligator cracks and potholes and other diseases in real time, and accurately record the location information, which is suitable for rural concrete roads and mountainous asphalt roads, providing data support for road maintenance.

Abstract:To address the limitations of existing path-planning methods applied to unmanned construction site, particularly their insufficient consideration of equipment geometry and kinematic characteristics, as well as the absence of effective multi-machine coordination, this study proposes a cooperative path-planning approach based on an improved RRT* algorithm. First, mobile construction equipment is modeled as the generalized rectangle in the top-down plan, and collision-detection strategies for both linear motion and rotational motion are developed using the separating axis theorem and vector cross-product operations. Second, a time-window mechanism and a spatiotemporal coordination framework are introduced to design two types of dynamic conflict-detection procedures, namely “straight-line-straight-line motion” and “straight-line-rotation motion”, enabling real-time collision avoidance among multiple machines. Finally, the proposed algorithm is validated through simulations in complex scenarios such as tunnels and beam fabrication yards. The results demonstrate that the planned paths fully account for the actual equipment geometry, dimensions, rotation constraints, and obstacle characteristics (shape, size, and distribution). Compared with conventional algorithms, the proposed method effectively resolves the challenge of obstacle avoidance for large length-width ratio equipment operating in narrow spaces, significantly improving path-search success rates and robustness in complex environments. Furthermore, the constructed spatiotemporal collaborative planning framework ensures that multiple machines can safely, orderly, and efficiently move or operate in complex construction site environments. This research not only verifies the applicability of the algorithm in real engineering contexts, such as tunnels and beam yards, but also provides essential theoretical and technical support for future intelligent and efficient multi-machine collaboration in unmanned construction sites.

Abstract:As expressways age, routine maintenance has become a critical aspect of expressway operations. However, such maintenance often necessitates partial lane closures, which can lead to traffic congestion and heightened safety risks. To address these challenges, this study proposes four optimized strategies for the deployment of safety facilities in work zones, drawing on prior research in this area. These strategies include the work area safety facilities logo plus red flag, road laying red strobe lights, the whole process to provide voice navigation and warning strategies comprehensive optimization scheme. To assess the effectiveness of each strategy, a driving simulation experiment was conducted. Driver behavior data were collected and analyzed to evaluate the impact of the different safety configurations on driving performance. The rank sum ratio (RSR) comprehensive evaluation method was used to assess and compare the performance of each scheme. The results show that the comprehensive optimization scheme of adding red flags to the safety facilities signs in the work area, laying red strobe lights on the road surface and providing voice navigation throughout the whole process has the highest improvement in driver safety. These findings suggest that integrating voice navigation into safety systems may further enhance safety in expressway work zones.

Abstract:During the regular heavy passenger flow periods in the morning peak of urban rail transit, stations become crowded, prompting managers to commonly adopt station flow restriction strategies, resulting in distinct preferences and heterogeneity in passenger travel behavior. To gain a deeper understanding of the travel time choice behavior of different passenger groups during the morning rush hour and the mechanism of flow restriction strategies, this paper considers individual attributes, travel characteristics, and attitudinal preferences. It designs a questionnaire on passengers' willingness to choose travel times, taking into account different planned travel times and commuting durations as scenarios. Based on the questionnaire survey results of Shanghai Metro, age, passenger expected arrival time elasticity, and congestion sensitivity were selected as characteristic variables reflecting passenger heterogeneity. Subsequently, a multinomial logit model for passenger travel time selection and a mixed logit model considering passenger heterogeneity were constructed. The model parameters are estimated using Biogeme software. The results indicate that, among all characteristic variables, travel duration has the most significant impact on passengers' travel time choices. Passengers are more inclined to avoid flow restriction when their planned departure times are closer to the start or end of flow restriction periods and when their commuting durations are longer. The analysis of individual heterogeneity reveals that passengers with flexible arrival times are more willing to adjust their travel times to avoid flow restriction or train congestion. Passengers with higher congestion sensitivity and younger passengers pay more attention to the number of people waiting in line.

Abstract:To improve the accuracy and robustness of fault diagnosis for metro train bogies, a multi-sensor information fusion diagnosis method combining convolutional neural network (CNN) and an improved graph convolutional network (GCN) is proposed. First, vibration signals collected from multiple sensors are transformed into time-frequency maps using continuous wavelet transform. Then, a five layers CNN is employed to extract features from each channel's time-frequency map, where each sensor is treated as a node in a graph and the extracted features serve as node attributes for the GCN. To overcome the limitation of traditional GCN with fixed adjacency matrices that fail to reflect dynamic relationships among nodes, a multilayer perceptron (MLP) is designed to adaptively update adjacency weights based on node features, enabling dynamic graph convolution. Finally, fault classification is performed through two GCN layers followed by a classification head. Experiments demonstrate that the proposed method achieves an average diagnostic accuracy of 99.46%, and the maximum accuracy can reach 100% under some working conditions, significantly outperforming existing models such as single-channel CNN, CNN-LSTM, CNN-Transformer, MSSCNN. The confusion matrix and t-SNE visualization results show clearly clustered fault features with a misclassification rate below 1%. The study shows that the proposed method maintains excellent diagnostic accuracy and stability under multiple operating conditions and fault modes, providing reliable technical support for the intelligent operation and maintenance of metro bogie systems.

Abstract:In order to perform structural fatigue analyses of vehicles, it is necessary to extrapolate the time-domain signals of dynamic stresses measured over a short period of time into a longer history using extrapolation techniques. Taking some measurement points of a certain locomotive body as an example, a method to determine the optimal threshold based on the entropy weight method and the Topsis method is proposed. Firstly, after the initial time-domain signal is pre-processed by de-zero drifting and other pre-processing, the entropy weighting method is used to assign weights to the threshold evaluation indexes of the peak-over-threshold (POT) model; secondly, the Topsis method of multiple indexes is used to conduct a comprehensive evaluation, and the optimal threshold is obtained by comparing the relative proximity. The parameters of generalized Pareto distribution were fitted to the excess of peak and valley values, and the extreme value was reconstructed and replaced the original samples to finally obtain the extrapolated samples. From the P-P and Q-Q plots, it can be seen that the peak and valley samples are fitted better; from the cumulative distribution plot, it can be seen that the extreme value of the sample after extrapolation by a factor of 5 and 10 becomes larger, and the curve is close to the actual sample curve. After the damage calculation of the time-domain signal after extrapolation, it is found that the fatigue life assessment method is more biased towards safety.

Abstract:SiC_p/Al composites demonstrate substantial potential for applications prospects in aerospace, rail transportation and other industries, owing to their low density, high specific strength, high specific modulus, excellent wear resistance and superior high-temperature performance. However, the significant disparities in physical and chemical properties between the reinforcing SiC phase and the Al matrix result in poor weldability, which severely hinders their adoption in engineering contexts. Laser welding has emerged as a highly promising joining technique for SiC_p/Al composites due to its benefits of high energy density, minimal heat-affected zones and precise processing control. This paper reviews the research progress in laser welding technology for SiC_p/Al composite materials, explores the main challenges it faces, summarizes the existing process optimization strategies, and focuses on analyzing the interface reaction mechanism of the weld seam, methods for interface structure control, and their impact on weld seam performance. It also elaborates on the related strengthening mechanisms. Finally, based on an analysis of the current research deficiencies and challenges, it prospects for future research directions, aiming to provide reference for the in-depth research and engineering application of this technology.

Abstract:K-means is a widely used and efficient unsupervised clustering algorithm. However, studies have shown that when dealing with high-dimensional or non-spherically distributed datasets, the K-means algorithm has significant limitations in determining the number of clusters and selecting initial centroids. To thoroughly explore and optimize the initial centroid selection mechanism and the problem of determining the number of clusters in the K-means algorithm, a K-means algorithm based on knowledge induction and useless center driven is proposed. This algorithm first introduces a detection mechanism for high-density knowledge points, constructs a candidate centroid set by identifying high-density knowledge points in the dataset; then infers the optimal number of clusters based on Gaussian mixture model theory; subsequently adopts a useless center screening strategy to optimally select the candidate centroids, and finally determines the optimal initial centroid set. Experiments on real datasets show that the proposed optimized algorithm generally outperforms other comparison algorithms in clustering performance. This algorithm effectively solves the clustering problem of non-spherical data distribution and exhibits relatively superior clustering performance in scenarios with complex data structures.