Effective infrastructure health monitoring is crucial within transportation cyber-physical systems, where accurate road health detection is vital for ensuring road safety and the stability of intelligent transportation systems. To address the challenges of identifying pavement subsurface objects using 3D ground penetrating radar (GPR) data, we propose a multi-perspective cascading recognition method that integrates B-scan and C-scan images. This method is built on a lightweight dual-stream semantic segmentation model called AttnGPRNet, developed in this work to improve feature extraction through attention mechanisms and enhance subsurface object recognition. Initially, the model segments B-scan images to identify potential target regions, followed by more precise segmentation of 3L-C-scan images based on preliminary results. Additionally, we constructed a multi-view dataset using 3D GPR scans from over 100 kilometers of urban roads and evaluated the effectiveness of the proposed method through experiments. Experimental results show that our model outperforms existing advanced methods, achieving mIoU of 78.80% and 83.96% on B-scan and 3L-C-scan, and F1 scores of 87.65% and 91.07%, respectively. Moreover, the method has been deployed in Xiaoning Road GPR image intelligent recognition system and verified through on-site drilling, demonstrating its practical potential for road health monitoring.

Quadrotor UAV has a strong mobility and flexibility in flight and has been widely used in military and civil fields in recent years. An adaptive backstepping sliding mode control (ABSMC) method is proposed to address the trajectory tracking control problem of quadrotor UAV based on actuator fault and external disturbance. In the proposed method, the switching gain of adaptive sliding mode control is constructed in the backstepping design process in order to suppress the chattering effect of sliding mode control effectively by differential iteration. Firstly, the dynamic model of quadrotor UAV with actuator fault and external disturbance is proposed, and then the controllers are designed based on the ABSMC method. Finally, the comparison experiments between sliding mode control (SMC) method and ABSMC method show that the ABSMC method can not only effectively suppress the chattering problem for the SMC method but also perform a perfect control effect.

Despite the success of Generative Adversarial Networks (GANs), little work has focused on the discrepancy between real and generated images in frequency domain. In this work, we provide a systematic analysis on this topic. We first demonstrate the general existence of the frequency discrepancy and further perform extensive experiments both on datasets with various frequency distributions and models with different upsampling methods to reveal the sources of the discrepancy. Experimental results show that: resize-convolution is not a perfect alternative to deconvolution, and natural images and unnatural images should be treated separately during training. Based on these studies, we provide some novel solutions to reduce the discrepancy. Finally, we further show the effectiveness of our solutions on Variational Auto Encoders (VAEs). We hope that the community should pay equal attention to the performance of generative models both in spatial and frequency domain.

To address the severe damage caused by voids beneath cement concrete pavement slabs, which compromise pavement performance and lifespan, there is an urgent need to develop an economical and efficient grouting material for slab void repair. This study employed a two-step orthogonal experiment design (OED) method to optimize the composition of grouting material. Results show that the plain cement mortar achieves the best flowability, setting time, compressive strength, or flexural strength when the water-to-binder ratio is 0.375, with 20% quartz sand, 2% coal ash, and 5% ground calcium carbonate. For the high-performance cement mortar developed, the optimal water-to-binder ratio is 0.35, with 0.5% redispersible latex powder, 0.2% polypropylene fiber, 0.6% water-reducing agent, 0.8% early-strength agent, and 2.0% expansion agent. Under these optimal conditions, the grouting material with a flowability of 15 s has a compressive strength and flexural strength of 76.98 MPa and 11.89 MPa, respectively, and achieves 77.4% of its 28-day compressive strength and 94.0% of its 28-day flexural strength by day 3. This grouting material also possesses a slight expansion within 0.1% at 3, 7, and 28 days, categorizing it as a micro-expansion mortar. The bond strength at the mortar-concrete interface exceeds the tensile strength of the mortar itself, ensuring no debonding at the interface before grouting material failure. The XRD, SEM, and infrared spectra results explain the early strength development mechanism of this cement mortar.

Aiming at the problems of simple, extensive, inefficient and high consumption of traditional agricultural production management in China, this paper takes the field management of vegetable industry as the starting point, and adopts intelligent, flat and interactive field production and management micro services by building a mobile "Internet+small programs". The system is based on microservice technology, which solves the problems of PaaS platform in dealing with high logic complexity of business system and low system performance, realizes application splitting and decoupling, and improves the ability of agile development and rapid deployment; For the needs of agricultural production materials and tasks, production status management, etc., production materials, tasks and labor assignments, work time limits, task prompts, etc. can be realized. Through hierarchical authorization, enterprise administrators, warehouse keepers, and workers can view relevant basic information and data online at any time, accurately understand the distribution of field management resources, and make field management traceable and refined.