The fifth-generation (5G) technology makes it widely applicable to connected vehicles. This would entail numerous transmitted data in communication networks and frequent information interactions between vehicles and other terminals, thus leading connected vehicles to be vulnerable to attacks from external communication interfaces. This paper analyzes potential security threats of 5G vehicular network and focuses on intrusion detection methods for in-vehicle networks. We choose four experiment scenarios from potential attacks for in-vehicle networks and collect real car data to compile various attack databases for the first time. In order to find appropriate methods to identify different attacks, four light-weight intrusion detection methods are presented to recognize abnormal behaviors of in-vehicle networks. Furthermore, our study undertakes the detection performance comparison between four detection methods with considering comprehensive evaluation metrics. The evaluation results provide optimal light-weight detection solution for in-vehicle networks. This paper facilitates the understanding of the advantages of the test methods in detection performance for in-vehicle networks and promotes the application of detection technology to deal with the security issues of automotive industry.

Acquiring large amounts of high-quality real sonar data for object detection of autonomous underwater vehicles (AUVs) is challenging. Synthetic data can be an alternative, but it is hard to generate diverse data using traditional generative models when real data are limited. This study proposes a novel style transfer method, i.e., the multigranular feature alignment cycle-consistent generative adversarial network (CycleGAN), to generate sonar images leveraging remote sensing images, which can alleviate the dependence on real sonar data. Specifically, we add a spatial attention-based feature aggregation module to preserve unique features by attending to instance parts of an image. A pair of cross-domain discriminators are designed to guide generators to produce images that capture sonar styles. We also introduce a novel cycle consistency loss based on the discrete cosine transform of images, which better utilizes features that are evident in the frequency domain. Extensive experimental results show that the generated sonar images have better quality than CycleGAN, with improvements of 15.2% in IS, 56.9% in FID, 42.6% in KID, and 7.6% in learned perceptual image patch similarity, respectively. Moreover, after expanding the real sonar dataset with generated data, the average accuracy of the object detector, e.g., YOLOv6, has increased by more than 48.7%, indicating the effectiveness of the generated sonar data by our method.

As external interfaces of vehicles multiply, information security of automobile network system has become increasingly troubling. Mounting attacks have raised the attention of researchers to seek optimal solutions. Therefore, they set forth attack detection to demonstrate the vulnerability of in-vehicle networks, yet most of them focus on packet information directly. This paper comprehensively analyzes the vulnerability of in-vehicle networks and investigates a unique detection method based on clock drift of electronic control units (ECUs). To investigate applications of the proposed method further, we take attack time and attack density into consideration and present different patterns of two typical attack scenarios, i.e., injecting attack and suspension attack. In addition, we develop a prototype for data acquisition in controller area network (CAN) and undertake substantial vehicle experiments. The results show that the attack detection method has advantages in both recognition accuracy and application range compared with the method based on information entropy theory. This research work is expected to contribute to the further development of attacks detection system applied in vehicular networks.

This article proposes an innovative energy management strategy for hybrid multi-source dump trucks operating under real slope conditions in mining areas. Although previous studies have addressed the energy management issues of hybrid vehicles, few studies have taken into account complex environmental factors such as slopes under actual working conditions. The article overcomes this limitation by integrating a radial basis function (RBF) neural network to directly and accurately predict future vehicle demand power, thereby optimizing the DP-MPC strategy and improving energy efficiency. The results indicate that, compared with the traditional MPC strategy, the proposed strategy reduces fuel consumption by 3.34% and engine start-stop events by 76.2%. Additionally, when compared with another strategy that uses historical data to predict future speed and slope, calculates the vehicle’s future power demand, and incorporates it into the DP-MPC algorithm, the proposed strategy achieves comparable fuel consumption while also reducing engine start-stop events by 69.7%. Notably, the average calculation time for each step is 43.85 ms, which is substantially less than the sampling time of 1 s. To further confirm the real-time performance of the strategy, a hardware-in-the-loop (HIL) test is conducted.

Inertial navigation system/Doppler velocity log (INS/DVL) integrated navigation is a mature underwater navigation method, where the initial alignment is a critical stage in its application. Alignment accuracy and alignment time are the main challenges for improving alignment performance. In this paper, the initial attitude estimation errors caused by acoustic outliers and limited observation time will be primarily investigated. To address this problem, a novel robust coarse alignment method is designed based on a globally optimal model, providing sufficient accuracy of initial attitude for fast alignment during the fine alignment stage. Additionally, to achieve fast dynamic alignment in a limited observation information environment, a dynamic alignment model based on time sequence reconstruction is proposed. The algorithm has been validated through simulations and field tests, demonstrating comparable accuracy to the current state-of-the-art approach as well as exhibiting better robustness and faster alignment speed under dynamic conditions.