The traditional operational maintenance (O&M) tasks for marine equipment involve the continuous collection of operational status data and full data transmission between the ship and shore. While this method provides comprehensive monitoring information, it often incurs significant data monitoring, storage, and transmission costs. These issues are particularly pronounced in marine environments where bandwidth is limited or the power supply for monitoring devices is constrained. This study proposes a Deep Learning-based method for Dynamic Collection of operational maintenance data and Transmission of data features between the Ship and Shore, termed the DLDCTSS. By employing a deep learning anomaly detection model, DLDCTSS establishes a closed-loop feedback mechanism for dynamic sampling. Specifically, vibration sensors are activated for data collection only when abnormalities are detected, and critical state feature data are selectively transmitted based on O&M requirements. A theoretical analysis demonstrates that the DLDCTSS approach effectively reduces onboard storage overhead, lowers communication energy consumption between ship and shore, and improves data transmission efficiency, cutting overall system expenses. This study first assesses various anomaly detection models on open-source datasets, evaluating their suitability in maritime contexts. Subsequently, tests on a custom water-lubricated stern bearing platform validate both the anomaly detection model and the DLDCTSS approach. This dynamic sampling strategy not only diminishes redundant data collection but also ensures vital information is captured at critical moments, maximizing monitoring quality while enhancing operational efficiency. Meanwhile, transmitting only essential feature data markedly lowers bandwidth usage, and onboard feature extraction safeguards data privacy and security, meeting shipowners’ requirements.

In the domain of autonomous ship navigation, the construction of bird’s-eye view (BEV) layouts for waterways has obvious significance. A helmsman can generate the BEV layout of the waterway using his/her eyes only. To simulate this intelligence, a novel neural network-based algorithm named Waterway-BEV is proposed, which enables reconstructing a local map formed by the waterway layout and ship occupancies in the bird’s-eye view given a first person view monocular image only. Waterway-BEV employs an efficient SEResNeXt encoder to extract features from first person view (FPV) monocular images, capturing deep semantic information related to waterways and ships. Due to the variations in information across different perspectives, Waterway-BEV incorporates a Cross-View Transformation Module, which takes the constraint of cycle consistency between views into account and makes full use of their correlation to strengthen the view transformation and scene understanding. To fully leverage the feature output of the SEResNeXt encoder, Waterway-BEV employs a decoder based on a dedicated lightweight network. This decoder is responsible for decoding the enhanced bird’s-eye view (BEV) feature maps and generating the BEV layout. By employing the Focal Loss as the loss function for model optimization, Waterway-BEV takes into account the quantity and classification difficulty of ship samples during the training process, thereby improving the generation performance and convergence speed. The experiments demonstrated that Waterway-BEV achieved notable performance metrics, with mIOU and mAP rates reaching 97.8% and 98.2%, respectively, in waterway bird’s-eye view layout generation. Waterway-BEV outperformed other state-of-the-art (SOTA) algorithms in generating BEV layouts of waterways. In particular, during specialized scenarios such as crossroads of waterways and tasks involving small target ships, Waterway-BEV consistently generated satisfactory bird’s-eye view layouts, demonstrating robustness and applicability.

High-quality ship kinematic information (i.e., speed and heading) is important for Vessel Traffic Service (VTS) to assess traffic situation. Presently, the ship speed and heading are derived from the Automatic Identification System (AIS) and radar signal transmission in VTS. However, there are uncertainties on ship speed and heading estimation caused by the false echo in radar images and packet loss rate in AIS data transmission, which affects the supervision of ship navigation and its safety. To address the uncertainty on ship speed and heading estimation and enhance the supervision of the marine traffic system, this paper proposes a ship speed and heading estimation approach by using radar sequential images and AIS data fused. The proposed approach consists of three steps: 1) ship detection using radar sequential images, 2) ship tracking with inter-frame information, and 3) ship speed and heading fusion. The experimental results in selected radar sequential images of the Yangtze River show that the variance of ship speed and heading distribution at 10s sampling frequency reduce from 2.55 to 0.38, and 28.35 to 23.48, respectively. It is indicated that the proposed approach can reduce the uncertainty on ship speed and heading estimation and quantitatively describe the ship navigation status.

This paper proposes an approach to estimate ship dynamic features (i.e., speed and heading) using radar sequential images, which can be used to assess the ship-ship collision risk in vessel traffic service (VTS) center. The proposed approach estimates the ship speed and heading in three steps, including ship detection, tracking, and data fusion. First, the ship target, together with its center coordinate, is detected by introducing the background subtraction detector in each radar image. Second, the ship position in one frame is mapped to the consecutive frame, and ship trajectory distribution is established using the Kalman filter and Hungarian algorithms. Third, fuzzy logic is introduced to fuse data from radar and AIS. Specifically, input variables include two parameters, which are the ship speed/heading difference in consecutive frames using radar and AIS, respectively. The variance of ship speed distribution is 1.30 at 10s sampling frequency, and the variance of ship heading distribution is 26.53, the experimental results indicate that the proposed approach can accurately estimate ship speed and heading in the radar sequential images of the Yangtze River. The strength of the proposed approach is its capability to estimate the ship speed and heading quantitatively from radar sequential images, which is interactive and interpretable for VTS operators.

Take a dual-winding permanent magnet fault tolerant motor (FTPMM) in the ship shaftless rim-driven thruster (RDT) as the research object, the position sensorless control algorithm based on high frequency (HF) current injection is presented to estimate the rotor position and the rotor position signal is extracted from the voltage. In order to reduce influences of proportional-integral (PI) controller, current regulators and voltage calculation errors, the generalized second-order integrator (SOGI) is discussed along with how to combine with the low-speed sensorless control. And the current vector fault-tolerant control strategy is applied to compensate for the faulty phase current with other healthy phase currents. The rotor position at low speed is estimated under healthy as well as open-circuit faulty conditions by using the HF current injection algorithm based on SOGI (HF-SOGI). After simulation in Matlab/Simulink, the experimental results further demonstrate the feasibility of the HF-SOGI strategy by the FTPMM experimental setup. It can be calculated that the rotor speed ripple is decreased obviously after fault-tolerant control strategy is applied. It can be concluded that the HF-SOGI strategy can estimate the position accurately, which can further improve the reliability and application scope of FTPMM and the RDT system.

This paper proposes a new belief rule-based (BRB) expert system for fault diagnosis of marine diesel engines. The expert system is the first of its kind that consists of multiple concurrently activated BRB subsystems, in which each subsystem has its distinctive outputs and uses the evidential reasoning approach for inference. This novel modeling approach can be applied to identify fault modes that may co-exist. In essence, the group of BRB subsystems is used to model the nonlinear relationships between the fault features and the fault modes in marine diesel engines. The initial BRB expert system can be established by using expert experience and then optimized by using the data samples accumulated during the operation of marine diesel engines. Due to limitations in knowledge and data collected, ignorance is also considered in some BRB subsystems. The proposed BRB expert system is applied to abnormal wear detection for a kind of marine diesel engine. The performance of the BRB expert system is investigated in comparison with that of artificial neural network (ANN) models, support vector machine (SVM) models, and binary logistic regression model with fivefold cross-validation. The results show that the BRB expert system can be used for fault diagnosis of marine diesel engines in a probabilistic manner, which outperforms the ANN models, SVM models, and the binary logistic regression model in terms of accuracy and stability, and can effectively identify concurrent faults.

This paper presents a novel cooperative unmanned surface vehicle-unmanned aerial vehicle (USV-UAV) platform to form a powerful combination, which offers foundations for collaborative task executed by the coupled USV-UAV systems. Adjustable buoys and unique carrier deck for the USV are designed to guarantee landing safety and transportation of UAV. The deck of USV is equipped with a series of sensors, and a multiultrasonic joint dynamic positioning algorithm is introduced for resolving the positioning problem of the coupled USV-UAV systems. To fulfill effective guidance for the landing operation of UAV, we design a hierarchical landing guide point generation algorithm to obtain a sequence of guide points. By employing the above sequential guide points, high-quality paths are planned for the UAV. Cooperative dynamic positioning process of the USV-UAV systems is elucidated, and then UAV can achieve landing on the deck of USV steadily. Our cooperative USV-UAV platform is validated by simulation and water experiments.

Accidents such as those caused by rollovers and sideslips in complex driving environments involving heavy-duty vehicles (HDVs) often have serious consequences. Such accidents can be due to many factors. In this paper, a probabilistic method for predicting and preventing these accidents is presented. First, a specific vehicle dynamics model based on various random parameters that consider the wind velocity and road curvature is developed. Second, a safety margin function is defined to divide the safe and dangerous domains in the parameter space. Then, the first-order reliability method and second-order reliability method approximations are developed to evaluate the probability of such an accident by using the vehicle dynamics model. Finally, the probability model is applied to explore the interrelations and sensitivities of those parameters with regard to their effects on the accident probability in different scenarios. The study suggests that the presented probabilistic methodology can effectively estimate rollovers and sideslips of HDVs in complex environments, which represent a challenge for the prediction of accidents based on sensors alone.

In this study, we developed a microcosmic mobile emissions model based on an intelligent agent model of vehicles. The intelligent agent was first introduced into a micro-traffic flow system. Individual differences in driver behavior were considered, and the theory of probability was applied to reflect the distribution of drivers' stochastic characteristic dispositions. Each vehicle expressed its intelligence through its own character by perceiving the leading vehicle. From an operational perspective, differences in drivers' dispositions were reflected by a weighted coefficient. Finally, a hybrid microcosmic mobile emissions model was proposed. Its coefficients were determined using traffic data and experiments. Because it addresses more aspects of the car-following process, this model is theoretically superior to previous models, as verified by a numerical simulation. The proposed model was applied to a case study of the emissions from ten vehicles in an urban setting. The model effectively estimated mobile emissions rates. The results indicate that the model can reflect individual differences among drivers and demonstrate that reckless drivers generate more emissions.