The vibration signals for offshore wind-turbine high-speed bearings are often contaminated with noises due to complex environmental and structural loads, which increase the difficulty of fault detection and diagnosis. In view of this problem, we propose a fault-diagnosis strategy with good noise immunity in this paper by integrating the two-dimensional convolutional neural network (2DCNN) with random forest (RF), which is supposed to utilize both CNN’s automatic feature-extraction capability and the robust discrimination performance of RF classifiers. More specifically, the raw 1D time-domain bearing-vibration signals are transformed into 2D grayscale images at first, which are then fed to the 2DCNN-RF model for fault diagnosis. At the same time, three procedures, including exponential linear unit (ELU), batch normalization (BN), and dropout, are introduced in the model to improve feature-extraction performance and the noise immune capability. In addition, when the 2DCNN feature extractor is trained, the obtained feature vectors are passed to the RF classifier to improve the classification accuracy and generalization ability of the model. The experimental results show that the diagnostic accuracy of the 2DCNN-RF model could achieve 99.548% on the CWRU high-speed bearing dataset, which outperforms the standard CNN and other standard machine-learning and deep-learning algorithms. Furthermore, when the vibration signals are polluted with noises, the 2DCNN-RF model, without retraining the model or any denoising process, still achieves satisfying performance with higher accuracy than the other methods.

In recent years, with the deep exploitation of marine resources and the development of maritime transportation, ship collision accidents occur frequently, which leads to the increasingly heavy task of maritime Search and Rescue (SAR). Unmanned Aerial Vehicles (UAVs) have the advantages of flexible maneuvering, robust adaptability and extensive monitoring, which have become an essential means and tool for emergency rescue of maritime accidents. However, the current UAVs-based drowning people detection technology has insufficient detection ability and low precision for small targets in high-altitude images. Moreover, limited by the load capacity, UAVs do not have enough computing power and storage space, resulting in the existing object detection algorithms based on deep learning cannot be directly deployed on UAVs. To solve the two issues mentioned above, this paper proposes a lightweight deep learning detection model based on YOLOv5s, which is used in the SAR task of drowning people of UAVs at sea. First, an extended small object detection layer is added to improve the detection effect of small objects, including the extraction of shallow features, a new feature fusion layer and one more prediction head. Then, the Ghost module and the C3Ghost module are used to replace the Conv module and the C3 module in YOLOv5s, which enable lightweight network improvements that make the model more suitable for deployment on UAVs. The experimental results indicate that the improved model can effectively identify the rescue targets in the marine casualty. Specifically, compared with the original YOLOv5s, the improved model mAP@0.5 value increased by 2.3% and the mAP@0.5:0.95 value increased by 1.1%. Meanwhile, the improved model meets the needs of the lightweight model. Specifically, compared with the original YOLOv5s, the parameters decreased by 44.9%, the model weight size compressed by 39.4%, and Floating Point Operations (FLOPs) reduced by 22.8%.

Wireless monitoring systems for the marine environment are important for rapidly growing subsea developments. The power supply of wireless sensor nodes within the monitoring systems, however, is a major challenge. This study proposes a novel piezoelectric wave energy converter (pWEC) device to power the wireless sensing nodes. Unlike previous studies, the proposed device utilizes contactless pWEC technology in which a spring pendulum provides a two-stage frequency amplification of 3.8 times for low-frequency wave environments. The pWEC device consists of a floating body, inner pendulum, spring pendulum, magnets and piezoelectric sheets. In order to harvest the energy from relatively low frequency ocean waves, the pWEC device is designed to have an enhanced energy-capturing frequency. The effects of internal pendulum mass, spring pendulum weight, pendulum length and spring stiffness on wave energy absorption are investigated using theoretical and numerical analysis combined with laboratory experiments. The slider that drives the motion of the piezoelectric sheet vibrates at up to 3.8 times the wave frequency. To test the piezoelectric generators in the laboratory environment, a mechanical structure is set up to simulate the motion of the external floating body and the internal wave energy converter under the action of waves. When the four piezoelectric plates are arranged horizontally, the average output power per plate is increased by 2.4 times, and a single piezoelectric plate can generate an average of 10 mW of power. The proposed piezoelectric wave energy converter device has the potential to provide long-term energy supply for small ocean monitoring platforms at remote locations with reasonable wave energy resources.

Navigation safety is one of the primary operational requirements for unmanned surface vehicles (USVs) in a complex marine environment, mainly guaranteed by a reliable path planning system for collision avoidance. This work proposes a novel weighted sum multi-objective optimisation strategy for USV collision avoidance path planning in restricted waters. In particular, the coefficients of different objectives could be tuned to emphasise the most critical design consideration under varying navigation scenarios. Moreover, in addition to the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs), the terrain and weather constraints were also considered in the path planning system. The proposed USV collision avoidance path planning framework’s effectiveness was demonstrated through numerical simulations and hardware-in-the-loop (HIL) tests. The numerical simulation results indicate that the proposed method could avoid collision with dynamic and static obstacles, and it is also adaptive to different navigation restrictions and preferences. Moreover, a USV navigation platform was established by incorporating true Automatic Identification System (AIS) signals, and HIL tests were performed with real-time AIS data in a water channel in the Zhoushan archipelago. The results demonstrate that the proposed USV path planning strategy is applicable in restricted waters with complex terrains and weather constraints.

Liquified natural gas (LNG) manipulator arms have been widely used in natural gas transportation. However, the automatic docking technology of LNG manipulator arms has not yet been realized. The first step of automatic docking is to identify and locate the target and estimate its pose. This work proposes a petroleum pipeline interface recognition and pose judgment method based on binocular stereo vision technology for the automatic docking of LNG manipulator arms. The proposed method has three main steps, including target detection, 3D information acquisition, and plane fitting. First, the target petroleum pipeline interface is segmented by using a color mask. Then, color space and Hu moment are used to obtain the pixel coordinates of the contour and center of the target petroleum pipeline interface. The semi-global block matching (SGBM) algorithm is used for stereo matching to obtain the depth information of an image. Finally, a plane fitting and center point estimation method based on a random sample consensus (RANSAC) algorithm is proposed. This work performs a measurement accuracy verification experiment to verify the accuracy of the proposed method. The experimental results show that the distance measurement error is not more than 1% and the angle measurement error is less than one degree. The measurement accuracy of the method meets the requirements of subsequent automatic docking, which proves the feasibility of the proposed method and provides data support for the subsequent automatic docking of manipulator arms.

Wave energy is one of the most reliable and promising renewable energy sources that has attracted lots of attention, including piezoelectric wave energy harvesting devices. One of the challenges for piezoelectric wave power generation is the relatively low-frequency wave environments in the ocean. Magnetic excitations are one of the techniques used to overcome this issue. However, there is a lack of understanding of the mechanisms to maximize the electric power output of piezoelectric wave energy harvesters through magnetic excitations. In the present study, magnetic excitation experiments were conducted to investigate the power generation of a coupled spring pendulum piezoelectric energy harvester under various magnetic field conditions. Firstly, the mass of the load magnet that can induce the resonance phenomenon in piezoelectric elements was experimentally determined. Then, the power generation of piezoelectric elements was tested under different excitation magnetic spacings. Finally, the influence of different distribution patterns of excitation magnets on the performance of piezoelectric elements was tested. It was found that under the conditions of a load magnet mass of 2 g, excitation magnet spacing of 4 mm, and two excitation magnets stacked on the inner pendulum, optimum power generation of the piezoelectric wave harvester was achieved with a peak-to-peak output voltage of 39 V. The outcome of this study provides new insight for magnetic excitation devices for piezoelectric wave energy harvesting to increase the feasibility and efficiency of wave energy conversion to electrical energy.