With the rapid development of unmanned surfaces and underwater vehicles, fault diagnoses for underwater thrusters are important to prevent sudden damage, which can cause huge losses. The propeller causes the most common type of thruster damage. Thus, it is important to monitor the propeller’s health reliably. This study proposes a fault diagnosis method for underwater thruster propellers. A deep convolutional neural network was proposed to monitor propeller conditions. A Hall element and hydrophone were used to obtain the current signal from the thruster and the sound signal in water, respectively. These raw data were fast Fourier transformed from the time domain to the frequency domain and used as the input to the neural network. The output of the neural network indicated the propeller’s health conditions. This study demonstrated the results of a single signal and the fusion of multiple signals in a neural network. The results showed that the multi-signal input had a higher accuracy than the one-signal input. With multi-signal inputs, training two types of signals with a separated neural network and then merging them at the end yielded the best results (99.88%), as compared to training two types of signals with a single neural network.

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird’s eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

Damage to the surface construction of reinforced concrete (RC) will impact the security of the facility’s structure. Deep learning can effectively identify various types of damage, which is useful for taking protective measures to avoid further deterioration of the structure. Based on deep learning, the multi-convolutional neural network (MCNN) has the potential for identifying multiple RC damage images. The MCNN6 of this study was evaluated by indicators (accuracy, loss, and efficiency), and the optimized architecture was confirmed. The results show that the identification performance for “crack and rebar exposure” (Type B) by MCNN6 is the best, with an accuracy of 96.81% and a loss of 0.07. The accuracy of the other five types of damage combinations is also higher than 80.0%, and the loss is less than 0.44. Finally, the MCNN6 model can be used in the detection of various damage to achieve automated assessment for RC facility surface conditions.

The development of automated systems for detecting defects in and damage to buildings is ongoing in the construction industry. Remaining aware of the surface conditions of buildings and making timely decisions regarding maintenance are crucial. In recent years, machine learning has emerged as a key technique in image classification methods. It can quickly handle large amounts of symmetry and asymmetry in images. In this study, three supervised machine learning models were trained and tested on images of efflorescence, and the performance of the models was compared. The results indicated that the support vector machine (SVM) model achieved the highest accuracy in classifying efflorescence (90.2%). The accuracy rates of the maximum likelihood (ML) and random forest (RF) models were 89.8% and 87.0%, respectively. This study examined the influence of different light sources and illumination intensity on classification models. The results indicated that light source conditions cause errors in image detection, and the machine learning field must prioritize resolving this problem.

A network of high-frequency radars (HFRs) has been deployed around Taiwan. The wide-area data coverage is dedicated to revealing near real-time sea-surface current information. This paper investigates three primary objectives: (1) describing the seasonal current synoptic variability; (2) determining the influence of wind forcing; (3) describing the tidal current field pattern and variability. Sea surface currents derived from HFR data include both geostrophic components and wind-driven components. This study explored vector complex correlations between the HFR time series and wind, which was sufficient to identify high-frequency components, including an Ekman balance among the surface currents and wind. Regarding the characteristics of mesoscale events and the tidal field, a year-long high-resolution surface dataset was utilized to observe the current–eddy–tide interactions over four seasons. The harmonic analysis results derived from surface currents off of northeastern Taiwan during 2013 are presented. The results agree well with the tidal parameters estimated from tide-gauge station observations. The analysis shows that this region features a strong, mixed, mainly semidiurnal tide. Continued monitoring by a variety of sensors (e.g., satellite and HFR) would improve the understanding of the circulation in the region.

To enhance remote sensing for maritime safety and security, various sensors need to be integrated into a centralized maritime surveillance system (MSS). High-frequency (HF) radar systems are a type of mainstream technology widely used in international marine remote sensing and have great potential to detect distant sea surface targets due to their over-the-horizon (OTH) capability. However, effectively recognizing targets in spectra with intrinsic strong disturbance echoes and random environmental noise is still challenging. To avoid the above problem, this paper proposes an adaptive signal identification method to detect target signals based on a rapid and flexible threshold. By integrating a watershed segmentation algorithm, the subsequent direction result can be used to automatically compute the direction of arrival (DOA) of the targets. To assist in the orientation of the object, forward intersections are integrated with the technique. Hence, the proposed technique can effectively recognize vessel echoes with automatic identification system (AIS) verification. Experiments have demonstrated the promising feasibility of the proposed method’s performance.