Wave Tank Experiment for Sea State Monitoring with Distributed Acoustic Sensing

Monitoring sea states across the offshore wind farm areas is essential to keep their structures safe, efficiently operate the systems, and assess the environmental effects of wind turbines. Conventional sea state sensors like buoys limit their observable coverage; therefore, installing many sensors across the wide area is necessary to obtain sufficient sea state information. However, such a situation is not practical in terms of cost. Instead, the study proposes utilising optical fibres, which is embedded in existing power cables for telecommunications on the seabed, as sea state monitoring sensors with distributed acoustic sensing (DAS). DAS is a vibration-sensing technology along optical fibres based on the Rayleigh backscattering of the injected laser. It measures the dynamic strain of the optical fibre in real time at each spatial bin, which is called a "channel" along the fibre. In power cables on the seabed, time-varying water pressure due to waves is expected to exert dynamic strain. This hypothesis motivates us to validate whether the application of DAS for power cables can estimate sea state, such as wave period, height, and the direction of arrival. Hence, the authors carried out a wave tank experiment with a programmable wave generator. An actual power cable is installed under the same condition as the bottom-mounted offshore wind turbines. The experimental results show that (i) the wave period can be accurately estimated from the frequency-domain analysis. (ii) The strong linearity between DAS vibration power and the wave height is found. (iii) The direction of arrival of waves can be estimated with the error of 1.5$^\circ$ when there are at least two laying angles of the cable in parallel with the estimation of wavelength. These outcomes promote the feasibility of utilising the existing power cables across offshore wind farms as sea state monitoring sensors.

Monitoring exposure-length variations in submarine power cables using distributed fiber-optic sensing

This study proposes an anomaly-detection framework for monitoring exposure-length variations in submarine free-span cables using Distributed Acoustic Sensing (DAS), which is one of the distributed fiber-optic sensing technologies. To address environmental variability and limited training data in offshore environments, a regression-based feature extraction method was introduced to derive low-dimensional latent representations that retain exposure length-dependent vibration characteristics while suppressing environmental influences. The extracted features were used for one-class Support Vector Machine (SVM)-based anomaly detection. The proposed framework was evaluated through wave-tank experiments with exposure lengths ranging from 2 to 10 m. Experimental results showed that anomaly scores decreased approximately monotonically with increasing exposure-length change, exhibiting a strong correlation ($r = -0.83$). The binary classification achieved an F1 score of 0.82 despite training with only small-sample datasets. These findings demonstrate that exposure-length variations can be reliably detected under severe data limitations, supporting the potential of DAS-based cable condition monitoring.

Event Classification by Physics-informed Inpainting for Distributed Multichannel Acoustic Sensor with Partially Degraded Channels

Distributed multichannel acoustic sensing (DMAS) enables large-scale sound event classification (SEC), but performance drops when many channels are degraded and when sensor layouts at test time differ from training layouts. We propose a learning-free, physics-informed inpainting frontend based on reverse time migration (RTM). In this approach, observed multichannel spectrograms are first back-propagated on a 3D grid using an analytic Green's function to form a scene-consistent image, and then forward-projected to reconstruct inpainted signals before log-mel feature extraction and Transformer-based classification. We evaluate the method on ESC-50 with 50 sensors and three layouts (circular, linear, right-angle), where per-channel SNRs are sampled from -30 to 0 dB. Compared with an AST baseline, scaling-sparsemax channel selection, and channel-swap augmentation, the proposed RTM frontend achieves the best or competitive accuracy across all layouts, improving accuracy by 13.1 points on the right-angle layout (from 9.7% to 22.8%). Correlation analyses show that spatial weights align more strongly with SNR than with channel--source distance, and that higher SNR--weight correlation corresponds to higher SEC accuracy. These results demonstrate that a reconstruct-then-project, physics-based preprocessing effectively complements learning-only methods for DMAS under layout-open configurations and severe channel degradation.

Trainingless Adaptation of Pretrained Models for Environmental Sound Classification

Deep neural network (DNN)-based models for environmental sound classification are not robust against a domain to which training data do not belong, that is, out-of-distribution or unseen data. To utilize pretrained models for the unseen domain, adaptation methods, such as finetuning and transfer learning, are used with rich computing resources, e.g., the graphical processing unit (GPU). However, it is becoming more difficult to keep up with research trends for those who have poor computing resources because state-of-the-art models are becoming computationally resource-intensive. In this paper, we propose a trainingless adaptation method for pretrained models for environmental sound classification. To introduce the trainingless adaptation method, we first propose an operation of recovering time--frequency-ish (TF-ish) structures in intermediate layers of DNN models. We then propose the trainingless frequency filtering method for domain adaptation, which is not a gradient-based optimization widely used. The experiments conducted using the ESC-50 dataset show that the proposed adaptation method improves the classification accuracy by 20.40 percentage points compared with the conventional method.