Feature Extraction of Ship Radiation Signals Based on Wavelet Packet Decomposition and Energy Entropy

Li, Yuxing; Ning, Feiyue; Jiang, Xinru; Yi, Yingmin

doi:10.1155/2022/8092706

Cited by 10 publications

(4 citation statements)

References 27 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to other signal processing methods, such as Fourier transform, fractal analysis, and Hilbert-Huang transform (Liao , 2019), wavelet packet analysis enables the decomposition of the input signal into low-and high-frequency bands (FBs) with the required resolution (Li et al, 2022), and the influence of the FBs of interest can be quantified using the energy ratio. Owing to these advantages, the wavelet packet-based energy analysis method (Zhang et al, 2021) was applied in subsequent data processing to identify the coupling mechanisms of the OWT model for the selected test cases.…”

Section: Wavelet Packet-based Energy Analysis Methodsmentioning

confidence: 99%

Experimental study of dynamic characteristics of an ultra-large jacket offshore wind turbine under wind and wave loads using aero-hydro-structural elastic similarities

Xiong

Pan²,

Wang³

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Owing to the difficulties in the scaled rotor-nacelle assembly (RNA) and support structure design, and alleviation of small scaling effects, the limited dynamic model tests are conducted for the jacket offshore wind turbines (OWTs), which are extensively constructed in the offshore wind farms located in the depth of 40–50 m. To address this limitation, an integrated test method based on aero-hydro-structural elastic similarities is proposed in this study. It comprises a performance-scaled RNA model and a scaled support structure model. A redesigned blade model is adopted in the scaled RNA model to ensure the similarities of aerodynamic thrust loads without modifications of the scaled test winds. Moreover, auxiliary scaled drivetrain and blade pitch control are designed to simulate the operational states of a practical OWT. The scaled model of the OWT support structure is fabricated based on the joint hydro-structural elastic similarity, and the small scaling effects are mitigated by introducing sectional bending stiffness similarities. Subsequently, the dynamic model tests of an ultra-large jacket OWT under wind-only, wave-only, and combined wind and wave conditions are carried out. The accuracy of the fabricated OWT test model is validated based on the recorded responses, and the influence of the dominant frequencies on the dynamic responses of the OWT model is quantitatively evaluated using the wavelet packet-based energy analysis method. Further, the coupling mechanisms of the scaled OWT model under typical wind and wave loads are investigated, and the interactions between the environmental loads and OWT motions are proved.

show abstract

Section: Wavelet Packet-based Energy Analysis Methodsmentioning

confidence: 99%

Experimental study of dynamic characteristics of an ultra-large jacket offshore wind turbine under wind and wave loads using aero-hydro-structural elastic similarities

Xiong

Pan²,

Wang³

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…Signal feature extraction and processing is crucial in object detection. Signal feature extraction for ships is becoming more and more mature; based on VMD and slope entropy [6] and based on wavelet packet decomposition and energy entropy [7] have achieved good results in signal feature extraction for ships. Dispersion entropy-based Lempel-Ziv complexity entropy [8] provides us a new metric for signal analysis.…”

Section: Introductionmentioning

confidence: 99%

A Robust and Lightweight Detector for Ship Target with Complex Background in SAR Image

Wang

Zhang

2022

Journal of Sensors

View full text Add to dashboard Cite

Accurate target detection technology on ships can improve the comprehensive perception ability of weapon equipment. For SAR ship target detection in complex environments, false and missing alarms are serious. We design a new real-time ship target detection algorithm 3S-YOLO in SAR images. Firstly, reconstruct the network structure, adjust the relationship between receptive field and multiscale fusion, and realize the lightweight processing of feature extraction network and feature fusion network. Then, the network is pruned and compressed by the FPGM pruning algorithm to accelerate the reasoning speed. Finally, the Varifocal-EIoU loss function is designed to balance the positive and negative samples and overlapping losses and highlight the contribution of positive samples. To verify the effectiveness of the 3S-YOLO algorithm, verification is carried out in public datasets SSDD and HRSID. The results show that the accuracy of the model can be improved to 99.2% and 95.6%, respectively, after optimization. After pruning, the model volume decreased significantly and could be compressed to 190 KB. Model reasoning time can be reduced to less than 3 ms. Compared with the current mainstream algorithms, 3S-YOLO has achieved good results in all aspects to meet the real-time ship target detection in SAR images.

show abstract

“…Traditional identi cation methods rst need to design features, which are further divided into physical features such as pixel values [6] and signal features such as slope entropy [7]. e designed features are extracted by means of image processing or variational modal decomposition (VMD) [8], and then these features are input into classi ers such as k-nearest neighbor [9] for identi cation. Yuan et al [10] proposed a method to concatenate all suboriented histograms of the local binary pattern (LBP) for smoke classi cation, better capturing the spatial distribution of texture features.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Smoke Recognition Based on Deep Convolution and Self-Attention

Zhao

Wang

Jung

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Deep convolutional networks have better smoke recognition performance. However, a lightweight network model and high recognition accuracy cannot be balanced when deployed on hardware with limited computing resources such as edge computing. Based on this background, we propose a novel smoke recognition network that combines convolutional networks (CNN) and self-attention. The core ideas of this framework are as follows: (1) Combine the depthwise convolution and asymmetric convolution of large convolution kernels to construct a lightweight CNN model, and realize multiscale extraction of feature information with slight model complexity. (2) Combined with the self-attention in transformer, a skip-connection branch is designed, which improves the feature extraction capability of the backbone network through parallel processing and fusion of feature map information. (3) Fusion multicomponent discrete cosine transform (DCT) is used to compress channel information and expand the ability of global average pooling (GAP) to aggregate feature maps. The proposed DCT-GAP improves the accuracy of the network without adding additional computational costs. Experimental results show that the proposed CSANet achieves an average accuracy of over 98.3% with 238 M FLOPs and 5.8 M parameters on the homemade smoke dataset, outperforming state-of-the-art competitors.

show abstract

Feature Extraction of Ship Radiation Signals Based on Wavelet Packet Decomposition and Energy Entropy

Cited by 10 publications

References 27 publications

Experimental study of dynamic characteristics of an ultra-large jacket offshore wind turbine under wind and wave loads using aero-hydro-structural elastic similarities

Experimental study of dynamic characteristics of an ultra-large jacket offshore wind turbine under wind and wave loads using aero-hydro-structural elastic similarities

A Robust and Lightweight Detector for Ship Target with Complex Background in SAR Image

Lightweight Smoke Recognition Based on Deep Convolution and Self-Attention

Contact Info

Product

Resources

About