Pub Date : 2025-03-16DOI: 10.1109/JOE.2025.3538948
Marko Orescanin;Derek Olson;Brian Harrington;Marc Geilhufe;Roy Edgar Hansen;Dalton Duvio;Narada Warakagoda
Synthetic aperture sonar (SAS) provides high-resolution underwater imaging but can suffer from artifacts due to environment or navigation errors. This work explores Bayesian deep learning for classifying common imaging artifacts while quantifying model reliability. We introduce a novel labeled data set with simulated imaging errors through controlled beamforming perturbations. Two Bayesian neural network variants, Monte Carlo dropout and flipout, were trained on this data to detect three artifacts induced by: sound speed errors, yaw attitude error, and additive noise. Results demonstrate these methods accurately classify artifacts in SAS imagery while producing well-calibrated uncertainty estimates. Uncertainty tends to be higher for uniform seafloor textures where artifacts are harder to perceive, and lower for richly textured environments. Analyzing uncertainty reveals regions likely to be misclassified. By discarding 20% of the most uncertain predictions, classification improves from 0.92 F$_{1}$-score to 0.98 F$_{1}$-score. Overall, the Bayesian approach enables uncertainty-aware perception, boosting model reliability—an essential capability for real-world autonomous underwater systems. This work establishes Bayesian deep learning as a robust technique for uncertainty quantification and artifact detection in SAS.
{"title":"Classification of Imaging Artifacts in Synthetic Aperture Sonar With Bayesian Deep Learning","authors":"Marko Orescanin;Derek Olson;Brian Harrington;Marc Geilhufe;Roy Edgar Hansen;Dalton Duvio;Narada Warakagoda","doi":"10.1109/JOE.2025.3538948","DOIUrl":"https://doi.org/10.1109/JOE.2025.3538948","url":null,"abstract":"Synthetic aperture sonar (SAS) provides high-resolution underwater imaging but can suffer from artifacts due to environment or navigation errors. This work explores Bayesian deep learning for classifying common imaging artifacts while quantifying model reliability. We introduce a novel labeled data set with simulated imaging errors through controlled beamforming perturbations. Two Bayesian neural network variants, Monte Carlo dropout and flipout, were trained on this data to detect three artifacts induced by: sound speed errors, yaw attitude error, and additive noise. Results demonstrate these methods accurately classify artifacts in SAS imagery while producing well-calibrated uncertainty estimates. Uncertainty tends to be higher for uniform seafloor textures where artifacts are harder to perceive, and lower for richly textured environments. Analyzing uncertainty reveals regions likely to be misclassified. By discarding 20% of the most uncertain predictions, classification improves from 0.92 F<inline-formula><tex-math>$_{1}$</tex-math></inline-formula>-score to 0.98 F<inline-formula><tex-math>$_{1}$</tex-math></inline-formula>-score. Overall, the Bayesian approach enables uncertainty-aware perception, boosting model reliability—an essential capability for real-world autonomous underwater systems. This work establishes Bayesian deep learning as a robust technique for uncertainty quantification and artifact detection in SAS.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"2280-2295"},"PeriodicalIF":3.8,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-16DOI: 10.1109/JOE.2025.3548665
Jongkwon Choi;Youngmin Choo;Geunhwan Kim;Wooyoung Hong;Keunhwa Lee
The application of machine learning in underwater acoustics is often limited by the lack of high-quality data. One method to avoid this data issue is to use modeled data to train a machine learning algorithm, called model-guided learning. In this study, a U-Net-based model-guided deep learning approach was developed to identify dispersion curves in an oceanic waveguide. The U-Net is trained using supervised learning with modeled data generated from an ocean propagation model to detect line segments in a time–frequency spectrogram. The evaluation of U-Net with the test data, based on the performance metrics, such as probability of false alarm, probability of detection, and normalized cross-correlation coefficient, reveals that it effectively extracts the dispersion curves. The proposed network was successfully applied to unseen simulated and experimental data. Our results demonstrate that the dispersion curve images generated through model-guided deep learning can serve as concise image features, including information regarding ocean environments.
{"title":"Model-Guided Deep Learning for Line Segment Detection in Time–Frequency Spectrograms of an Ocean Waveguide","authors":"Jongkwon Choi;Youngmin Choo;Geunhwan Kim;Wooyoung Hong;Keunhwa Lee","doi":"10.1109/JOE.2025.3548665","DOIUrl":"https://doi.org/10.1109/JOE.2025.3548665","url":null,"abstract":"The application of machine learning in underwater acoustics is often limited by the lack of high-quality data. One method to avoid this data issue is to use modeled data to train a machine learning algorithm, called model-guided learning. In this study, a U-Net-based model-guided deep learning approach was developed to identify dispersion curves in an oceanic waveguide. The U-Net is trained using supervised learning with modeled data generated from an ocean propagation model to detect line segments in a time–frequency spectrogram. The evaluation of U-Net with the test data, based on the performance metrics, such as probability of false alarm, probability of detection, and normalized cross-correlation coefficient, reveals that it effectively extracts the dispersion curves. The proposed network was successfully applied to unseen simulated and experimental data. Our results demonstrate that the dispersion curve images generated through model-guided deep learning can serve as concise image features, including information regarding ocean environments.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1812-1821"},"PeriodicalIF":3.8,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11006262","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-15DOI: 10.1109/JOE.2025.3557106
Shiyu Liu;Jun Ye;Mingsheng Chen;Junfeng Dong;Zhiyong Liu;Xinran Guo;Hongxing Wang
Heavy lift vessels are widely used in the installation and decommissioning of offshore structures. During offshore construction, heavy lift vessels under dynamic positioning must deal with complicated nonlinear dynamics due to the influence of large external disturbances. Existing studies on the nonlinear dynamics of heavy lift vessels mainly focus on moored vessels in surge, heave, and pitch directions, while neglecting other degrees of freedom. This article introduces a comprehensive nonlinear dynamic analysis of heavy lift vessels under dynamic positioning control. The full-dimensional nonlinear mathematical model is presented and analyzed using chaos theory. The vessel's behavior is visualized through Poincaré maps, showing stability around the fixed point under control. The dynamics of the vessel are affected by factors, such as the load mass, proportion–integration–differentiation controller parameters, and environmental forces. Simulations are conducted to validate the mathematical analysis.
{"title":"Full-Dimensional Nonlinear Dynamic Analysis for Lift Operation of a DP Crane Vessel","authors":"Shiyu Liu;Jun Ye;Mingsheng Chen;Junfeng Dong;Zhiyong Liu;Xinran Guo;Hongxing Wang","doi":"10.1109/JOE.2025.3557106","DOIUrl":"https://doi.org/10.1109/JOE.2025.3557106","url":null,"abstract":"Heavy lift vessels are widely used in the installation and decommissioning of offshore structures. During offshore construction, heavy lift vessels under dynamic positioning must deal with complicated nonlinear dynamics due to the influence of large external disturbances. Existing studies on the nonlinear dynamics of heavy lift vessels mainly focus on moored vessels in surge, heave, and pitch directions, while neglecting other degrees of freedom. This article introduces a comprehensive nonlinear dynamic analysis of heavy lift vessels under dynamic positioning control. The full-dimensional nonlinear mathematical model is presented and analyzed using chaos theory. The vessel's behavior is visualized through Poincaré maps, showing stability around the fixed point under control. The dynamics of the vessel are affected by factors, such as the load mass, proportion–integration–differentiation controller parameters, and environmental forces. Simulations are conducted to validate the mathematical analysis.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"2090-2100"},"PeriodicalIF":3.8,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In underwater subsea environments light attenuation, water turbidity, and limitations of the optical devices make the captured images suffer from poor contrast and quality, proportional degradation, low visibility, and low color richness. In recent years, various image enhancement techniques have been applied to improve the image quality, resulting in a new challenge, i.e., the quality assessment of the underwater images. In this study, we introduce an innovative and versatile blind quality assessment method for underwater images without using any references. Our approach leverages structural and contour-based metrics, combined with dispersion rate analysis, to quantify image degradation and color richness within an opponent color space. Specifically, we measure the proportional degradation by computing the edge magnitude using the directional Kirsch kernels, strengthened by image contour and saliency maps. To assess the color quality, chrominance dispersion rates and the overall saturation and hue are used to capture color distortions introduced by enhancement methods. The final quality score is obtained via a multiple linear regression model trained on extensive data sets. Experiments on three benchmark data sets have demonstrated the superior accuracy, consistency, and computational efficiency of the proposed method for both raw and enhanced underwater images.
{"title":"Blind Quality Assessment Using Channel-Based Structural, Dispersion Rate Scores, and Overall Saturation and Hue for Underwater Images","authors":"Hamidreza Farhadi Tolie;Jinchang Ren;Jun Cai;Rongjun Chen;Huimin Zhao","doi":"10.1109/JOE.2025.3553888","DOIUrl":"https://doi.org/10.1109/JOE.2025.3553888","url":null,"abstract":"In underwater subsea environments light attenuation, water turbidity, and limitations of the optical devices make the captured images suffer from poor contrast and quality, proportional degradation, low visibility, and low color richness. In recent years, various image enhancement techniques have been applied to improve the image quality, resulting in a new challenge, i.e., the quality assessment of the underwater images. In this study, we introduce an innovative and versatile blind quality assessment method for underwater images without using any references. Our approach leverages structural and contour-based metrics, combined with dispersion rate analysis, to quantify image degradation and color richness within an opponent color space. Specifically, we measure the proportional degradation by computing the edge magnitude using the directional Kirsch kernels, strengthened by image contour and saliency maps. To assess the color quality, chrominance dispersion rates and the overall saturation and hue are used to capture color distortions introduced by enhancement methods. The final quality score is obtained via a multiple linear regression model trained on extensive data sets. Experiments on three benchmark data sets have demonstrated the superior accuracy, consistency, and computational efficiency of the proposed method for both raw and enhanced underwater images.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1944-1959"},"PeriodicalIF":3.8,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-15DOI: 10.1109/JOE.2025.3557927
Songbo Xu;He Shen;Yixin Yang
Undersea cable detection is a prerequisite for cable maintenance and repair. However, extracting cables from side-scan sonar images is challenging due to the lack of details and interference from seabed sediments. In this article, an automatic rotation-invariant segmentation method for undersea cables is proposed. First, a filter based on the curvelet transform is designed to extract features of cables automatically. Second, a 2-D constant false alarm rate detector is used for feature denoising. Third, a morphology repair method is proposed to fulfill features that have been missed during feature extraction and image denoising. Finally, the maximum connected area in images is retained for cable segmentation. Results show that the proposed method can extract cables accurately. Four performance indicators, including structural similarity index, precision, pixel accuracy, and intersection over union reach 0.9810, 0.6108, 0.8348, and 0.8915, respectively. Consistent performance has been observed in images with different cable postures.
{"title":"Rotation Invariant Sonar Image Segmentation for Undersea Cables","authors":"Songbo Xu;He Shen;Yixin Yang","doi":"10.1109/JOE.2025.3557927","DOIUrl":"https://doi.org/10.1109/JOE.2025.3557927","url":null,"abstract":"Undersea cable detection is a prerequisite for cable maintenance and repair. However, extracting cables from side-scan sonar images is challenging due to the lack of details and interference from seabed sediments. In this article, an automatic rotation-invariant segmentation method for undersea cables is proposed. First, a filter based on the curvelet transform is designed to extract features of cables automatically. Second, a 2-D constant false alarm rate detector is used for feature denoising. Third, a morphology repair method is proposed to fulfill features that have been missed during feature extraction and image denoising. Finally, the maximum connected area in images is retained for cable segmentation. Results show that the proposed method can extract cables accurately. Four performance indicators, including structural similarity index, precision, pixel accuracy, and intersection over union reach 0.9810, 0.6108, 0.8348, and 0.8915, respectively. Consistent performance has been observed in images with different cable postures.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"2345-2354"},"PeriodicalIF":3.8,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deconvolution algorithms often rely on conventional beamforming methods to obtain beamforming vectors, which limit their resolution. To enhance parameter estimation resolution, this article introduces the Parameter Estimation by Alternating Reconstruction and Sensation (PEARS) algorithm. In the proposed algorithm, direction estimation leverages a linearly constrained quadratic programming method and weighted L1-norm to solve the objective function, achieving higher resolution in the direction spectrum under fixed weighted vector conditions. The algorithm utilizes the gradient descent method to update the weighted vector, and the relationship among the dictionary matrix, direction spectrum, and weighted vector is computed using the chain rule. This process improves direction estimation results, particularly in scenarios with low signal-to-noise ratios. By alternating between target parameter estimation and weight vector calculation, the PEARS algorithm achieves highly accurate target azimuth estimation. Simulation results validate the algorithm's ability to accurately estimate target azimuth angles. In addition, lake and sea experimental results demonstrate the algorithm's effectiveness in correctly estimating direction in complex environments.
反卷积算法通常依赖于传统的波束形成方法来获得波束形成向量，这限制了它们的分辨率。为了提高参数估计的分辨率，本文引入了交替重建与感知（Alternating Reconstruction and Sensation，简称PEARS）算法。在该算法中，方向估计利用线性约束二次规划方法和加权l1范数求解目标函数，在固定加权向量条件下实现了更高的方向谱分辨率。该算法利用梯度下降法更新加权向量，利用链式法则计算字典矩阵、方向谱和加权向量之间的关系。这个过程改善了方向估计结果，特别是在低信噪比的情况下。该算法通过目标参数估计和权向量计算交替进行，实现了高精度的目标方位估计。仿真结果验证了该算法准确估计目标方位角的能力。此外，湖泊和海洋实验结果也证明了该算法在复杂环境下正确估计方向的有效性。
{"title":"Parameter Estimation by Alternating Reconstruction and Sensation for Sonar System","authors":"Haoran Ji;Lei Wang;Shuhao Zhang;Wenjie Zhou;Cong Peng","doi":"10.1109/JOE.2025.3529255","DOIUrl":"https://doi.org/10.1109/JOE.2025.3529255","url":null,"abstract":"Deconvolution algorithms often rely on conventional beamforming methods to obtain beamforming vectors, which limit their resolution. To enhance parameter estimation resolution, this article introduces the Parameter Estimation by Alternating Reconstruction and Sensation (PEARS) algorithm. In the proposed algorithm, direction estimation leverages a linearly constrained quadratic programming method and weighted L1-norm to solve the objective function, achieving higher resolution in the direction spectrum under fixed weighted vector conditions. The algorithm utilizes the gradient descent method to update the weighted vector, and the relationship among the dictionary matrix, direction spectrum, and weighted vector is computed using the chain rule. This process improves direction estimation results, particularly in scenarios with low signal-to-noise ratios. By alternating between target parameter estimation and weight vector calculation, the PEARS algorithm achieves highly accurate target azimuth estimation. Simulation results validate the algorithm's ability to accurately estimate target azimuth angles. In addition, lake and sea experimental results demonstrate the algorithm's effectiveness in correctly estimating direction in complex environments.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"2311-2326"},"PeriodicalIF":3.8,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-12DOI: 10.1109/JOE.2025.3560367
Yonggang Ji;Zhihao Li;Xiaoyu Cheng;Jiawei Wang;Ruozhao Qu;Zhihang Zhang;Weifeng Sun;Yiming Wang
Shipborne bistatic high-frequency surface wave radar (HFSWR) is a new type of HFSWR system, where the transmitting and receiving stations are deployed on different shipborne platforms. It combines the advantages of strong concealment and anti-interference capability of the dual-base system, as well as the mobility and flexibility of the shipborne system. However, for shipborne bistatic HFSWR radar, radar echoes are simultaneously affected by the combined motion modulation of two shipborne platforms, resulting in the broadening of target echoes and induced peaks. So, it is necessary to perform motion compensation processing for the target echo. Inertial navigation attitude information can be used for motion compensation, but the delay of attitude data will affect the compensation performance. In addition, the direct wave signal can be used to estimate the platform attitude information for motion compensation, but the performance of this method will be reduced due to noise. This article proposes a motion compensation method for shipborne bistatic HFSWR target echoes based on calibrated attitude information. First, considering that the motion compensation method of shore-ship bistatic can be adopted, the two-ship modulation model can be transformed into the shore-ship model. Then, the direct wave signal is used as the auxiliary reference source to estimate the attitude information of the shipborne platform, the inertial navigation attitude data are calibrated with it to eliminate the delay error of inertial navigation attitude data, and the calibrated attitude data are used for motion compensation. Finally, the simulation results show that the proposed method can further improve the performance of motion compensation.
{"title":"Motion Compensation Method for Target Echoes of Shipborne Bistatic HFSWR Using Calibrated Attitude Information","authors":"Yonggang Ji;Zhihao Li;Xiaoyu Cheng;Jiawei Wang;Ruozhao Qu;Zhihang Zhang;Weifeng Sun;Yiming Wang","doi":"10.1109/JOE.2025.3560367","DOIUrl":"https://doi.org/10.1109/JOE.2025.3560367","url":null,"abstract":"Shipborne bistatic high-frequency surface wave radar (HFSWR) is a new type of HFSWR system, where the transmitting and receiving stations are deployed on different shipborne platforms. It combines the advantages of strong concealment and anti-interference capability of the dual-base system, as well as the mobility and flexibility of the shipborne system. However, for shipborne bistatic HFSWR radar, radar echoes are simultaneously affected by the combined motion modulation of two shipborne platforms, resulting in the broadening of target echoes and induced peaks. So, it is necessary to perform motion compensation processing for the target echo. Inertial navigation attitude information can be used for motion compensation, but the delay of attitude data will affect the compensation performance. In addition, the direct wave signal can be used to estimate the platform attitude information for motion compensation, but the performance of this method will be reduced due to noise. This article proposes a motion compensation method for shipborne bistatic HFSWR target echoes based on calibrated attitude information. First, considering that the motion compensation method of shore-ship bistatic can be adopted, the two-ship modulation model can be transformed into the shore-ship model. Then, the direct wave signal is used as the auxiliary reference source to estimate the attitude information of the shipborne platform, the inertial navigation attitude data are calibrated with it to eliminate the delay error of inertial navigation attitude data, and the calibrated attitude data are used for motion compensation. Finally, the simulation results show that the proposed method can further improve the performance of motion compensation.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1885-1894"},"PeriodicalIF":3.8,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-11DOI: 10.1109/JOE.2024.3519679
Qi Chen;Chengjun Ming;Guoyang Qin;Daqi Zhu
A hybrid underwater vehicle (HUV) equipped with thrusters and tracks has the great ability of free flying in the water and crawling on the surfaces of underwater structures, making it highly effective for inspecting underwater structures and cleaning hulls. In this article, a novel cascade control strategy that consists of a kinematic controller and a dynamic controller is proposed for trajectory tracking control of HUVs in free-flying and crawling operation modes. Based on the tracking error, a model predictive control (MPC)-based kinematic controller is designed for both free-flying and crawling modes. To improve the tracking accuracy, an improved snake optimizer is used in the optimization process of MPC to derive the expected optimal velocity. Then, the error between the expected optimal velocity and the real velocity is used as the input of the dynamic controller. To compensate for external disturbances, such as ocean currents and waves, a dynamic controller composed of a nonlinear disturbance observer and an integral sliding mode control (ISMC) is adopted to optimize the thrust force for trajectory tracking in free-flying mode. In addition, a dynamic controller composed of a radial basis function neural network and an ISMC is established to reduce the impact of slipperiness in crawling mode. The simulation results show that the proposed cascade trajectory tracking control strategy for HUVs in free-flying and crawling modes can improve the trajectory tracking accuracy and robustness to unknown dynamic factors.
{"title":"Trajectory Tracking Control for a Hybrid Underwater Vehicle in Free-Flying and Crawling Operation Modes","authors":"Qi Chen;Chengjun Ming;Guoyang Qin;Daqi Zhu","doi":"10.1109/JOE.2024.3519679","DOIUrl":"https://doi.org/10.1109/JOE.2024.3519679","url":null,"abstract":"A hybrid underwater vehicle (HUV) equipped with thrusters and tracks has the great ability of free flying in the water and crawling on the surfaces of underwater structures, making it highly effective for inspecting underwater structures and cleaning hulls. In this article, a novel cascade control strategy that consists of a kinematic controller and a dynamic controller is proposed for trajectory tracking control of HUVs in free-flying and crawling operation modes. Based on the tracking error, a model predictive control (MPC)-based kinematic controller is designed for both free-flying and crawling modes. To improve the tracking accuracy, an improved snake optimizer is used in the optimization process of MPC to derive the expected optimal velocity. Then, the error between the expected optimal velocity and the real velocity is used as the input of the dynamic controller. To compensate for external disturbances, such as ocean currents and waves, a dynamic controller composed of a nonlinear disturbance observer and an integral sliding mode control (ISMC) is adopted to optimize the thrust force for trajectory tracking in free-flying mode. In addition, a dynamic controller composed of a radial basis function neural network and an ISMC is established to reduce the impact of slipperiness in crawling mode. The simulation results show that the proposed cascade trajectory tracking control strategy for HUVs in free-flying and crawling modes can improve the trajectory tracking accuracy and robustness to unknown dynamic factors.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"1001-1014"},"PeriodicalIF":3.8,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-10DOI: 10.1109/JOE.2024.3516204
Ruwei Li;Man Li;Qiuyan Li;Jiangqiao Li
The accuracy of existing underwater sound source localization algorithms is unsatisfactory, and most of them cannot achieve cross-domain localization. To solve these problems, a cross-domain underwater sound source localization algorithm based on a binaural matrix and mutual information constraint loss is proposed. In this algorithm, a new binaural matrix feature is first extracted based on binaural cues, which is less susceptible to environmental interference and can obtain reliable direction information from received signals. Then, a constrained loss based on mutual information is designed to constrain the proposed neural network to accurately learn the shared representations of different domains. This ensures that the high-dimensional representations used for localization have more explicit orientation directionality. Finally, a cross-domain underwater sound source localization network is constructed to achieve accurate cross-domain localization. Experimental results indicate that the algorithm proposed in this study has a higher localization accuracy than comparative algorithms, both in the same domain and in different domains.
{"title":"Cross-Domain Underwater Sound Source Localization Algorithm Based on Binaural Matrix and Mutual Information Constraint Loss","authors":"Ruwei Li;Man Li;Qiuyan Li;Jiangqiao Li","doi":"10.1109/JOE.2024.3516204","DOIUrl":"https://doi.org/10.1109/JOE.2024.3516204","url":null,"abstract":"The accuracy of existing underwater sound source localization algorithms is unsatisfactory, and most of them cannot achieve cross-domain localization. To solve these problems, a cross-domain underwater sound source localization algorithm based on a binaural matrix and mutual information constraint loss is proposed. In this algorithm, a new binaural matrix feature is first extracted based on binaural cues, which is less susceptible to environmental interference and can obtain reliable direction information from received signals. Then, a constrained loss based on mutual information is designed to constrain the proposed neural network to accurately learn the shared representations of different domains. This ensures that the high-dimensional representations used for localization have more explicit orientation directionality. Finally, a cross-domain underwater sound source localization network is constructed to achieve accurate cross-domain localization. Experimental results indicate that the algorithm proposed in this study has a higher localization accuracy than comparative algorithms, both in the same domain and in different domains.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 2","pages":"1419-1428"},"PeriodicalIF":3.8,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-09DOI: 10.1109/JOE.2025.3553955
Dugald J. M. Thomson;David R. Barclay
The horizontal directionality of ship-radiated noise was estimated in the Canadian Arctic Archipelago using two 48-element bottom-mounted hydrophone arrays. Source levels (SL) were estimated using automated identification system data for distance and bearing with a geometric spreading propagation loss model for ships passing within 3 km of the arrays. Time-averaged received levels are calculated in 3-s increments for broadband (10–600 Hz) as well as selected narrowband tonal sources. Tonal components are identified with spectral analysis and algorithmically tracked in the time-frequency domain. From the difference of received levels and propagation loss, SLs are calculated and sorted by ship's bearing from each of the 96 array elements for both broadband and predominant narrowband sources. Broadband SL estimates ranged from 148 to 181 dB re 1 μPa2 m2 for the four ships of opportunity.
利用两个48单元底置水听器阵列估计了加拿大北极群岛船舶辐射噪声的水平方向性。利用距离和方位的自动识别系统数据，利用几何扩散传播损耗模型对经过阵列3公里范围内的船舶进行源电平（SL）估计。时间平均接收电平以3-s增量计算宽带（10 - 600hz）以及选定的窄带音调源。用频谱分析识别音调分量，并在时频域进行算法跟踪。根据接收电平和传播损耗的差异，根据船舶方位对宽带和主要窄带源的96个阵列元素中的每个元素进行SLs计算和分类。四艘机遇号的宽带SL估计范围为148至181 dB / 1 μPa2 m2。
{"title":"Directionality of Tonal Components of Ship Noise Using Arctic Hydrophone Array Elements","authors":"Dugald J. M. Thomson;David R. Barclay","doi":"10.1109/JOE.2025.3553955","DOIUrl":"https://doi.org/10.1109/JOE.2025.3553955","url":null,"abstract":"The horizontal directionality of ship-radiated noise was estimated in the Canadian Arctic Archipelago using two 48-element bottom-mounted hydrophone arrays. Source levels (SL) were estimated using automated identification system data for distance and bearing with a geometric spreading propagation loss model for ships passing within 3 km of the arrays. Time-averaged received levels are calculated in 3-s increments for broadband (10–600 Hz) as well as selected narrowband tonal sources. Tonal components are identified with spectral analysis and algorithmically tracked in the time-frequency domain. From the difference of received levels and propagation loss, SLs are calculated and sorted by ship's bearing from each of the 96 array elements for both broadband and predominant narrowband sources. Broadband SL estimates ranged from 148 to 181 dB re 1 <italic>μ</i>Pa<sup>2</sup> m<sup>2</sup> for the four ships of opportunity.","PeriodicalId":13191,"journal":{"name":"IEEE Journal of Oceanic Engineering","volume":"50 3","pages":"1782-1797"},"PeriodicalIF":3.8,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：