This study explores the application of single photon detection(SPD)technology in underwater wireless optical communication(UWOC)and analyzes the influence of different modulation modes and error correction coding type...This study explores the application of single photon detection(SPD)technology in underwater wireless optical communication(UWOC)and analyzes the influence of different modulation modes and error correction coding types on communication performance.The study investigates the impact of on-off keying(OOK)and 2-pulse-position modulation(2-PPM)on the bit error rate(BER)in single-channel intensity and polarization multiplexing.Furthermore,it compares the error correction performance of low-density parity check(LDPC)and Reed-Solomon(RS)codes across different error correction coding types.The effects of unscattered photon ratio and depolarization ratio on BER are also verified.Finally,a UWOC system based on SPD is constructed,achieving 14.58 Mbps with polarization OOK multiplexing modulation and 4.37 Mbps with polarization 2-PPM multiplexing modulation using LDPC code error correction.展开更多
The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a c...The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a classification model that combines an EfficientnetB0 neural network and a two-hidden-layer random vector functional link network(EfficientnetB0-TRVFL).The features of underwater images were extracted using the EfficientnetB0 neural network pretrained via ImageNet,and a new fully connected layer was trained on the underwater image dataset using the transfer learning method.Transfer learning ensures the initial performance of the network and helps in the development of a high-precision classification model.Subsequently,a TRVFL was proposed to improve the classification property of the model.Net construction of the two hidden layers exhibited a high accuracy when the same hidden layer nodes were used.The parameters of the second hidden layer were obtained using a novel calculation method,which reduced the outcome error to improve the performance instability caused by the random generation of parameters of RVFL.Finally,the TRVFL classifier was used to classify features and obtain classification results.The proposed EfficientnetB0-TRVFL classification model achieved 87.28%,74.06%,and 99.59%accuracy on the MLC2008,MLC2009,and Fish-gres datasets,respectively.The best convolutional neural networks and existing methods were stacked up through box plots and Kolmogorov-Smirnov tests,respectively.The increases imply improved systematization properties in underwater image classification tasks.The image classification model offers important performance advantages and better stability compared with existing methods.展开更多
This paper investigates the tracking control problem for unmanned underwater vehicles(UUVs)systems with sensor faults,input saturation,and external disturbance caused by waves and ocean currents.An active sensor fault...This paper investigates the tracking control problem for unmanned underwater vehicles(UUVs)systems with sensor faults,input saturation,and external disturbance caused by waves and ocean currents.An active sensor fault-tolerant control scheme is proposed.First,the developed method only requires the inertia matrix of the UUV,without other dynamic information,and can handle both additive and multiplicative sensor faults.Subsequently,an adaptive fault-tolerant controller is designed to achieve asymptotic tracking control of the UUV by employing robust integral of the sign of error feedback method.It is shown that the effect of sensor faults is online estimated and compensated by an adaptive estimator.With the proposed controller,the tracking error and estimation error can asymptotically converge to zero.Finally,simulation results are performed to demonstrate the effectiveness of the proposed method.展开更多
This study focuses on the improvement of path planning efficiency for underwater gravity-aided navigation.Firstly,a Depth Sorting Fast Search(DSFS)algorithm was proposed to improve the planning speed of the Quick Rapi...This study focuses on the improvement of path planning efficiency for underwater gravity-aided navigation.Firstly,a Depth Sorting Fast Search(DSFS)algorithm was proposed to improve the planning speed of the Quick Rapidly-exploring Random Trees*(Q-RRT*)algorithm.A cost inequality relationship between an ancestor and its descendants was derived,and the ancestors were filtered accordingly.Secondly,the underwater gravity-aided navigation path planning system was designed based on the DSFS algorithm,taking into account the fitness,safety,and asymptotic optimality of the routes,according to the gravity suitability distribution of the navigation space.Finally,experimental comparisons of the computing performance of the ChooseParent procedure,the Rewire procedure,and the combination of the two procedures for Q-RRT*and DSFS were conducted under the same planning environment and parameter conditions,respectively.The results showed that the computational efficiency of the DSFS algorithm was improved by about 1.2 times compared with the Q-RRT*algorithm while ensuring correct computational results.展开更多
Underwater image enhancement aims to restore a clean appearance and thus improves the quality of underwater degraded images.Current methods feed the whole image directly into the model for enhancement.However,they ign...Underwater image enhancement aims to restore a clean appearance and thus improves the quality of underwater degraded images.Current methods feed the whole image directly into the model for enhancement.However,they ignored that the R,G and B channels of underwater degraded images present varied degrees of degradation,due to the selective absorption for the light.To address this issue,we propose an unsupervised multi-expert learning model by considering the enhancement of each color channel.Specifically,an unsupervised architecture based on generative adversarial network is employed to alleviate the need for paired underwater images.Based on this,we design a generator,including a multi-expert encoder,a feature fusion module and a feature fusion-guided decoder,to generate the clear underwater image.Accordingly,a multi-expert discriminator is proposed to verify the authenticity of the R,G and B channels,respectively.In addition,content perceptual loss and edge loss are introduced into the loss function to further improve the content and details of the enhanced images.Extensive experiments on public datasets demonstrate that our method achieves more pleasing results in vision quality.Various metrics(PSNR,SSIM,UIQM and UCIQE) evaluated on our enhanced images have been improved obviously.展开更多
For underwater robots in the process of performing target detection tasks,the color distortion and the uneven quality of underwater images lead to great difficulties in the feature extraction process of the model,whic...For underwater robots in the process of performing target detection tasks,the color distortion and the uneven quality of underwater images lead to great difficulties in the feature extraction process of the model,which is prone to issues like error detection,omission detection,and poor accuracy.Therefore,this paper proposed the CER-YOLOv7(CBAM-EIOU-RepVGG-YOLOv7)underwater target detection algorithm.To improve the algorithm’s capability to retain valid features from both spatial and channel perspectives during the feature extraction phase,we have added a Convolutional Block Attention Module(CBAM)to the backbone network.The Reparameterization Visual Geometry Group(RepVGG)module is inserted into the backbone to improve the training and inference capabilities.The Efficient Intersection over Union(EIoU)loss is also used as the localization loss function,which reduces the error detection rate and missed detection rate of the algorithm.The experimental results of the CER-YOLOv7 algorithm on the UPRC(Underwater Robot Prototype Competition)dataset show that the mAP(mean Average Precision)score of the algorithm is 86.1%,which is a 2.2%improvement compared to the YOLOv7.The feasibility and validity of the CER-YOLOv7 are proved through ablation and comparison experiments,and it is more suitable for underwater target detection.展开更多
Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color...Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual perception.Finally, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.展开更多
Underwater direction of arrival(DOA)estimation has always been a very challenging theoretical and practical problem.Due to the serious non-stationary,non-linear,and non-Gaussian characteristics,machine learning based ...Underwater direction of arrival(DOA)estimation has always been a very challenging theoretical and practical problem.Due to the serious non-stationary,non-linear,and non-Gaussian characteristics,machine learning based DOA estimation methods trained on simulated Gaussian noised array data cannot be directly applied to actual underwater DOA estimation tasks.In order to deal with this problem,environmental data with no target echoes can be employed to analyze the non-Gaussian components.Then,the obtained information about non-Gaussian components can be used to whiten the array data.Based on these considerations,a novel practical sonar array whitening method was proposed.Specifically,based on a weak assumption that the non-Gaussian components in adjacent patches with and without target echoes are almost the same,canonical cor-relation analysis(CCA)and non-negative matrix factorization(NMF)techniques are employed for whitening the array data.With the whitened array data,machine learning based DOA estimation models trained on simulated Gaussian noised datasets can be used to perform underwater DOA estimation tasks.Experimental results illustrated that,using actual underwater datasets for testing with known machine learning based DOA estimation models,accurate and robust DOA estimation performance can be achieved by using the proposed whitening method in different underwater con-ditions.展开更多
With the continuous development of the economy and society,plastic pollution in rivers,lakes,oceans,and other bodies of water is increasingly severe,posing a serious challenge to underwater ecosystems.Effective cleani...With the continuous development of the economy and society,plastic pollution in rivers,lakes,oceans,and other bodies of water is increasingly severe,posing a serious challenge to underwater ecosystems.Effective cleaning up of underwater litter by robots relies on accurately identifying and locating the plastic waste.However,it often causes significant challenges such as noise interference,low contrast,and blurred textures in underwater optical images.A weighted fusion-based algorithm for enhancing the quality of underwater images is proposed,which combines weighted logarithmic transformations,adaptive gamma correction,improved multi-scale Retinex(MSR)algorithm,and the contrast limited adaptive histogram equalization(CLAHE)algorithm.The proposed algorithm improves brightness,contrast,and color recovery and enhances detail features resulting in better overall image quality.A network framework is proposed in this article based on the YOLOv5 model.MobileViT is used as the backbone of the network framework,detection layer is added to improve the detection capability for small targets,self-attention and mixed-attention modules are introduced to enhance the recognition capability of important features.The cross stage partial(CSP)structure is employed in the spatial pyramid pooling(SPP)section to enrich feature information,and the complete intersection over union(CIOU)loss is replaced with the focal efficient intersection over union(EIOU)loss to accelerate convergence while improving regression accuracy.Experimental results proved that the target recognition algorithm achieved a recognition accuracy of 0.913 and ensured a recognition speed of 45.56 fps/s.Subsequently,Using red,green,blue and depth(RGB-D)camera to construct a system for identifying and locating underwater plastic waste.Experiments were conducted underwater for recognition,localization,and error analysis.The experimental results demonstrate the effectiveness of the proposed method for identifying and locating underwater plastic waste,and it has good localization accuracy.展开更多
With the continuous development and utilization of marine resources,the underwater target detection has gradually become a popular research topic in the field of underwater robot operations and target detection.Howeve...With the continuous development and utilization of marine resources,the underwater target detection has gradually become a popular research topic in the field of underwater robot operations and target detection.However,it is difficult to combine the environmental semantic information and the semantic information of targets at different scales by detection algorithms due to the complex underwater environment.In this paper,a cascade model based on the UGC-YOLO network structure with high detection accuracy is proposed.The YOLOv3 convolutional neural network is employed as the baseline structure.By fusing the global semantic information between two residual stages in the parallel structure of the feature extraction network,the perception of underwater targets is improved and the detection rate of hard-to-detect underwater objects is raised.Furthermore,the deformable convolution is applied to capture longrange semantic dependencies and PPM pooling is introduced in the highest layer network for aggregating semantic information.Finally,a multi-scale weighted fusion approach is presented for learning semantic information at different scales.Experiments are conducted on an underwater test dataset and the results have demonstrated that our proposed algorithm could detect aquatic targets in complex degraded underwater images.Compared with the baseline network algorithm,the Common Objects in Context(COCO)evaluation metric has been improved by 4.34%.展开更多
To investigate the overall damage characteristics and failure modes of a warship subjected to an underwater non-contact near-field explosion,a hull girder with a trapezoidal cross-section was designed,manufactured,and...To investigate the overall damage characteristics and failure modes of a warship subjected to an underwater non-contact near-field explosion,a hull girder with a trapezoidal cross-section was designed,manufactured,and tested.The design criteria and parameters were determined according to the similarity criterion.Dynamic responses of the girder freely floating on water were obtained under varying conditions,including stand-off distance,charge mass,and position of attack.Damage morphologies of the girder model were obtained.Based on our analysis,basic conditions for sagging damage of the hull girder are proposed.The aim of this study was to determine an efficient method of attack resulting in the most severe damage to the ship hull.The experimental results show that the girder mainly exhibits a first-order response when the first wet frequency of the girder is close to the frequency of the explosion bubble pulsation.The largest deformation was observed when the underwater explosion occurred directly below the midspan of the girder compared to other explosions of the same intensity at different attack positions.When the ratio of stand-off to maximum bubble radius(λ)satisfies 0.7≤λ<2,the bubble mainly causes sagging damage instead of hogging.Asλdecreases(1≤λ<2),the sagging damage increases under the same charge mass.However,asλdecreases further(0.7≤λ<1),the sagging deformation decreases.This is likely due to the impact of the liquid jet formed by the collapsing bubble,which causes the girder deformation to shift from sagging back to hogging deformation.The initial shock wave excites the high-frequency response of the girder structure but contributes very little to the overall velocity and displacement.However,bubble pulsation typically causes a low-frequency response,which will affect the velocity and displacement of the girder.The low-pressure region of the flow field formed by bubble pulsation and resonant coupling between the girder and the bubble are the predominant causes of damage to the overall girder structure.展开更多
In recent years,there has been a rapid growth in Underwater Wireless Sensor Networks(UWSNs).The focus of research in this area is now on solving the problems associated with large-scale UWSN.One of the major issues in...In recent years,there has been a rapid growth in Underwater Wireless Sensor Networks(UWSNs).The focus of research in this area is now on solving the problems associated with large-scale UWSN.One of the major issues in such a network is the localization of underwater nodes.Localization is required for tracking objects and detecting the target.It is also considered tagging of data where sensed contents are not found of any use without localization.This is useless for application until the position of sensed content is confirmed.This article’s major goal is to review and analyze underwater node localization to solve the localization issues in UWSN.The present paper describes various existing localization schemes and broadly categorizes these schemes as Centralized and Distributed localization schemes underwater.Also,a detailed subdivision of these localization schemes is given.Further,these localization schemes are compared from different perspectives.The detailed analysis of these schemes in terms of certain performance metrics has been discussed in this paper.At the end,the paper addresses several future directions for potential research in improving localization problems of UWSN.展开更多
The polyacrylamide which is directly added into concrete shows strong water absorption property.Thus the construction of underwater constructure would demand high amount of water,resulting in poor workability of concr...The polyacrylamide which is directly added into concrete shows strong water absorption property.Thus the construction of underwater constructure would demand high amount of water,resulting in poor workability of concrete and strength shrinkage after hardening.Herein,a kind of anionic polyacrylamide(APAM)grafted with water reducing functional group(-COOH)was synthesized at low temperatures by partial factor design and response surface design.The structure and morphology of APAM were characterized by UV,FTIR and SEM methods.The experimental results show that the molecular weight of the synthesized APAM could reach 11 million,under the condition that the temperature was 35℃,the pH value was 8,the monomer concentration was 27wt%,the initiator dosage was 0.6wt%,and the monomer ratio(n(AM):n(AA))was 3.When the APAM was applied into the underwater slurry,it presented good flocculation and low water demand.When the dosage was 1%of the mass of the cement,the water demand increased by 12%,which could meet the self-leveling and anti-dispersity of the underwater slurry at the same time.This technology provides technical guidance for the large-scale industrial production of polyacrylamide for underwater concrete construction while achieving environmental protection during production.展开更多
Ionic gels can be potentially used in wearable devices owing to their high humidity resistance and non-volatility.However,the applicability of existing ionic gel pressure sensors is limited by their low sensitivity.Th...Ionic gels can be potentially used in wearable devices owing to their high humidity resistance and non-volatility.However,the applicability of existing ionic gel pressure sensors is limited by their low sensitivity.Therefore,it is very import-ant to develop an ionic gel pressure sensor with high sensitivity and a wide pressure detection range without sacrificing mechan-ical stretchability and self-healing ability.Herein,we report an effective strategy for developing pressure sensors based on ion-ic gel composites consisting of high-molecular-weight polymers,ionic liquids,and Au nanoparticles.The resulting capacitive pressure sensors exhibit high pressure sensitivity,fast response,and excellent self-healing properties.The sensors composed of highly hydrophobic polymers and ionic liquids can be used to track underwater movements,demonstrating broad application prospects in human motion state monitoring and underwater mechanical operations.展开更多
Due to the complexity of marine environment,underwater acoustic signal will be affected by complex background noise during transmission.Underwater acoustic signal denoising is always a difficult problem in underwater ...Due to the complexity of marine environment,underwater acoustic signal will be affected by complex background noise during transmission.Underwater acoustic signal denoising is always a difficult problem in underwater acoustic signal processing.To obtain a better denoising effect,a new denoising method of underwater acoustic signal based on optimized variational mode decomposition by black widow optimization algorithm(BVMD),fluctuation-based dispersion entropy threshold improved by Otsu method(OFDE),cosine similarity stationary threshold(CSST),BVMD,fluctuation-based dispersion entropy(FDE),named BVMD-OFDE-CSST-BVMD-FDE,is proposed.In the first place,decompose the original signal into a series of intrinsic mode functions(IMFs)by BVMD.Afterwards,distinguish pure IMFs,mixed IMFs and noise IMFs by OFDE and CSST,and reconstruct pure IMFs and mixed IMFs to obtain primary denoised signal.In the end,decompose primary denoising signal into IMFs by BVMD again,use the FDE value to distinguish noise IMFs and pure IMFs,and reconstruct pure IMFs to obtain the final denoised signal.The proposed mothod has three advantages:(i)BVMD can adaptively select the decomposition layer and penalty factor of VMD.(ii)FDE and CS are used as double criteria to distinguish noise IMFs from useful IMFs,and Otsu algorithm and CSST algorithm can effectively avoid the error caused by manually selecting thresholds.(iii)Secondary decomposition can make up for the deficiency of primary decomposition and further remove a small amount of noise.The chaotic signal and real ship signal are denoised.The experiment result shows that the proposed method can effectively denoise.It improves the denoising effect after primary decomposition,and has good practical value.展开更多
Hybrid-driven Underwater Glider(HUG)is a new type of underwater vehicle which integrates the functions of an Autonomous Underwater Glider(AUG)and an Autonomous Unmanned Vehicle(AUV).Although HUG has the characteristic...Hybrid-driven Underwater Glider(HUG)is a new type of underwater vehicle which integrates the functions of an Autonomous Underwater Glider(AUG)and an Autonomous Unmanned Vehicle(AUV).Although HUG has the characteristics of long endurance distance,its maneuverability still has room to be improved.This work introduces a new movement form of the neck of the underwater creature into HUG and proposes a parallel mechanism to adjust the attitude angle and displacement of the HUG’s bow,which can improve the steering maneuverability.Firstly,the influence of bow movement and rotation on the hydrodynamic force and flow field of the whole machine is analyzed by using the Computational Fluid Dynamics(CFD)method.The degree of freedom,attitude control range and movement amount of the Movable Bow Mechanism(MBM)are obtained,and then the design of MBM is completed based on these constraints.Secondly,the kinematic and dynamic models of MBM are established based on the closed vector method and the Lagrange equation,respectively,which are fully verified by comparing the results of simulation in Matlab and Adams software,then a Radial Basis Function(RBF)neural network adaptive sliding mode controller is designed to improve the dynamic response effect of the output parameters of MBM.Finally,a prototype of MBM is manufactured and assembled.The kinematic,dynamics model and controller are verified by experiments,which provides a basis for applying MBM in HUGs.展开更多
Reinforced concrete(RC)structures are common in engineering,and usually exposed to air or water,may be subjected to various blast scenarios.This paper aims to investigate the blast resistance of an airbacked RC slab a...Reinforced concrete(RC)structures are common in engineering,and usually exposed to air or water,may be subjected to various blast scenarios.This paper aims to investigate the blast resistance of an airbacked RC slab against underwater contact explosions(UWCEs).A detailed numerical model based on CLE method considering explosive,water,air,and RC slab is developed to examine the structural behavior of the air-backed RC slab due to UWCEs.At first,the reliability of the numerical method is validated by comparing the numerical results of an UWCE test with experimental data.Then,the difference in dynamic behavior of air-backed and water-backed RC slabs due to UWCEs is explored with the calibrated model.The results indicate that the blast response of the air-backed slab induced by UWCE is fiercer than that of water-backed slab with equal charge mass.In addition,parametric studies are also conducted to explore the effects of the charge mass,standoff distance,reinforcement spacing,concrete compression strength,and boundary condition on the blast performance of the air-backed RC slab.展开更多
As low-cost and highly autonomous ocean observation platforms,underwater gliders encounter risks during their launch and recovery,especially when coordinating multi-glider deployments.This work focuses on cooperative ...As low-cost and highly autonomous ocean observation platforms,underwater gliders encounter risks during their launch and recovery,especially when coordinating multi-glider deployments.This work focuses on cooperative path planning of an underwater glider fleet with simultaneous launch and recovery to enhance the autonomy of sampling and reduce deployment risks.Specifically,the gliders collaborate to achieve sampling considering the specified routines of interest.The overall paths to be planned are divided into four rectangular parts with the same starting point,and each glider is assigned a local sampling route.A clipped-oriented line-of-sight algorithm is proposed to ensure the coverage of the desired edges.The pitch angle of the glider is selected as the optimizing parameter to coordinate the overall progress considering the susceptibility of gliders to currents and the randomness of paths produced by complex navigational strategies.Therefore,a multi-actuation deep-Q network algorithm is proposed to ensure simultaneous launch and recovery.Simulation results demonstrate the acceptable effectiveness of the proposed method.展开更多
Aiming at the requirement of autonomous navigation capability of the underwater unmanned vehicle(UUV),a novel bionic method for underwater navigation based on polarization pattern within Snell’s window is proposed.In...Aiming at the requirement of autonomous navigation capability of the underwater unmanned vehicle(UUV),a novel bionic method for underwater navigation based on polarization pattern within Snell’s window is proposed.Inspired by creatures,polarization navigation is a satellite-free navigation scheme and has great potential to be used in the water.However,because of the complex underwater environment,whether UUV polarization navigation can be realized is doubtful.To illustrate the feasibility of underwater polarization navigation,we firstly establish the model of under-water polarization patterns to prove the stability and predictability of the underwater polarization pattern within Snell’s window.Then,we carry out static and dynamic experiments of underwater heading determination based on developed polarization information detection equipment.Finally,we obtain underwater polarization patterns and conduct the tracking experiment at different water depths.The experimental results of the underwater polarization patterns are consistent with the simulation,which proves the correctness of the proposed model.At the water depth of 5 m,the average angle and position error of the tracking experiment are 14.3508°and 4.0812 m,respectively.It is illustrated that underwater polarization navigation is realizable and the precision can meet the real-time navigation requirements of UUV.This study promotes the improvement of underwater navigation ability and the development of marine equipment.展开更多
Autonomous underwater vehicle(AUV)-assisted data collection is an efficient approach to implementing smart ocean.However,the data collection in time-varying ocean currents is plagued by two critical issues:AUV yaw and...Autonomous underwater vehicle(AUV)-assisted data collection is an efficient approach to implementing smart ocean.However,the data collection in time-varying ocean currents is plagued by two critical issues:AUV yaw and sensor node movement.We propose an adaptive AUV-assisted data collection strategy for ocean currents to address these issues.First,we consider the energy consumption of an AUV in conjunction with the value of information(VoI)over the sensor nodes and formulate an optimization problem to maximize the VoI-energy ratio.The AUV yaw problem is then solved by deriving the AUV's reachable region in different ocean current environments and the optimal cruising direction to the target nodes.Finally,using the predicted VoI-energy ratio,we sequentially design a distributed path planning algorithm to select the next target node for AUV.The simulation results indicate that the proposed strategy can utilize ocean currents to aid AUV navigation,thereby reducing the AUV's energy consumption and ensuring timely data collection.展开更多
基金supported in part by the National Natural Science Foundation of China(Nos.62071441 and 61701464)in part by the Fundamental Research Funds for the Central Universities(No.202151006).
文摘This study explores the application of single photon detection(SPD)technology in underwater wireless optical communication(UWOC)and analyzes the influence of different modulation modes and error correction coding types on communication performance.The study investigates the impact of on-off keying(OOK)and 2-pulse-position modulation(2-PPM)on the bit error rate(BER)in single-channel intensity and polarization multiplexing.Furthermore,it compares the error correction performance of low-density parity check(LDPC)and Reed-Solomon(RS)codes across different error correction coding types.The effects of unscattered photon ratio and depolarization ratio on BER are also verified.Finally,a UWOC system based on SPD is constructed,achieving 14.58 Mbps with polarization OOK multiplexing modulation and 4.37 Mbps with polarization 2-PPM multiplexing modulation using LDPC code error correction.
基金support of the National Key R&D Program of China(No.2022YFC2803903)the Key R&D Program of Zhejiang Province(No.2021C03013)the Zhejiang Provincial Natural Science Foundation of China(No.LZ20F020003).
文摘The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a classification model that combines an EfficientnetB0 neural network and a two-hidden-layer random vector functional link network(EfficientnetB0-TRVFL).The features of underwater images were extracted using the EfficientnetB0 neural network pretrained via ImageNet,and a new fully connected layer was trained on the underwater image dataset using the transfer learning method.Transfer learning ensures the initial performance of the network and helps in the development of a high-precision classification model.Subsequently,a TRVFL was proposed to improve the classification property of the model.Net construction of the two hidden layers exhibited a high accuracy when the same hidden layer nodes were used.The parameters of the second hidden layer were obtained using a novel calculation method,which reduced the outcome error to improve the performance instability caused by the random generation of parameters of RVFL.Finally,the TRVFL classifier was used to classify features and obtain classification results.The proposed EfficientnetB0-TRVFL classification model achieved 87.28%,74.06%,and 99.59%accuracy on the MLC2008,MLC2009,and Fish-gres datasets,respectively.The best convolutional neural networks and existing methods were stacked up through box plots and Kolmogorov-Smirnov tests,respectively.The increases imply improved systematization properties in underwater image classification tasks.The image classification model offers important performance advantages and better stability compared with existing methods.
基金the National Natural Science Foundation of China(62303012,62236002,61911004,62303008)。
文摘This paper investigates the tracking control problem for unmanned underwater vehicles(UUVs)systems with sensor faults,input saturation,and external disturbance caused by waves and ocean currents.An active sensor fault-tolerant control scheme is proposed.First,the developed method only requires the inertia matrix of the UUV,without other dynamic information,and can handle both additive and multiplicative sensor faults.Subsequently,an adaptive fault-tolerant controller is designed to achieve asymptotic tracking control of the UUV by employing robust integral of the sign of error feedback method.It is shown that the effect of sensor faults is online estimated and compensated by an adaptive estimator.With the proposed controller,the tracking error and estimation error can asymptotically converge to zero.Finally,simulation results are performed to demonstrate the effectiveness of the proposed method.
基金the National Natural Science Foundation of China(Grant No.42274119)the Liaoning Revitalization Talents Program(Grant No.XLYC2002082)+1 种基金National Key Research and Development Plan Key Special Projects of Science and Technology Military Civil Integration(Grant No.2022YFF1400500)the Key Project of Science and Technology Commission of the Central Military Commission.
文摘This study focuses on the improvement of path planning efficiency for underwater gravity-aided navigation.Firstly,a Depth Sorting Fast Search(DSFS)algorithm was proposed to improve the planning speed of the Quick Rapidly-exploring Random Trees*(Q-RRT*)algorithm.A cost inequality relationship between an ancestor and its descendants was derived,and the ancestors were filtered accordingly.Secondly,the underwater gravity-aided navigation path planning system was designed based on the DSFS algorithm,taking into account the fitness,safety,and asymptotic optimality of the routes,according to the gravity suitability distribution of the navigation space.Finally,experimental comparisons of the computing performance of the ChooseParent procedure,the Rewire procedure,and the combination of the two procedures for Q-RRT*and DSFS were conducted under the same planning environment and parameter conditions,respectively.The results showed that the computational efficiency of the DSFS algorithm was improved by about 1.2 times compared with the Q-RRT*algorithm while ensuring correct computational results.
基金supported in part by the National Key Research and Development Program of China(2020YFB1313002)the National Natural Science Foundation of China(62276023,U22B2055,62222302,U2013202)+1 种基金the Fundamental Research Funds for the Central Universities(FRF-TP-22-003C1)the Postgraduate Education Reform Project of Henan Province(2021SJGLX260Y)。
文摘Underwater image enhancement aims to restore a clean appearance and thus improves the quality of underwater degraded images.Current methods feed the whole image directly into the model for enhancement.However,they ignored that the R,G and B channels of underwater degraded images present varied degrees of degradation,due to the selective absorption for the light.To address this issue,we propose an unsupervised multi-expert learning model by considering the enhancement of each color channel.Specifically,an unsupervised architecture based on generative adversarial network is employed to alleviate the need for paired underwater images.Based on this,we design a generator,including a multi-expert encoder,a feature fusion module and a feature fusion-guided decoder,to generate the clear underwater image.Accordingly,a multi-expert discriminator is proposed to verify the authenticity of the R,G and B channels,respectively.In addition,content perceptual loss and edge loss are introduced into the loss function to further improve the content and details of the enhanced images.Extensive experiments on public datasets demonstrate that our method achieves more pleasing results in vision quality.Various metrics(PSNR,SSIM,UIQM and UCIQE) evaluated on our enhanced images have been improved obviously.
基金Scientific Research Fund of Liaoning Provincial Education Department(No.JGLX2021030):Research on Vision-Based Intelligent Perception Technology for the Survival of Benthic Organisms.
文摘For underwater robots in the process of performing target detection tasks,the color distortion and the uneven quality of underwater images lead to great difficulties in the feature extraction process of the model,which is prone to issues like error detection,omission detection,and poor accuracy.Therefore,this paper proposed the CER-YOLOv7(CBAM-EIOU-RepVGG-YOLOv7)underwater target detection algorithm.To improve the algorithm’s capability to retain valid features from both spatial and channel perspectives during the feature extraction phase,we have added a Convolutional Block Attention Module(CBAM)to the backbone network.The Reparameterization Visual Geometry Group(RepVGG)module is inserted into the backbone to improve the training and inference capabilities.The Efficient Intersection over Union(EIoU)loss is also used as the localization loss function,which reduces the error detection rate and missed detection rate of the algorithm.The experimental results of the CER-YOLOv7 algorithm on the UPRC(Underwater Robot Prototype Competition)dataset show that the mAP(mean Average Precision)score of the algorithm is 86.1%,which is a 2.2%improvement compared to the YOLOv7.The feasibility and validity of the CER-YOLOv7 are proved through ablation and comparison experiments,and it is more suitable for underwater target detection.
基金supported by the national key research and development program (No.2020YFB1806608)Jiangsu natural science foundation for distinguished young scholars (No.BK20220054)。
文摘Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual perception.Finally, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.
基金supported by the National Natural Science Foundation of China(No.51279033).
文摘Underwater direction of arrival(DOA)estimation has always been a very challenging theoretical and practical problem.Due to the serious non-stationary,non-linear,and non-Gaussian characteristics,machine learning based DOA estimation methods trained on simulated Gaussian noised array data cannot be directly applied to actual underwater DOA estimation tasks.In order to deal with this problem,environmental data with no target echoes can be employed to analyze the non-Gaussian components.Then,the obtained information about non-Gaussian components can be used to whiten the array data.Based on these considerations,a novel practical sonar array whitening method was proposed.Specifically,based on a weak assumption that the non-Gaussian components in adjacent patches with and without target echoes are almost the same,canonical cor-relation analysis(CCA)and non-negative matrix factorization(NMF)techniques are employed for whitening the array data.With the whitened array data,machine learning based DOA estimation models trained on simulated Gaussian noised datasets can be used to perform underwater DOA estimation tasks.Experimental results illustrated that,using actual underwater datasets for testing with known machine learning based DOA estimation models,accurate and robust DOA estimation performance can be achieved by using the proposed whitening method in different underwater con-ditions.
基金supported by the Foundation of Henan Key Laboratory of Underwater Intelligent Equipment under Grant No.KL02C2105Project of SongShan Laboratory under Grant No.YYJC062022012+2 种基金Training Plan for Young Backbone Teachers in Colleges and Universities in Henan Province under Grant No.2021GGJS077Key Scientific Research Projects of Colleges and Universities in Henan Province under Grant No.22A460022North China University of Water Resources and Electric Power Young Backbone Teacher Training Project under Grant No.2021-125-4.
文摘With the continuous development of the economy and society,plastic pollution in rivers,lakes,oceans,and other bodies of water is increasingly severe,posing a serious challenge to underwater ecosystems.Effective cleaning up of underwater litter by robots relies on accurately identifying and locating the plastic waste.However,it often causes significant challenges such as noise interference,low contrast,and blurred textures in underwater optical images.A weighted fusion-based algorithm for enhancing the quality of underwater images is proposed,which combines weighted logarithmic transformations,adaptive gamma correction,improved multi-scale Retinex(MSR)algorithm,and the contrast limited adaptive histogram equalization(CLAHE)algorithm.The proposed algorithm improves brightness,contrast,and color recovery and enhances detail features resulting in better overall image quality.A network framework is proposed in this article based on the YOLOv5 model.MobileViT is used as the backbone of the network framework,detection layer is added to improve the detection capability for small targets,self-attention and mixed-attention modules are introduced to enhance the recognition capability of important features.The cross stage partial(CSP)structure is employed in the spatial pyramid pooling(SPP)section to enrich feature information,and the complete intersection over union(CIOU)loss is replaced with the focal efficient intersection over union(EIOU)loss to accelerate convergence while improving regression accuracy.Experimental results proved that the target recognition algorithm achieved a recognition accuracy of 0.913 and ensured a recognition speed of 45.56 fps/s.Subsequently,Using red,green,blue and depth(RGB-D)camera to construct a system for identifying and locating underwater plastic waste.Experiments were conducted underwater for recognition,localization,and error analysis.The experimental results demonstrate the effectiveness of the proposed method for identifying and locating underwater plastic waste,and it has good localization accuracy.
基金supported by the National Natural Science Foundation of China(No.62271199)the Natural Science Foundation of Hunan Province,China(No.2020JJ5170)the Scientific Research Fund of Hunan Provincial Education Department(No.18C0299)。
文摘With the continuous development and utilization of marine resources,the underwater target detection has gradually become a popular research topic in the field of underwater robot operations and target detection.However,it is difficult to combine the environmental semantic information and the semantic information of targets at different scales by detection algorithms due to the complex underwater environment.In this paper,a cascade model based on the UGC-YOLO network structure with high detection accuracy is proposed.The YOLOv3 convolutional neural network is employed as the baseline structure.By fusing the global semantic information between two residual stages in the parallel structure of the feature extraction network,the perception of underwater targets is improved and the detection rate of hard-to-detect underwater objects is raised.Furthermore,the deformable convolution is applied to capture longrange semantic dependencies and PPM pooling is introduced in the highest layer network for aggregating semantic information.Finally,a multi-scale weighted fusion approach is presented for learning semantic information at different scales.Experiments are conducted on an underwater test dataset and the results have demonstrated that our proposed algorithm could detect aquatic targets in complex degraded underwater images.Compared with the baseline network algorithm,the Common Objects in Context(COCO)evaluation metric has been improved by 4.34%.
基金supported by the National Natural Science Foundation of China(Grant No.51679244).
文摘To investigate the overall damage characteristics and failure modes of a warship subjected to an underwater non-contact near-field explosion,a hull girder with a trapezoidal cross-section was designed,manufactured,and tested.The design criteria and parameters were determined according to the similarity criterion.Dynamic responses of the girder freely floating on water were obtained under varying conditions,including stand-off distance,charge mass,and position of attack.Damage morphologies of the girder model were obtained.Based on our analysis,basic conditions for sagging damage of the hull girder are proposed.The aim of this study was to determine an efficient method of attack resulting in the most severe damage to the ship hull.The experimental results show that the girder mainly exhibits a first-order response when the first wet frequency of the girder is close to the frequency of the explosion bubble pulsation.The largest deformation was observed when the underwater explosion occurred directly below the midspan of the girder compared to other explosions of the same intensity at different attack positions.When the ratio of stand-off to maximum bubble radius(λ)satisfies 0.7≤λ<2,the bubble mainly causes sagging damage instead of hogging.Asλdecreases(1≤λ<2),the sagging damage increases under the same charge mass.However,asλdecreases further(0.7≤λ<1),the sagging deformation decreases.This is likely due to the impact of the liquid jet formed by the collapsing bubble,which causes the girder deformation to shift from sagging back to hogging deformation.The initial shock wave excites the high-frequency response of the girder structure but contributes very little to the overall velocity and displacement.However,bubble pulsation typically causes a low-frequency response,which will affect the velocity and displacement of the girder.The low-pressure region of the flow field formed by bubble pulsation and resonant coupling between the girder and the bubble are the predominant causes of damage to the overall girder structure.
文摘In recent years,there has been a rapid growth in Underwater Wireless Sensor Networks(UWSNs).The focus of research in this area is now on solving the problems associated with large-scale UWSN.One of the major issues in such a network is the localization of underwater nodes.Localization is required for tracking objects and detecting the target.It is also considered tagging of data where sensed contents are not found of any use without localization.This is useless for application until the position of sensed content is confirmed.This article’s major goal is to review and analyze underwater node localization to solve the localization issues in UWSN.The present paper describes various existing localization schemes and broadly categorizes these schemes as Centralized and Distributed localization schemes underwater.Also,a detailed subdivision of these localization schemes is given.Further,these localization schemes are compared from different perspectives.The detailed analysis of these schemes in terms of certain performance metrics has been discussed in this paper.At the end,the paper addresses several future directions for potential research in improving localization problems of UWSN.
基金Funded by the National Natural Science Foundation of China(No.51778378)the Natural Science Foundation of Hebei Province(No.E2022210103)。
文摘The polyacrylamide which is directly added into concrete shows strong water absorption property.Thus the construction of underwater constructure would demand high amount of water,resulting in poor workability of concrete and strength shrinkage after hardening.Herein,a kind of anionic polyacrylamide(APAM)grafted with water reducing functional group(-COOH)was synthesized at low temperatures by partial factor design and response surface design.The structure and morphology of APAM were characterized by UV,FTIR and SEM methods.The experimental results show that the molecular weight of the synthesized APAM could reach 11 million,under the condition that the temperature was 35℃,the pH value was 8,the monomer concentration was 27wt%,the initiator dosage was 0.6wt%,and the monomer ratio(n(AM):n(AA))was 3.When the APAM was applied into the underwater slurry,it presented good flocculation and low water demand.When the dosage was 1%of the mass of the cement,the water demand increased by 12%,which could meet the self-leveling and anti-dispersity of the underwater slurry at the same time.This technology provides technical guidance for the large-scale industrial production of polyacrylamide for underwater concrete construction while achieving environmental protection during production.
基金supported by the National Natural Science Foundation of China(NSFC,Grant Nos.61874111,62174152 and 62022079)the National Key Research and Development Program of China(Grant No.2020YFB1506400)+1 种基金the Youth Innovation Promotion Association of the Chinese Academy of Sciences(No.2020115)the Strategic Priority Research Program of the Chinese Academy of Sciences(XDA16021200).
文摘Ionic gels can be potentially used in wearable devices owing to their high humidity resistance and non-volatility.However,the applicability of existing ionic gel pressure sensors is limited by their low sensitivity.Therefore,it is very import-ant to develop an ionic gel pressure sensor with high sensitivity and a wide pressure detection range without sacrificing mechan-ical stretchability and self-healing ability.Herein,we report an effective strategy for developing pressure sensors based on ion-ic gel composites consisting of high-molecular-weight polymers,ionic liquids,and Au nanoparticles.The resulting capacitive pressure sensors exhibit high pressure sensitivity,fast response,and excellent self-healing properties.The sensors composed of highly hydrophobic polymers and ionic liquids can be used to track underwater movements,demonstrating broad application prospects in human motion state monitoring and underwater mechanical operations.
基金supported by the National Natural Science Foundation of China(Grant No.51709228)。
文摘Due to the complexity of marine environment,underwater acoustic signal will be affected by complex background noise during transmission.Underwater acoustic signal denoising is always a difficult problem in underwater acoustic signal processing.To obtain a better denoising effect,a new denoising method of underwater acoustic signal based on optimized variational mode decomposition by black widow optimization algorithm(BVMD),fluctuation-based dispersion entropy threshold improved by Otsu method(OFDE),cosine similarity stationary threshold(CSST),BVMD,fluctuation-based dispersion entropy(FDE),named BVMD-OFDE-CSST-BVMD-FDE,is proposed.In the first place,decompose the original signal into a series of intrinsic mode functions(IMFs)by BVMD.Afterwards,distinguish pure IMFs,mixed IMFs and noise IMFs by OFDE and CSST,and reconstruct pure IMFs and mixed IMFs to obtain primary denoised signal.In the end,decompose primary denoising signal into IMFs by BVMD again,use the FDE value to distinguish noise IMFs and pure IMFs,and reconstruct pure IMFs to obtain the final denoised signal.The proposed mothod has three advantages:(i)BVMD can adaptively select the decomposition layer and penalty factor of VMD.(ii)FDE and CS are used as double criteria to distinguish noise IMFs from useful IMFs,and Otsu algorithm and CSST algorithm can effectively avoid the error caused by manually selecting thresholds.(iii)Secondary decomposition can make up for the deficiency of primary decomposition and further remove a small amount of noise.The chaotic signal and real ship signal are denoised.The experiment result shows that the proposed method can effectively denoise.It improves the denoising effect after primary decomposition,and has good practical value.
基金supported by the National Key R&D Program of China,the Laoshan Laboratory Science and Technology Innovation Project (Nos.LSKJ202200200,LSKJ202202801 and LSKJ202202802)the National Natural Science Foundation of China (No.51721003)Aoshan Talent Cultivation Program (No.2017ASTCP-OE01)of the Pilot National Laboratory for Marine Science and Technology (Qingdao).
文摘Hybrid-driven Underwater Glider(HUG)is a new type of underwater vehicle which integrates the functions of an Autonomous Underwater Glider(AUG)and an Autonomous Unmanned Vehicle(AUV).Although HUG has the characteristics of long endurance distance,its maneuverability still has room to be improved.This work introduces a new movement form of the neck of the underwater creature into HUG and proposes a parallel mechanism to adjust the attitude angle and displacement of the HUG’s bow,which can improve the steering maneuverability.Firstly,the influence of bow movement and rotation on the hydrodynamic force and flow field of the whole machine is analyzed by using the Computational Fluid Dynamics(CFD)method.The degree of freedom,attitude control range and movement amount of the Movable Bow Mechanism(MBM)are obtained,and then the design of MBM is completed based on these constraints.Secondly,the kinematic and dynamic models of MBM are established based on the closed vector method and the Lagrange equation,respectively,which are fully verified by comparing the results of simulation in Matlab and Adams software,then a Radial Basis Function(RBF)neural network adaptive sliding mode controller is designed to improve the dynamic response effect of the output parameters of MBM.Finally,a prototype of MBM is manufactured and assembled.The kinematic,dynamics model and controller are verified by experiments,which provides a basis for applying MBM in HUGs.
基金The supports from the Natural Science Research of Jiangsu Higher Education Institutions of China(21KJB580001)the National Natural Science Foundation of China(Grant No.52209162,51979152)+2 种基金Educational Commission of Hubei Province of China(T2020005)Young Top-notch Talent Cultivation Program of Hubei ProvinceJiangxi Provincial Natural Science Foundation(20212BAB214044)。
文摘Reinforced concrete(RC)structures are common in engineering,and usually exposed to air or water,may be subjected to various blast scenarios.This paper aims to investigate the blast resistance of an airbacked RC slab against underwater contact explosions(UWCEs).A detailed numerical model based on CLE method considering explosive,water,air,and RC slab is developed to examine the structural behavior of the air-backed RC slab due to UWCEs.At first,the reliability of the numerical method is validated by comparing the numerical results of an UWCE test with experimental data.Then,the difference in dynamic behavior of air-backed and water-backed RC slabs due to UWCEs is explored with the calibrated model.The results indicate that the blast response of the air-backed slab induced by UWCE is fiercer than that of water-backed slab with equal charge mass.In addition,parametric studies are also conducted to explore the effects of the charge mass,standoff distance,reinforcement spacing,concrete compression strength,and boundary condition on the blast performance of the air-backed RC slab.
基金supported by the National Natural Science Foundation of China(No.51909252)the Fundamental Research Funds for the Central Universities(No.202061004)This work is also partly supported by the China Scholar Council.
文摘As low-cost and highly autonomous ocean observation platforms,underwater gliders encounter risks during their launch and recovery,especially when coordinating multi-glider deployments.This work focuses on cooperative path planning of an underwater glider fleet with simultaneous launch and recovery to enhance the autonomy of sampling and reduce deployment risks.Specifically,the gliders collaborate to achieve sampling considering the specified routines of interest.The overall paths to be planned are divided into four rectangular parts with the same starting point,and each glider is assigned a local sampling route.A clipped-oriented line-of-sight algorithm is proposed to ensure the coverage of the desired edges.The pitch angle of the glider is selected as the optimizing parameter to coordinate the overall progress considering the susceptibility of gliders to currents and the randomness of paths produced by complex navigational strategies.Therefore,a multi-actuation deep-Q network algorithm is proposed to ensure simultaneous launch and recovery.Simulation results demonstrate the acceptable effectiveness of the proposed method.
基金supported by the National Natural Science Foundation of China(Grant No.52175265).
文摘Aiming at the requirement of autonomous navigation capability of the underwater unmanned vehicle(UUV),a novel bionic method for underwater navigation based on polarization pattern within Snell’s window is proposed.Inspired by creatures,polarization navigation is a satellite-free navigation scheme and has great potential to be used in the water.However,because of the complex underwater environment,whether UUV polarization navigation can be realized is doubtful.To illustrate the feasibility of underwater polarization navigation,we firstly establish the model of under-water polarization patterns to prove the stability and predictability of the underwater polarization pattern within Snell’s window.Then,we carry out static and dynamic experiments of underwater heading determination based on developed polarization information detection equipment.Finally,we obtain underwater polarization patterns and conduct the tracking experiment at different water depths.The experimental results of the underwater polarization patterns are consistent with the simulation,which proves the correctness of the proposed model.At the water depth of 5 m,the average angle and position error of the tracking experiment are 14.3508°and 4.0812 m,respectively.It is illustrated that underwater polarization navigation is realizable and the precision can meet the real-time navigation requirements of UUV.This study promotes the improvement of underwater navigation ability and the development of marine equipment.
基金supported by the National Natural Science Foundation of China(62071472,62101556)the Natural Science Foundation of Jiangsu province(BK20200650,BK20210489)the Future Network Scientific Research Fund Project(FNSRFP2021-YB-12)。
文摘Autonomous underwater vehicle(AUV)-assisted data collection is an efficient approach to implementing smart ocean.However,the data collection in time-varying ocean currents is plagued by two critical issues:AUV yaw and sensor node movement.We propose an adaptive AUV-assisted data collection strategy for ocean currents to address these issues.First,we consider the energy consumption of an AUV in conjunction with the value of information(VoI)over the sensor nodes and formulate an optimization problem to maximize the VoI-energy ratio.The AUV yaw problem is then solved by deriving the AUV's reachable region in different ocean current environments and the optimal cruising direction to the target nodes.Finally,using the predicted VoI-energy ratio,we sequentially design a distributed path planning algorithm to select the next target node for AUV.The simulation results indicate that the proposed strategy can utilize ocean currents to aid AUV navigation,thereby reducing the AUV's energy consumption and ensuring timely data collection.
