Recycled aggregate concrete refers to a new type of concrete material made by processing waste concrete materials through grading,crushing,and cleaning,and then mixing them with cement,water,and other materials in a c...Recycled aggregate concrete refers to a new type of concrete material made by processing waste concrete materials through grading,crushing,and cleaning,and then mixing them with cement,water,and other materials in a certain gradation or proportion.This type of concrete is highly suitable for modern construction waste disposal and reuse and has been widely used in various construction projects.It can also be used as an environmentally friendly permeable brick material to promote the development of modern green buildings.However,practical applications have found that compared to ordinary concrete,the durability of this type of concrete is more susceptible to high-temperature and complex environments.Based on this,this paper conducts theoretical research on its durability in high-temperature and complex environments,including the current research status,existing problems,and application prospects of recycled aggregate concrete’s durability in such environments.It is hoped that this analysis can provide some reference for studying the influence of high-temperature and complex environments on recycled aggregate concrete and its subsequent application strategies.展开更多
In recent decades,path planning for unmanned surface vehicles(USVs)in complex environments,such as harbours and coastlines,has become an important concern.The existing algorithms for real-time path planning for USVs a...In recent decades,path planning for unmanned surface vehicles(USVs)in complex environments,such as harbours and coastlines,has become an important concern.The existing algorithms for real-time path planning for USVs are either too slow at replanning or unreliable in changing environments with multiple dynamic obstacles.In this study,we developed a novel path planning method based on the D^(*) lite algorithm for real-time path planning of USVs in complex environments.The proposed method has the following advantages:(1)the computational time for replanning is reduced significantly owing to the use of an incremental algorithm and a new method for modelling dynamic obstacles;(2)a constrained artificial potential field method is employed to enhance the safety of the planned paths;and(3)the method is practical in terms of vehicle performance.The performance of the proposed method was evaluated through simulations and compared with those of existing algorithms.The simulation results confirmed the efficiency of the method for real-time path planning of USVs in complex environments.展开更多
The Internet of Things(IoT)has become an integral part of various industries,from smart cities to healthcare,driving the need for energy-efficient and stable devices,especially in complex and unpredictable environment...The Internet of Things(IoT)has become an integral part of various industries,from smart cities to healthcare,driving the need for energy-efficient and stable devices,especially in complex and unpredictable environments.This research investigates the optimization of energy consumption and the enhancement of stability in IoT devices operating in such environments.The study addresses key challenges,including resource constraints,fluctuating environmental conditions,and the increasing complexity of IoT networks.It explores various energy optimization techniques,such as low-power communication protocols,edge and cloud computing,and machine learning models,that help reduce energy usage while maintaining performance.Furthermore,it examines stability enhancement strategies,including fault-tolerant mechanisms,resilient network architectures,and real-time monitoring and adaptive control,that ensure the continuous and reliable operation of IoT devices despite external disruptions.The findings of this research contribute to the development of next-generation IoT systems that are both energy-efficient and resilient,thereby promoting sustainable deployment in real-world applications.展开更多
Complex environments featuring variable lighting and backgrounds similar in color to the target objects present challenges for the rapid and accurate detection of tobacco leaves,which is critical for the development o...Complex environments featuring variable lighting and backgrounds similar in color to the target objects present challenges for the rapid and accurate detection of tobacco leaves,which is critical for the development of automated tobacco leaf harvesting robots.This study introduces a depth filtering approach to filter out complex regions based on distance information,thereby simplifying the detection task,and proposes a lightweight detection method based on an enhanced YOLOv5s model.Initially,the YOLOv5s backbone network is substituted with a more lightweight MobileNetV2 to reduce the model size.Subsequently,sparse model training combined with the scaling factor distribution rules of batch normalization layers is utilized to identify and eliminate inconsequential neural network channels.Finally,fine-tuning and knowledge distillation techniques are employed to achieve a model accuracy close to the YOLOv5s baseline.Experimental results indicate that the depth filtering method can improve the model’s precision,recall,and mean Average Precision(mAP)by 11.2%,29.6%,and 17.1%,respectively.The optimized lightweight model achieves a precision of 91.1%,a recall of 90.8%,and an mAP of 91.6%,with a memory footprint of only 1.4MB.It delivers a detection frame rate of 112 fps on desktop computers and 21 fps on mobile devices,which is approximately 3.5 and 4 times faster,respectively,compared to the baseline YOLOv5s tobacco leaf detection model.The precision,recall,and mAP experience a marginal decrease of 3.8,1.6,and 2.8 percentage points,respectively,while the memory consumption is merely 10%of the pre-optimization amount.In summary,the proposed method enables the accurate detection of tobacco leaves against near-color backgrounds.Simultaneously,it achieves effective lightweighting of the model without compromising its performance,thereby providing technical support for deploying tobacco leaf detection on mobile platforms.展开更多
With the increasing global demand for renewable energy,the application of photovoltaic power generation in mountainous areas is gradually increasing.However,the complex wind environment in mountainous areas poses seve...With the increasing global demand for renewable energy,the application of photovoltaic power generation in mountainous areas is gradually increasing.However,the complex wind environment in mountainous areas poses severe challenges to the design and optimization of solar photovoltaic brackets.Traditional design methods are difficult to cope with the changeable wind speed and direction in mountainous areas,resulting in structural instability or material waste.Researchers have identified the key factors affecting wind response through parametric research and dynamic wind response analysis,so as to optimize the brackets design and improve its adaptability and stability in complex wind environments.In this paper,the complexity of wind speed,wind direction and turbulence characteristics in mountainous areas and their influence on brackets design are explored.Through static and dynamic wind load analysis,the geometrical shape and material selection of the bracket are optimized to enhance its wind resistance.The application of multi-objective optimization model and intelligent optimization algorithm provides an effective solution for the design of solar photovoltaic brackets,ensuring their safety and reliability in complex wind environments.展开更多
Underwater imaging is frequently influenced by factors such as illumination,scattering,and refraction,which can result in low image contrast and blurriness.Moreover,the presence of numerous small,overlapping targets r...Underwater imaging is frequently influenced by factors such as illumination,scattering,and refraction,which can result in low image contrast and blurriness.Moreover,the presence of numerous small,overlapping targets reduces detection accuracy.To address these challenges,first,green channel images are preprocessed to rectify color bias while improving contrast and clarity.Se-cond,the YOLO-DBS network that employs deformable convolution is proposed to enhance feature learning from underwater blurry images.The ECA attention mechanism is also introduced to strengthen feature focus.Moreover,a bidirectional feature pyramid net-work is utilized for efficient multilayer feature fusion while removing nodes that contribute minimally to detection performance.In addition,the SIoU loss function that considers factors such as angular error and distance deviation is incorporated into the network.Validation on the RUOD dataset demonstrates that YOLO-DBS achieves approximately 3.1%improvement in mAP@0.5 compared with YOLOv8n and surpasses YOLOv9-tiny by 1.3%.YOLO-DBS reduces parameter count by 32%relative to YOLOv8n,thereby demonstrating superior performance in real-time detection on underwater observation platforms.展开更多
This paper presents a 3D path planning algorithm for an unmanned aerial vehicle （UAV） in complex environments. In this algorithm, the environments are divided into voxels by octree algorithm. In order to satisfy the...This paper presents a 3D path planning algorithm for an unmanned aerial vehicle （UAV） in complex environments. In this algorithm, the environments are divided into voxels by octree algorithm. In order to satisfy the safety requirement of the UAV, free space is represented by free voxels, which have enough space margin for the UAV to pass through. A bounding box array is created in the whole 3D space to evaluate the free voxel connectivity. The probabilistic roadmap method （PRM） is improved by random sampling in the bounding box array to ensure a more efficient distribution of roadmap nodes in 3D space. According to the connectivity evaluation, the roadmap is used to plan a feasible path by using A＊ algorithm. Experimental results indicate that the proposed algorithm is valid in complex 3D environments.展开更多
In recent years,the rapid development of artificial intelligence has driven the widespread deployment of visual systems in complex environments such as autonomous driving,security surveillance,and medical diagnosis.Ho...In recent years,the rapid development of artificial intelligence has driven the widespread deployment of visual systems in complex environments such as autonomous driving,security surveillance,and medical diagnosis.However,existing image sensors—such as CMOS and CCD devices—intrinsically suffer from the limitation of fixed spectral response.Especially in environments with strong glare,haze,or dust,external spectral conditions often severely mismatch the device's design range,leading to significant degradation in image quality and a sharp drop in target recognition accuracy.While algorithmic post-processing(such as color bias correction or background suppression)can mitigate these issues,algorithm approaches typically introduce computational latency and increased energy consumption,making them unsuitable for edge computing or high-speed scenarios.展开更多
Detecting individuals wearing safety helmets in complex environments faces several challenges.These factors include limited detection accuracy and frequent missed or false detections.Additionally,existing algorithms o...Detecting individuals wearing safety helmets in complex environments faces several challenges.These factors include limited detection accuracy and frequent missed or false detections.Additionally,existing algorithms often have excessive parameter counts,complex network structures,and high computational demands.These challenges make it difficult to deploy such models efficiently on resource-constrained devices like embedded systems.Aiming at this problem,this research proposes an optimized and lightweight solution called FGP-YOLOv8,an improved version of YOLOv8n.The YOLOv8 backbone network is replaced with the FasterNet model to reduce parameters and computational demands while local convolution layers are added.This modification minimizes computational costs with only a minor impact on accuracy.A new GSTA(GSConv-Triplet Attention)module is introduced to enhance feature fusion and reduce computational complexity.This is achieved using attention weights generated from dimensional interactions within the feature map.Additionally,the ParNet-C2f module replaces the original C2f(CSP Bottleneck with 2 Convolutions)module,improving feature extraction for safety helmets of various shapes and sizes.The CIoU(Complete-IoU)is replaced with the WIoU(Wise-IoU)to boost performance further,enhancing detection accuracy and generalization capabilities.Experimental results validate the improvements.The proposedmodel reduces the parameter count by 19.9% and the computational load by 18.5%.At the same time,mAP(mean average precision)increases by 2.3%,and precision improves by 1.2%.These results demonstrate the model’s robust performance in detecting safety helmets across diverse environments.展开更多
This study introduces a novel algorithm known as the dung beetle optimization algorithm based on bounded reflection optimization andmulti-strategy fusion(BFDBO),which is designed to tackle the complexities associated ...This study introduces a novel algorithm known as the dung beetle optimization algorithm based on bounded reflection optimization andmulti-strategy fusion(BFDBO),which is designed to tackle the complexities associated with multi-UAV collaborative trajectory planning in intricate battlefield environments.Initially,a collaborative planning cost function for the multi-UAV system is formulated,thereby converting the trajectory planning challenge into an optimization problem.Building on the foundational dung beetle optimization(DBO)algorithm,BFDBO incorporates three significant innovations:a boundary reflection mechanism,an adaptive mixed exploration strategy,and a dynamic multi-scale mutation strategy.These enhancements are intended to optimize the equilibrium between local exploration and global exploitation,facilitating the discovery of globally optimal trajectories thatminimize the cost function.Numerical simulations utilizing the CEC2022 benchmark function indicate that all three enhancements of BFDBOpositively influence its performance,resulting in accelerated convergence and improved optimization accuracy relative to leading optimization algorithms.In two battlefield scenarios of varying complexities,BFDBO achieved a minimum of a 39% reduction in total trajectory planning costs when compared to DBO and three other highperformance variants,while also demonstrating superior average runtime.This evidence underscores the effectiveness and applicability of BFDBO in practical,real-world contexts.展开更多
With China and Africa having worked hand in hand for mutual benefits for a long time,China-Africa economic and trade cooperation has developed steadily,achieving significant progress in many fields.However,at the same...With China and Africa having worked hand in hand for mutual benefits for a long time,China-Africa economic and trade cooperation has developed steadily,achieving significant progress in many fields.However,at the same time,the environment in which China-Africa economic and trade cooperation operates is becoming increasingly complex.Risks and challenges from different levels are worth noticing.展开更多
Mid-Year Marine Economy Report Developing the marine economy and building China into a maritime powerhouse are of great significance for China’s socio-economic sustainable development,as well as for advancing its mod...Mid-Year Marine Economy Report Developing the marine economy and building China into a maritime powerhouse are of great significance for China’s socio-economic sustainable development,as well as for advancing its modernization drive.Recently released data from the Ministry of Natural Resources shows that during the first half of 2025,despite a complex and volatile external environment,China’s marine economy withstood the pressure and maintained a steady and positive development trend.展开更多
Studying and analyzing the dynamic behavior of offshore wind turbines are of great importance to ensure the safety and improve the efficiency of such expensive equipments.In this work,a tapered beam model is proposed ...Studying and analyzing the dynamic behavior of offshore wind turbines are of great importance to ensure the safety and improve the efficiency of such expensive equipments.In this work,a tapered beam model is proposed to investigate the dynamic response of an offshore wind turbine tower on the monopile foundation assembled with rotating blades in the complex ocean environment.Several environment factors like wind,wave,current,and soil resistance are taken into account.The proposed model is ana-lytically solved with the Galerkin method.Based on the numerical results,the effects of various structure parameters including the taper angle,the height and thickness of the tower,the depth,and the diameter and the cement filler of the monopile on the funda-mental natural frequency of the wind turbine tower system are investigated in detail.It is found that the fundamental natural frequency decreases with the increase in the taper angle and the height and thickness of the tower,and increases with the increase in the diameter of the monopile.Moreover,filling cement into the monopile can effectively im-prove the fundamental natural frequency of the wind turbine tower system,but there is a critical value of the amount of cement maximizing the property of the monopile.This research may be helpful in the design and safety evaluation of offshore wind turbines.展开更多
In virtue of effect of N-S intensive ground stress and mining disturbance to +579E2EB_(1+2) mining site at Weihuliang Mine,the dip angle and section height is 65° and 52 m,respectively,the collapses happed freque...In virtue of effect of N-S intensive ground stress and mining disturbance to +579E2EB_(1+2) mining site at Weihuliang Mine,the dip angle and section height is 65° and 52 m,respectively,the collapses happed frequently during mining.Firstly,mining condi- tions,spatial structure and parameters were investigated.Then physical simulation and dynamic numerical tracing and elaborate simulation relating roof and top-coal were ap- plied based on 2D-Block Program and quantitative regularity of stress at variable depths had been estimated.Furthermore,it was manifested that effective measures,i.e.,fast mining,control symmetrical top-coal-caving at dip and strike directions,optimizing ventila- tion system,active-stereo preventing gas were performed successfully in mining practice. Ultimately,the derived dynamic hazard were prevented so as to safety mining.展开更多
With the development of unmanned driving technology,intelligent robots and drones,high-precision localization,navigation and state estimation technologies have also made great progress.Traditional global navigation sa...With the development of unmanned driving technology,intelligent robots and drones,high-precision localization,navigation and state estimation technologies have also made great progress.Traditional global navigation satellite system/inertial navigation system(GNSS/INS)integrated navigation systems can provide high-precision navigation information continuously.However,when this system is applied to indoor or GNSS-denied environments,such as outdoor substations with strong electromagnetic interference and complex dense spaces,it is often unable to obtain high-precision GNSS positioning data.The positioning and orientation errors will diverge and accumulate rapidly,which cannot meet the high-precision localization requirements in large-scale and long-distance navigation scenarios.This paper proposes a method of high-precision state estimation with fusion of GNSS/INS/Vision using a nonlinear optimizer factor graph optimization as the basis for multi-source optimization.Through the collected experimental data and simulation results,this system shows good performance in the indoor environment and the environment with partial GNSS signal loss.展开更多
1 Introduction Constrained Reinforcement Learning(CRL),modeled as a Constrained Markov Decision Process(CMDP)[1,2],is commonly used to address applications with security restrictions.Previous works[3]primarily focused...1 Introduction Constrained Reinforcement Learning(CRL),modeled as a Constrained Markov Decision Process(CMDP)[1,2],is commonly used to address applications with security restrictions.Previous works[3]primarily focused on the single-constraint issue,overlooking the more common multi-constraint setting which involves extensive computations and combinatorial optimization of multiple Lagrange multipliers.展开更多
Shield tunneling is an important link in the current subway construction. It has a high level of automation, which greatly improves the construction efficiency. At the same time, subway shield construction can also re...Shield tunneling is an important link in the current subway construction. It has a high level of automation, which greatly improves the construction efficiency. At the same time, subway shield construction can also reduce the impact of urban ground traffic, so it has been widely used in the construction of subway projects. In this paper, the technology and construction technology of shield tunneling under complex environment are studied and analyzed for reference.展开更多
Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and ...Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.展开更多
A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very co...A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very complicated,and the fault characteristic signal is weak and hard to extract.Firstly,the best wavelet base Cmor 3-3 is selected by comparing 6 different wavelet base types.Secondly,continuous wavelet transform(CWT)is applied to the acquired original vibration signal to generate the feature map and process the gray level.Finally,the improved ResNeXt network is used to diagnose faults in precision machining equipment.The experimental results show that the proposed CWT and the improved ResNeXt algorithm have high accuracy in identifying precision machining equipment faults in complex environments,with an average accuracy of 99.4%。展开更多
基金Chongqing Municipal Education Commission Science and Technology Research Project(Project No.KJQN202301910).
文摘Recycled aggregate concrete refers to a new type of concrete material made by processing waste concrete materials through grading,crushing,and cleaning,and then mixing them with cement,water,and other materials in a certain gradation or proportion.This type of concrete is highly suitable for modern construction waste disposal and reuse and has been widely used in various construction projects.It can also be used as an environmentally friendly permeable brick material to promote the development of modern green buildings.However,practical applications have found that compared to ordinary concrete,the durability of this type of concrete is more susceptible to high-temperature and complex environments.Based on this,this paper conducts theoretical research on its durability in high-temperature and complex environments,including the current research status,existing problems,and application prospects of recycled aggregate concrete’s durability in such environments.It is hoped that this analysis can provide some reference for studying the influence of high-temperature and complex environments on recycled aggregate concrete and its subsequent application strategies.
基金financially supported by the Cultivation of Scientific Research Ability of Young Talents of Shanghai Jiao Tong University(Grant No.19X100040072)the Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education(Grant No.MIES-2020-07)。
文摘In recent decades,path planning for unmanned surface vehicles(USVs)in complex environments,such as harbours and coastlines,has become an important concern.The existing algorithms for real-time path planning for USVs are either too slow at replanning or unreliable in changing environments with multiple dynamic obstacles.In this study,we developed a novel path planning method based on the D^(*) lite algorithm for real-time path planning of USVs in complex environments.The proposed method has the following advantages:(1)the computational time for replanning is reduced significantly owing to the use of an incremental algorithm and a new method for modelling dynamic obstacles;(2)a constrained artificial potential field method is employed to enhance the safety of the planned paths;and(3)the method is practical in terms of vehicle performance.The performance of the proposed method was evaluated through simulations and compared with those of existing algorithms.The simulation results confirmed the efficiency of the method for real-time path planning of USVs in complex environments.
文摘The Internet of Things(IoT)has become an integral part of various industries,from smart cities to healthcare,driving the need for energy-efficient and stable devices,especially in complex and unpredictable environments.This research investigates the optimization of energy consumption and the enhancement of stability in IoT devices operating in such environments.The study addresses key challenges,including resource constraints,fluctuating environmental conditions,and the increasing complexity of IoT networks.It explores various energy optimization techniques,such as low-power communication protocols,edge and cloud computing,and machine learning models,that help reduce energy usage while maintaining performance.Furthermore,it examines stability enhancement strategies,including fault-tolerant mechanisms,resilient network architectures,and real-time monitoring and adaptive control,that ensure the continuous and reliable operation of IoT devices despite external disruptions.The findings of this research contribute to the development of next-generation IoT systems that are both energy-efficient and resilient,thereby promoting sustainable deployment in real-world applications.
基金supported by the Horizontal Research Project of China Agricultural University(Project No.202405410711069).
文摘Complex environments featuring variable lighting and backgrounds similar in color to the target objects present challenges for the rapid and accurate detection of tobacco leaves,which is critical for the development of automated tobacco leaf harvesting robots.This study introduces a depth filtering approach to filter out complex regions based on distance information,thereby simplifying the detection task,and proposes a lightweight detection method based on an enhanced YOLOv5s model.Initially,the YOLOv5s backbone network is substituted with a more lightweight MobileNetV2 to reduce the model size.Subsequently,sparse model training combined with the scaling factor distribution rules of batch normalization layers is utilized to identify and eliminate inconsequential neural network channels.Finally,fine-tuning and knowledge distillation techniques are employed to achieve a model accuracy close to the YOLOv5s baseline.Experimental results indicate that the depth filtering method can improve the model’s precision,recall,and mean Average Precision(mAP)by 11.2%,29.6%,and 17.1%,respectively.The optimized lightweight model achieves a precision of 91.1%,a recall of 90.8%,and an mAP of 91.6%,with a memory footprint of only 1.4MB.It delivers a detection frame rate of 112 fps on desktop computers and 21 fps on mobile devices,which is approximately 3.5 and 4 times faster,respectively,compared to the baseline YOLOv5s tobacco leaf detection model.The precision,recall,and mAP experience a marginal decrease of 3.8,1.6,and 2.8 percentage points,respectively,while the memory consumption is merely 10%of the pre-optimization amount.In summary,the proposed method enables the accurate detection of tobacco leaves against near-color backgrounds.Simultaneously,it achieves effective lightweighting of the model without compromising its performance,thereby providing technical support for deploying tobacco leaf detection on mobile platforms.
文摘With the increasing global demand for renewable energy,the application of photovoltaic power generation in mountainous areas is gradually increasing.However,the complex wind environment in mountainous areas poses severe challenges to the design and optimization of solar photovoltaic brackets.Traditional design methods are difficult to cope with the changeable wind speed and direction in mountainous areas,resulting in structural instability or material waste.Researchers have identified the key factors affecting wind response through parametric research and dynamic wind response analysis,so as to optimize the brackets design and improve its adaptability and stability in complex wind environments.In this paper,the complexity of wind speed,wind direction and turbulence characteristics in mountainous areas and their influence on brackets design are explored.Through static and dynamic wind load analysis,the geometrical shape and material selection of the bracket are optimized to enhance its wind resistance.The application of multi-objective optimization model and intelligent optimization algorithm provides an effective solution for the design of solar photovoltaic brackets,ensuring their safety and reliability in complex wind environments.
基金funded by the Jilin City Science and Technology Innovation Development Plan Project(No.20240302014)the Jilin Provincial Department of Educa-tion Science and Technology Research Project(No.JJKH 20250879KJ)the Jilin Province Science and Tech-nology Development Plan Project(No.YDZJ202401640 ZYTS).
文摘Underwater imaging is frequently influenced by factors such as illumination,scattering,and refraction,which can result in low image contrast and blurriness.Moreover,the presence of numerous small,overlapping targets reduces detection accuracy.To address these challenges,first,green channel images are preprocessed to rectify color bias while improving contrast and clarity.Se-cond,the YOLO-DBS network that employs deformable convolution is proposed to enhance feature learning from underwater blurry images.The ECA attention mechanism is also introduced to strengthen feature focus.Moreover,a bidirectional feature pyramid net-work is utilized for efficient multilayer feature fusion while removing nodes that contribute minimally to detection performance.In addition,the SIoU loss function that considers factors such as angular error and distance deviation is incorporated into the network.Validation on the RUOD dataset demonstrates that YOLO-DBS achieves approximately 3.1%improvement in mAP@0.5 compared with YOLOv8n and surpasses YOLOv9-tiny by 1.3%.YOLO-DBS reduces parameter count by 32%relative to YOLOv8n,thereby demonstrating superior performance in real-time detection on underwater observation platforms.
基金supported by National Natural Science Foundation of China(No.61305128)Fundamental Research Funds for the Central Universities,and U.S.Army Research Ofce(No.W911NF-091-0565)
文摘This paper presents a 3D path planning algorithm for an unmanned aerial vehicle （UAV） in complex environments. In this algorithm, the environments are divided into voxels by octree algorithm. In order to satisfy the safety requirement of the UAV, free space is represented by free voxels, which have enough space margin for the UAV to pass through. A bounding box array is created in the whole 3D space to evaluate the free voxel connectivity. The probabilistic roadmap method （PRM） is improved by random sampling in the bounding box array to ensure a more efficient distribution of roadmap nodes in 3D space. According to the connectivity evaluation, the roadmap is used to plan a feasible path by using A＊ algorithm. Experimental results indicate that the proposed algorithm is valid in complex 3D environments.
基金supported in part by STI 2030-Major Projects(2022ZD0209200)in part by National Natural Science Foundation of China(62374099)+2 种基金in part by Beijing Natural Science Foundation−Xiaomi Innovation Joint Fund(L233009)Beijing Natural Science Foundation(L248104)in part by Independent Research Program of School of Integrated Circuits,Tsinghua University,in part by Tsinghua University Fuzhou Data Technology Joint Research Institute.
文摘In recent years,the rapid development of artificial intelligence has driven the widespread deployment of visual systems in complex environments such as autonomous driving,security surveillance,and medical diagnosis.However,existing image sensors—such as CMOS and CCD devices—intrinsically suffer from the limitation of fixed spectral response.Especially in environments with strong glare,haze,or dust,external spectral conditions often severely mismatch the device's design range,leading to significant degradation in image quality and a sharp drop in target recognition accuracy.While algorithmic post-processing(such as color bias correction or background suppression)can mitigate these issues,algorithm approaches typically introduce computational latency and increased energy consumption,making them unsuitable for edge computing or high-speed scenarios.
基金funded by National Natural Science Foundation of China(61741303)the Foundation Project of Guangxi Key Laboratory of Spatial Information andMapping(No.21-238-21-16).
文摘Detecting individuals wearing safety helmets in complex environments faces several challenges.These factors include limited detection accuracy and frequent missed or false detections.Additionally,existing algorithms often have excessive parameter counts,complex network structures,and high computational demands.These challenges make it difficult to deploy such models efficiently on resource-constrained devices like embedded systems.Aiming at this problem,this research proposes an optimized and lightweight solution called FGP-YOLOv8,an improved version of YOLOv8n.The YOLOv8 backbone network is replaced with the FasterNet model to reduce parameters and computational demands while local convolution layers are added.This modification minimizes computational costs with only a minor impact on accuracy.A new GSTA(GSConv-Triplet Attention)module is introduced to enhance feature fusion and reduce computational complexity.This is achieved using attention weights generated from dimensional interactions within the feature map.Additionally,the ParNet-C2f module replaces the original C2f(CSP Bottleneck with 2 Convolutions)module,improving feature extraction for safety helmets of various shapes and sizes.The CIoU(Complete-IoU)is replaced with the WIoU(Wise-IoU)to boost performance further,enhancing detection accuracy and generalization capabilities.Experimental results validate the improvements.The proposedmodel reduces the parameter count by 19.9% and the computational load by 18.5%.At the same time,mAP(mean average precision)increases by 2.3%,and precision improves by 1.2%.These results demonstrate the model’s robust performance in detecting safety helmets across diverse environments.
基金funded by the National Defense Science and Technology Innovation project,grant number ZZKY20223103the Basic Frontier InnovationProject at the Engineering University of PAP,grant number WJY202429+2 种基金the Basic Frontier lnnovation Project at the Engineering University of PAP,grant number WJY202408the Graduate Student Funding Priority Project,grant number JYWJ2024B006Key project of National Social Science Foundation,grant number 2023-SKJJ-A-116.
文摘This study introduces a novel algorithm known as the dung beetle optimization algorithm based on bounded reflection optimization andmulti-strategy fusion(BFDBO),which is designed to tackle the complexities associated with multi-UAV collaborative trajectory planning in intricate battlefield environments.Initially,a collaborative planning cost function for the multi-UAV system is formulated,thereby converting the trajectory planning challenge into an optimization problem.Building on the foundational dung beetle optimization(DBO)algorithm,BFDBO incorporates three significant innovations:a boundary reflection mechanism,an adaptive mixed exploration strategy,and a dynamic multi-scale mutation strategy.These enhancements are intended to optimize the equilibrium between local exploration and global exploitation,facilitating the discovery of globally optimal trajectories thatminimize the cost function.Numerical simulations utilizing the CEC2022 benchmark function indicate that all three enhancements of BFDBOpositively influence its performance,resulting in accelerated convergence and improved optimization accuracy relative to leading optimization algorithms.In two battlefield scenarios of varying complexities,BFDBO achieved a minimum of a 39% reduction in total trajectory planning costs when compared to DBO and three other highperformance variants,while also demonstrating superior average runtime.This evidence underscores the effectiveness and applicability of BFDBO in practical,real-world contexts.
文摘With China and Africa having worked hand in hand for mutual benefits for a long time,China-Africa economic and trade cooperation has developed steadily,achieving significant progress in many fields.However,at the same time,the environment in which China-Africa economic and trade cooperation operates is becoming increasingly complex.Risks and challenges from different levels are worth noticing.
文摘Mid-Year Marine Economy Report Developing the marine economy and building China into a maritime powerhouse are of great significance for China’s socio-economic sustainable development,as well as for advancing its modernization drive.Recently released data from the Ministry of Natural Resources shows that during the first half of 2025,despite a complex and volatile external environment,China’s marine economy withstood the pressure and maintained a steady and positive development trend.
基金Project supported by the National Natural Science Foundation of China(Nos.11872233,11727804,and 11472163)the National Key Basic Research Project of China(No.2014CB046203)the Innovation Program of Shanghai Municipal Education Commission(No.2017-01-07-00-09-E00019)。
文摘Studying and analyzing the dynamic behavior of offshore wind turbines are of great importance to ensure the safety and improve the efficiency of such expensive equipments.In this work,a tapered beam model is proposed to investigate the dynamic response of an offshore wind turbine tower on the monopile foundation assembled with rotating blades in the complex ocean environment.Several environment factors like wind,wave,current,and soil resistance are taken into account.The proposed model is ana-lytically solved with the Galerkin method.Based on the numerical results,the effects of various structure parameters including the taper angle,the height and thickness of the tower,the depth,and the diameter and the cement filler of the monopile on the funda-mental natural frequency of the wind turbine tower system are investigated in detail.It is found that the fundamental natural frequency decreases with the increase in the taper angle and the height and thickness of the tower,and increases with the increase in the diameter of the monopile.Moreover,filling cement into the monopile can effectively im-prove the fundamental natural frequency of the wind turbine tower system,but there is a critical value of the amount of cement maximizing the property of the monopile.This research may be helpful in the design and safety evaluation of offshore wind turbines.
基金the National Natural Science Foundation of China(10402033,10772144)
文摘In virtue of effect of N-S intensive ground stress and mining disturbance to +579E2EB_(1+2) mining site at Weihuliang Mine,the dip angle and section height is 65° and 52 m,respectively,the collapses happed frequently during mining.Firstly,mining condi- tions,spatial structure and parameters were investigated.Then physical simulation and dynamic numerical tracing and elaborate simulation relating roof and top-coal were ap- plied based on 2D-Block Program and quantitative regularity of stress at variable depths had been estimated.Furthermore,it was manifested that effective measures,i.e.,fast mining,control symmetrical top-coal-caving at dip and strike directions,optimizing ventila- tion system,active-stereo preventing gas were performed successfully in mining practice. Ultimately,the derived dynamic hazard were prevented so as to safety mining.
基金supported in part by the Guangxi Power Grid Company’s 2023 Science and Technol-ogy Innovation Project(No.GXKJXM20230169)。
文摘With the development of unmanned driving technology,intelligent robots and drones,high-precision localization,navigation and state estimation technologies have also made great progress.Traditional global navigation satellite system/inertial navigation system(GNSS/INS)integrated navigation systems can provide high-precision navigation information continuously.However,when this system is applied to indoor or GNSS-denied environments,such as outdoor substations with strong electromagnetic interference and complex dense spaces,it is often unable to obtain high-precision GNSS positioning data.The positioning and orientation errors will diverge and accumulate rapidly,which cannot meet the high-precision localization requirements in large-scale and long-distance navigation scenarios.This paper proposes a method of high-precision state estimation with fusion of GNSS/INS/Vision using a nonlinear optimizer factor graph optimization as the basis for multi-source optimization.Through the collected experimental data and simulation results,this system shows good performance in the indoor environment and the environment with partial GNSS signal loss.
基金supported by the Fundamental Research Funds for the Central Universities(No.2023JBZX011)the Aeronautical Science Foundation of China(No.202300010M5001).
文摘1 Introduction Constrained Reinforcement Learning(CRL),modeled as a Constrained Markov Decision Process(CMDP)[1,2],is commonly used to address applications with security restrictions.Previous works[3]primarily focused on the single-constraint issue,overlooking the more common multi-constraint setting which involves extensive computations and combinatorial optimization of multiple Lagrange multipliers.
文摘Shield tunneling is an important link in the current subway construction. It has a high level of automation, which greatly improves the construction efficiency. At the same time, subway shield construction can also reduce the impact of urban ground traffic, so it has been widely used in the construction of subway projects. In this paper, the technology and construction technology of shield tunneling under complex environment are studied and analyzed for reference.
基金supported in part by the National Natural Science Foundation of China(62222301, 62073085, 62073158, 61890930-5, 62021003)the National Key Research and Development Program of China (2021ZD0112302, 2021ZD0112301, 2018YFC1900800-5)Beijing Natural Science Foundation (JQ19013)。
文摘Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.
基金Funding from the Key Research and development plan of Shaanxi Province"Research on key problems of surface finishing for Aerospace Fastener"(2023-YBGY-386).
文摘A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very complicated,and the fault characteristic signal is weak and hard to extract.Firstly,the best wavelet base Cmor 3-3 is selected by comparing 6 different wavelet base types.Secondly,continuous wavelet transform(CWT)is applied to the acquired original vibration signal to generate the feature map and process the gray level.Finally,the improved ResNeXt network is used to diagnose faults in precision machining equipment.The experimental results show that the proposed CWT and the improved ResNeXt algorithm have high accuracy in identifying precision machining equipment faults in complex environments,with an average accuracy of 99.4%。
