Frequent flood disasters caused by climate change may lead to tremendous economic and human losses along inland waterways.Emergency response and rescue vessels(ERRVs)play an essential role in minimizing losses and pro...Frequent flood disasters caused by climate change may lead to tremendous economic and human losses along inland waterways.Emergency response and rescue vessels(ERRVs)play an essential role in minimizing losses and protecting lives and property.However,the path planning of ERRVs has mainly depended on expert experiences instead of rational decision making.This paper proposes an improved artificial potential field(APF)algorithm to optimize the shortest path for ERRVs in the rescue process.To verify the feasibility of the proposed model,eight tests were carried out in two water areas of the Yangtze River.The results showed that the improved APF algorithm was efficient with fewer iterations and that the response time of path planning was reduced to around eight seconds.The improved APF algorithm performed better in the ERRV’s goal achievement,compared with the traditional algorithm.The path planning method for ERRVs proposed in this paper has theoretical and practical value in flood relief.It can be applied in the emergency management of ERRVs to accelerate flood management efficiency and improve capacity to prevent,mitigate,and relieve flood disasters.展开更多
To address low learning efficiency and inadequate path safety in spraying robot navigation within complex obstacle-rich environments—with dense,dynamic,unpredictable obstacles challenging conventional methods—this p...To address low learning efficiency and inadequate path safety in spraying robot navigation within complex obstacle-rich environments—with dense,dynamic,unpredictable obstacles challenging conventional methods—this paper proposes a hybrid algorithm integrating Q-learning and improved A*-Artificial Potential Field(A-APF).Centered on theQ-learning framework,the algorithmleverages safety-oriented guidance generated byA-APF and employs a dynamic coordination mechanism that adaptively balances exploration and exploitation.The proposed system comprises four core modules:(1)an environment modeling module that constructs grid-based obstacle maps;(2)an A-APF module that combines heuristic search from A*algorithm with repulsive force strategies from APF to generate guidance;(3)a Q-learning module that learns optimal state-action values(Q-values)through spraying robot-environment interaction and a reward function emphasizing path optimality and safety;and(4)a dynamic optimization module that ensures adaptive cooperation between Q-learning and A-APF through exploration rate control and environment-aware constraints.Simulation results demonstrate that the proposed method significantly enhances path safety in complex underground mining environments.Quantitative results indicate that,compared to the traditional Q-learning algorithm,the proposed method shortens training time by 42.95% and achieves a reduction in training failures from 78 to just 3.Compared to the static fusion algorithm,it further reduces both training time(by 10.78%)and training failures(by 50%),thereby improving overall training efficiency.展开更多
Accurate modeling of ship magnetic fields is important for predicting their spatial distribution to improve the magnetic stealth effect of ships.This study proposes an extrapolation model for ship magnetic fields base...Accurate modeling of ship magnetic fields is important for predicting their spatial distribution to improve the magnetic stealth effect of ships.This study proposes an extrapolation model for ship magnetic fields based on genetic algorithms and convolutional neural networks(CNNs).The magnetic probe position matrix of the traditional equivalent source is utilized as input,and the three-directional components of the magnetic field measured by the probes are employed as output.The extrapolation model for ship magnetic fields is obtained through iterative training and fitting with CNNs.Variables such as the number of magnetic dipoles,the distance between magnetic dipoles,the size and quantity of convolutional kernels,batch size,learning rate,and L2 regularization coefficient are optimized to boost the accuracy of the extrapolation model for magnetic fields.The fitting accuracy of the extrapolation model for ship magnetic fields is used as the optimization objective.Based on a finite element simulation model of ship magnetic fields,the accuracy and robustness of the CNN algorithm under different magnetic field conditions are validated using the known standard depth plane,the unknown depth at 1.125 times the standard depth plane,and the unknown depth at 1.25 times the standard depth plane.Results show that,after optimization,the fitting error for the magnetic field extrapolation model based on CNN is 1.50%for the standard depth plane,1.63%for the unknown depth at 1.125 times the standard depth plane,and 2.36%for the unknown depth at 1.25 times the standard depth plane.The error remains below 5%under varying magnetic field conditions.When a random measurement error of 0%-5%is introduced for the magnetic probes,the prediction error at 1.25 times the standard depth plane is 2.30%;with a random error of 0%-10%,the prediction error is 4.95%.This approach significantly improves the accuracy and robustness of magnetic field extrapolation,which makes it an effective and feasible method for ship magnetic field modeling.展开更多
为解决无人船在复杂水面环境中路径规划困难且算法效率较低的问题,该文提出了一种融合人工势场(artificial potential field,APF)法与RRT*(rapidly-exploring random tree star)算法的路径规划方法——双向APF-RRT*算法。该方法...为解决无人船在复杂水面环境中路径规划困难且算法效率较低的问题,该文提出了一种融合人工势场(artificial potential field,APF)法与RRT*(rapidly-exploring random tree star)算法的路径规划方法——双向APF-RRT*算法。该方法首先引入目标偏置策略,使新生成节点更倾向于朝目标方向扩展;同时采用双向搜索机制,驱动两棵随机树相互靠近,以加快算法收敛速度。在节点扩展过程中,利用APF法中的引力引导节点朝目标点扩展,利用斥力实现有效避障。最后,在Matlab平台开展仿真实验,将该文算法同传统RRT*算法和APF-RRT*算法进行对比分析。实验结果表明:在多种典型场景下,双向APF-RRT*算法较上述算法在路径节点数量、路径长度及规划效率等方面均表现更优,展现出更高的规划性能与环境适应能力。展开更多
With the increase in ocean exploration activities and underwater development,the autonomous underwater vehicle(AUV)has been widely used as a type of underwater automation equipment in the detection of underwater envir...With the increase in ocean exploration activities and underwater development,the autonomous underwater vehicle(AUV)has been widely used as a type of underwater automation equipment in the detection of underwater environments.However,nowadays AUVs generally have drawbacks such as weak endurance,low intelligence,and poor detection ability.The research and implementation of path-planning methods are the premise of AUVs to achieve actual tasks.To improve the underwater operation ability of the AUV,this paper studies the typical problems of path-planning for the ant colony algorithm and the artificial potential field algorithm.In response to the limitations of a single algorithm,an optimization scheme is proposed to improve the artificial potential field ant colony(APF-AC)algorithm.Compared with traditional ant colony and comparative algorithms,the APF-AC reduced the path length by 1.57%and 0.63%(in the simple environment),8.92%and 3.46%(in the complex environment).The iteration time has been reduced by approximately 28.48%and 18.05%(in the simple environment),18.53%and 9.24%(in the complex environment).Finally,the improved APF-AC algorithm has been validated on the AUV platform,and the experiment is consistent with the simulation.Improved APF-AC algorithm can effectively reduce the underwater operation time and overall power consumption of the AUV,and shows a higher safety.展开更多
In this study. an automated conformer selection procedure using generic algorithm (GA) has been applied in comparative molecular field analysis (CoMFA) method. Using genetic algorithm. the 3D-QSAR model is optimized t...In this study. an automated conformer selection procedure using generic algorithm (GA) has been applied in comparative molecular field analysis (CoMFA) method. Using genetic algorithm. the 3D-QSAR model is optimized to an optimal one. From the calculation results, a group of QSAR models with high predictive ability can be obtained, which is superior than using conventional CoMFA: meanwhile. the active conformers for these compounds in data set can be determined fi om the best model.展开更多
基金The National Natural Science Foundation of China(Grant No.72274052)the National Natural Science Foundation of China(Grant No.72174173).
摘要Frequent flood disasters caused by climate change may lead to tremendous economic and human losses along inland waterways.Emergency response and rescue vessels(ERRVs)play an essential role in minimizing losses and protecting lives and property.However,the path planning of ERRVs has mainly depended on expert experiences instead of rational decision making.This paper proposes an improved artificial potential field(APF)algorithm to optimize the shortest path for ERRVs in the rescue process.To verify the feasibility of the proposed model,eight tests were carried out in two water areas of the Yangtze River.The results showed that the improved APF algorithm was efficient with fewer iterations and that the response time of path planning was reduced to around eight seconds.The improved APF algorithm performed better in the ERRV’s goal achievement,compared with the traditional algorithm.The path planning method for ERRVs proposed in this paper has theoretical and practical value in flood relief.It can be applied in the emergency management of ERRVs to accelerate flood management efficiency and improve capacity to prevent,mitigate,and relieve flood disasters.
基金supported by the National Natural Science Foundation of China(Grant No.52374156).
摘要To address low learning efficiency and inadequate path safety in spraying robot navigation within complex obstacle-rich environments—with dense,dynamic,unpredictable obstacles challenging conventional methods—this paper proposes a hybrid algorithm integrating Q-learning and improved A*-Artificial Potential Field(A-APF).Centered on theQ-learning framework,the algorithmleverages safety-oriented guidance generated byA-APF and employs a dynamic coordination mechanism that adaptively balances exploration and exploitation.The proposed system comprises four core modules:(1)an environment modeling module that constructs grid-based obstacle maps;(2)an A-APF module that combines heuristic search from A*algorithm with repulsive force strategies from APF to generate guidance;(3)a Q-learning module that learns optimal state-action values(Q-values)through spraying robot-environment interaction and a reward function emphasizing path optimality and safety;and(4)a dynamic optimization module that ensures adaptive cooperation between Q-learning and A-APF through exploration rate control and environment-aware constraints.Simulation results demonstrate that the proposed method significantly enhances path safety in complex underground mining environments.Quantitative results indicate that,compared to the traditional Q-learning algorithm,the proposed method shortens training time by 42.95% and achieves a reduction in training failures from 78 to just 3.Compared to the static fusion algorithm,it further reduces both training time(by 10.78%)and training failures(by 50%),thereby improving overall training efficiency.
摘要Accurate modeling of ship magnetic fields is important for predicting their spatial distribution to improve the magnetic stealth effect of ships.This study proposes an extrapolation model for ship magnetic fields based on genetic algorithms and convolutional neural networks(CNNs).The magnetic probe position matrix of the traditional equivalent source is utilized as input,and the three-directional components of the magnetic field measured by the probes are employed as output.The extrapolation model for ship magnetic fields is obtained through iterative training and fitting with CNNs.Variables such as the number of magnetic dipoles,the distance between magnetic dipoles,the size and quantity of convolutional kernels,batch size,learning rate,and L2 regularization coefficient are optimized to boost the accuracy of the extrapolation model for magnetic fields.The fitting accuracy of the extrapolation model for ship magnetic fields is used as the optimization objective.Based on a finite element simulation model of ship magnetic fields,the accuracy and robustness of the CNN algorithm under different magnetic field conditions are validated using the known standard depth plane,the unknown depth at 1.125 times the standard depth plane,and the unknown depth at 1.25 times the standard depth plane.Results show that,after optimization,the fitting error for the magnetic field extrapolation model based on CNN is 1.50%for the standard depth plane,1.63%for the unknown depth at 1.125 times the standard depth plane,and 2.36%for the unknown depth at 1.25 times the standard depth plane.The error remains below 5%under varying magnetic field conditions.When a random measurement error of 0%-5%is introduced for the magnetic probes,the prediction error at 1.25 times the standard depth plane is 2.30%;with a random error of 0%-10%,the prediction error is 4.95%.This approach significantly improves the accuracy and robustness of magnetic field extrapolation,which makes it an effective and feasible method for ship magnetic field modeling.
摘要为解决无人船在复杂水面环境中路径规划困难且算法效率较低的问题,该文提出了一种融合人工势场(artificial potential field,APF)法与RRT*(rapidly-exploring random tree star)算法的路径规划方法——双向APF-RRT*算法。该方法首先引入目标偏置策略,使新生成节点更倾向于朝目标方向扩展;同时采用双向搜索机制,驱动两棵随机树相互靠近,以加快算法收敛速度。在节点扩展过程中,利用APF法中的引力引导节点朝目标点扩展,利用斥力实现有效避障。最后,在Matlab平台开展仿真实验,将该文算法同传统RRT*算法和APF-RRT*算法进行对比分析。实验结果表明:在多种典型场景下,双向APF-RRT*算法较上述算法在路径节点数量、路径长度及规划效率等方面均表现更优,展现出更高的规划性能与环境适应能力。
基金supported by Research Program supported by the National Natural Science Foundation of China(No.62201249)the Jiangsu Agricultural Science and Technology Innovation Fund(No.CX(21)1007)+2 种基金the Open Project of the Zhejiang Provincial Key Laboratory of Crop Harvesting Equipment and Technology(Nos.2021KY03,2021KY04)University-Industry Collaborative Education Program(No.201801166003)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.SJCX22_1042).
摘要With the increase in ocean exploration activities and underwater development,the autonomous underwater vehicle(AUV)has been widely used as a type of underwater automation equipment in the detection of underwater environments.However,nowadays AUVs generally have drawbacks such as weak endurance,low intelligence,and poor detection ability.The research and implementation of path-planning methods are the premise of AUVs to achieve actual tasks.To improve the underwater operation ability of the AUV,this paper studies the typical problems of path-planning for the ant colony algorithm and the artificial potential field algorithm.In response to the limitations of a single algorithm,an optimization scheme is proposed to improve the artificial potential field ant colony(APF-AC)algorithm.Compared with traditional ant colony and comparative algorithms,the APF-AC reduced the path length by 1.57%and 0.63%(in the simple environment),8.92%and 3.46%(in the complex environment).The iteration time has been reduced by approximately 28.48%and 18.05%(in the simple environment),18.53%and 9.24%(in the complex environment).Finally,the improved APF-AC algorithm has been validated on the AUV platform,and the experiment is consistent with the simulation.Improved APF-AC algorithm can effectively reduce the underwater operation time and overall power consumption of the AUV,and shows a higher safety.
摘要In this study. an automated conformer selection procedure using generic algorithm (GA) has been applied in comparative molecular field analysis (CoMFA) method. Using genetic algorithm. the 3D-QSAR model is optimized to an optimal one. From the calculation results, a group of QSAR models with high predictive ability can be obtained, which is superior than using conventional CoMFA: meanwhile. the active conformers for these compounds in data set can be determined fi om the best model.