模型辅助检测概率(model-assisted probability of detection,MAPoD)和灵敏度分析对于量化涡流无损检测(eddy current nondestructive testing,ECNDT)系统的检测能力非常重要。由于不确定性在涡流无损检测的MAPoD和SA问题中的传播,传统...模型辅助检测概率(model-assisted probability of detection,MAPoD)和灵敏度分析对于量化涡流无损检测(eddy current nondestructive testing,ECNDT)系统的检测能力非常重要。由于不确定性在涡流无损检测的MAPoD和SA问题中的传播,传统基于实验方法和物理仿真模型对该问题的分析需要耗费大量的时间和人力成本,为了降低这些成本,提出基于粒子群算法(particle swarm optimization,PSO)的支持向量回归(support vector regression,SVR)模型取代传统的实验方法以及物理仿真模型,对涡流无损检测模型的响应进行预测,从而加速MAPoD和SA问题的分析。此外,创新性地将网格搜索、随机搜索、模拟退火算法和PSO等优化算法与SVR相结合,研究不同的优化算法对SVR的关键参数优化的精度和效率,验证PSO相较于其他优化算法的性能优势。最后,将PSO-SVR模型应用于ECNDT算例中,对表面裂缝长度的不确定性进行MAPoD和SA的分析。结果表明,所提算法在保证求解精度的同时,加速了涡流无损检测系统的MAPoD和SA问题的研究,并减少了计算开销。在计算量方面,对这两个问题的求解,平均分别仅需纯物理模型计算量的3.5%和0.06%。展开更多
To solve the problem of multi-platform collaborative use in anti-ship missile (ASM) path planning, this paper pro-posed multi-operator real-time constraints particle swarm opti-mization (MRC-PSO) algorithm. MRC-PSO al...To solve the problem of multi-platform collaborative use in anti-ship missile (ASM) path planning, this paper pro-posed multi-operator real-time constraints particle swarm opti-mization (MRC-PSO) algorithm. MRC-PSO algorithm utilizes a semi-rasterization environment modeling technique and inte-grates the geometric gradient law of ASMs which distinguishes itself from other collaborative path planning algorithms by fully considering the coupling between collaborative paths. Then, MRC-PSO algorithm conducts chunked stepwise recursive evo-lution of particles while incorporating circumvent, coordination, and smoothing operators which facilitates local selection opti-mization of paths, gradually reducing algorithmic space, accele-rating convergence, and enhances path cooperativity. Simula-tion experiments comparing the MRC-PSO algorithm with the PSO algorithm, genetic algorithm and operational area cluster real-time restriction (OACRR)-PSO algorithm, which demon-strate that the MRC-PSO algorithm has a faster convergence speed, and the average number of iterations is reduced by approximately 75%. It also proves that it is equally effective in resolving complex scenarios involving multiple obstacles. More-over it effectively addresses the problem of path crossing and can better satisfy the requirements of multi-platform collabora-tive path planning. The experiments are conducted in three col-laborative operation modes, namely, three-to-two, three-to-three, and four-to-two, and the outcomes demonstrate that the algorithm possesses strong universality.展开更多
The influence of ocean environment on navigation of autonomous underwater vehicle(AUV)cannot be ignored.In the marine environment,ocean currents,internal waves,and obstacles are usually considered in AUV path planning...The influence of ocean environment on navigation of autonomous underwater vehicle(AUV)cannot be ignored.In the marine environment,ocean currents,internal waves,and obstacles are usually considered in AUV path planning.In this paper,an improved particle swarm optimization(PSO)is proposed to solve three problems,traditional PSO algorithm is prone to fall into local optimization,path smoothing is always carried out after all the path planning steps,and the path fitness function is so simple that it cannot adapt to complex marine environment.The adaptive inertia weight and the“active”particle of the fish swarm algorithm are established to improve the global search and local search ability of the algorithm.The cubic spline interpolation method is combined with PSO to smooth the path in real time.The fitness function of the algorithm is optimized.Five evaluation indexes are comprehensively considered to solve the three-demensional(3D)path planning problem of AUV in the ocean currents and internal wave environment.The proposed method improves the safety of the path planning and saves energy.展开更多
文摘模型辅助检测概率(model-assisted probability of detection,MAPoD)和灵敏度分析对于量化涡流无损检测(eddy current nondestructive testing,ECNDT)系统的检测能力非常重要。由于不确定性在涡流无损检测的MAPoD和SA问题中的传播,传统基于实验方法和物理仿真模型对该问题的分析需要耗费大量的时间和人力成本,为了降低这些成本,提出基于粒子群算法(particle swarm optimization,PSO)的支持向量回归(support vector regression,SVR)模型取代传统的实验方法以及物理仿真模型,对涡流无损检测模型的响应进行预测,从而加速MAPoD和SA问题的分析。此外,创新性地将网格搜索、随机搜索、模拟退火算法和PSO等优化算法与SVR相结合,研究不同的优化算法对SVR的关键参数优化的精度和效率,验证PSO相较于其他优化算法的性能优势。最后,将PSO-SVR模型应用于ECNDT算例中,对表面裂缝长度的不确定性进行MAPoD和SA的分析。结果表明,所提算法在保证求解精度的同时,加速了涡流无损检测系统的MAPoD和SA问题的研究,并减少了计算开销。在计算量方面,对这两个问题的求解,平均分别仅需纯物理模型计算量的3.5%和0.06%。
基金supported by Hunan Provincial Natural Science Foundation(2024JJ5173,2023JJ50047)Hunan Provincial Department of Education Scientific Research Project(23A0494)Hunan Provincial Innovation Foundation for Postgraduate(CX20231221).
文摘To solve the problem of multi-platform collaborative use in anti-ship missile (ASM) path planning, this paper pro-posed multi-operator real-time constraints particle swarm opti-mization (MRC-PSO) algorithm. MRC-PSO algorithm utilizes a semi-rasterization environment modeling technique and inte-grates the geometric gradient law of ASMs which distinguishes itself from other collaborative path planning algorithms by fully considering the coupling between collaborative paths. Then, MRC-PSO algorithm conducts chunked stepwise recursive evo-lution of particles while incorporating circumvent, coordination, and smoothing operators which facilitates local selection opti-mization of paths, gradually reducing algorithmic space, accele-rating convergence, and enhances path cooperativity. Simula-tion experiments comparing the MRC-PSO algorithm with the PSO algorithm, genetic algorithm and operational area cluster real-time restriction (OACRR)-PSO algorithm, which demon-strate that the MRC-PSO algorithm has a faster convergence speed, and the average number of iterations is reduced by approximately 75%. It also proves that it is equally effective in resolving complex scenarios involving multiple obstacles. More-over it effectively addresses the problem of path crossing and can better satisfy the requirements of multi-platform collabora-tive path planning. The experiments are conducted in three col-laborative operation modes, namely, three-to-two, three-to-three, and four-to-two, and the outcomes demonstrate that the algorithm possesses strong universality.
基金supported by the High-tech Ship Projects of the Ministry of Industry and Information Technology of China(2021-342).
文摘The influence of ocean environment on navigation of autonomous underwater vehicle(AUV)cannot be ignored.In the marine environment,ocean currents,internal waves,and obstacles are usually considered in AUV path planning.In this paper,an improved particle swarm optimization(PSO)is proposed to solve three problems,traditional PSO algorithm is prone to fall into local optimization,path smoothing is always carried out after all the path planning steps,and the path fitness function is so simple that it cannot adapt to complex marine environment.The adaptive inertia weight and the“active”particle of the fish swarm algorithm are established to improve the global search and local search ability of the algorithm.The cubic spline interpolation method is combined with PSO to smooth the path in real time.The fitness function of the algorithm is optimized.Five evaluation indexes are comprehensively considered to solve the three-demensional(3D)path planning problem of AUV in the ocean currents and internal wave environment.The proposed method improves the safety of the path planning and saves energy.
