社会群体优化(social group optimization,SGO)算法是一种基于社会群体学习而提出的一种新型优化算法。针对社会群体优化算法易于陷入局部最优问题,提出了一种多子群社会群体学习算法(MPSGO)。本算法采用多子群学习方法,对算法两个阶段...社会群体优化(social group optimization,SGO)算法是一种基于社会群体学习而提出的一种新型优化算法。针对社会群体优化算法易于陷入局部最优问题,提出了一种多子群社会群体学习算法(MPSGO)。本算法采用多子群学习方法,对算法两个阶段的个体学习方法进行改进,在维持群体收敛性能的前提下提高群体多样性,同时对部分个体中引入量子学习,使个体学习的有用信息得以增强;此外,每隔一定代数对子群进行随机重组,既能保证各子群个体充分进化,又维持了子群多样性。在设计算法的基础上,分析了其收敛性和多样性;通过与其他四种算法进行对比实验,验证了改进后算法性能更优。展开更多
针对已有多任务优化算法寻优精度受限、计算时间成本过高等问题,提出一种基于改进灰狼算法的多任务优化算法(improved grey wolf algorithm based multitask optimization algorithm,IGWMTO)。该算法采用灰狼算法代替典型多任务算法中...针对已有多任务优化算法寻优精度受限、计算时间成本过高等问题,提出一种基于改进灰狼算法的多任务优化算法(improved grey wolf algorithm based multitask optimization algorithm,IGWMTO)。该算法采用灰狼算法代替典型多任务算法中的遗传算法,计算个体的因素等级和技能因子实现狼群分类,并以此更新个体隶属任务,引入扰动因子和动态权重改善狼群个体的更新方式。仿真测试结果表明:相比于传统多任务优化算法,所提算法在4个优化问题上的寻优精度的提升均超过了4.8%,计算耗时降低了70%以上。展开更多
To improve the operational efficiency of global optimization in engineering, Kriging model was established to simplify the mathematical model for calculations. Ducted coaxial-rotors aircraft was taken as an example an...To improve the operational efficiency of global optimization in engineering, Kriging model was established to simplify the mathematical model for calculations. Ducted coaxial-rotors aircraft was taken as an example and Fluent software was applied to the virtual prototype simulations. Through simulation sample points, the total lift of the ducted coaxial-rotors aircraft was obtained. The Kriging model was then constructed, and the function was fitted. Improved particle swarm optimization(PSO) was also utilized for the global optimization of the Kriging model of the ducted coaxial-rotors aircraft for the determination of optimized global coordinates. Finally, the optimized results were simulated by Fluent. The results show that the Kriging model and the improved PSO algorithm significantly improve the lift performance of ducted coaxial-rotors aircraft and computer operational efficiency.展开更多
In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel...In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel cells(PEMFC).Firstly,the Shapley additive explanations(SHAP)value method is used to select external characteristic parameters with high contributions as inputs for the data-driven approach.Next,a novel swarm optimization algorithm,the enhanced search ant colony optimization,is proposed.This algorithm improves the ant colony optimization(ACO)algorithm based on a reinforcement factor to avoid premature convergence and accelerate the convergence speed.Comparative experiments are set up to compare the performance differences between particle swarm optimization(PSO),ACO,and ENSACO.Finally,a data-driven method based on ENSACO-LSTM is proposed to predict the power degradation trend of PEMFCs.And actual aging data is used to validate the method.The results show that,within a limited number of iterations,the optimization capability of ENSACO is significantly stronger than that of PSO and ACO.Additionally,the prediction accuracy of the ENSACO-LSTM method is greatly improved,with an average increase of approximately 50.58%compared to LSTM,PSO-LSTM,and ACO-LSTM.展开更多
文摘社会群体优化(social group optimization,SGO)算法是一种基于社会群体学习而提出的一种新型优化算法。针对社会群体优化算法易于陷入局部最优问题,提出了一种多子群社会群体学习算法(MPSGO)。本算法采用多子群学习方法,对算法两个阶段的个体学习方法进行改进,在维持群体收敛性能的前提下提高群体多样性,同时对部分个体中引入量子学习,使个体学习的有用信息得以增强;此外,每隔一定代数对子群进行随机重组,既能保证各子群个体充分进化,又维持了子群多样性。在设计算法的基础上,分析了其收敛性和多样性;通过与其他四种算法进行对比实验,验证了改进后算法性能更优。
文摘针对已有多任务优化算法寻优精度受限、计算时间成本过高等问题,提出一种基于改进灰狼算法的多任务优化算法(improved grey wolf algorithm based multitask optimization algorithm,IGWMTO)。该算法采用灰狼算法代替典型多任务算法中的遗传算法,计算个体的因素等级和技能因子实现狼群分类,并以此更新个体隶属任务,引入扰动因子和动态权重改善狼群个体的更新方式。仿真测试结果表明:相比于传统多任务优化算法,所提算法在4个优化问题上的寻优精度的提升均超过了4.8%,计算耗时降低了70%以上。
基金Project(2013AA063903)supported by High-tech Research and Development Program of China
文摘To improve the operational efficiency of global optimization in engineering, Kriging model was established to simplify the mathematical model for calculations. Ducted coaxial-rotors aircraft was taken as an example and Fluent software was applied to the virtual prototype simulations. Through simulation sample points, the total lift of the ducted coaxial-rotors aircraft was obtained. The Kriging model was then constructed, and the function was fitted. Improved particle swarm optimization(PSO) was also utilized for the global optimization of the Kriging model of the ducted coaxial-rotors aircraft for the determination of optimized global coordinates. Finally, the optimized results were simulated by Fluent. The results show that the Kriging model and the improved PSO algorithm significantly improve the lift performance of ducted coaxial-rotors aircraft and computer operational efficiency.
基金Supported by the Major Science and Technology Project of Jilin Province(20220301010GX)the International Scientific and Technological Cooperation(20240402071GH).
文摘In this paper,a fusion model based on a long short-term memory(LSTM)neural network and enhanced search ant colony optimization(ENSACO)is proposed to predict the power degradation trend of proton exchange membrane fuel cells(PEMFC).Firstly,the Shapley additive explanations(SHAP)value method is used to select external characteristic parameters with high contributions as inputs for the data-driven approach.Next,a novel swarm optimization algorithm,the enhanced search ant colony optimization,is proposed.This algorithm improves the ant colony optimization(ACO)algorithm based on a reinforcement factor to avoid premature convergence and accelerate the convergence speed.Comparative experiments are set up to compare the performance differences between particle swarm optimization(PSO),ACO,and ENSACO.Finally,a data-driven method based on ENSACO-LSTM is proposed to predict the power degradation trend of PEMFCs.And actual aging data is used to validate the method.The results show that,within a limited number of iterations,the optimization capability of ENSACO is significantly stronger than that of PSO and ACO.Additionally,the prediction accuracy of the ENSACO-LSTM method is greatly improved,with an average increase of approximately 50.58%compared to LSTM,PSO-LSTM,and ACO-LSTM.
