针对网联商用车换道安全性、平顺性较低的问题,提出一种基于多策略改进金豺优化算法(multi-strategy improved golden jackal optimization,MSIGJO)的网联商用车换道轨迹规划方法。首先,基于V2X(vehicle to everything)技术获取智能网...针对网联商用车换道安全性、平顺性较低的问题,提出一种基于多策略改进金豺优化算法(multi-strategy improved golden jackal optimization,MSIGJO)的网联商用车换道轨迹规划方法。首先,基于V2X(vehicle to everything)技术获取智能网联商用车周围状态信息,建立商用车换道安全距离模型;其次,引入商用车换道平顺性、经济性和换道效率作为指标,构建多目标协同优化函数;最后,引入动态权重位置更新策略和翻转策略改进金豺优化算法(golden jackal optimization,GJO),进而提出MSIGJO算法,利用MSIGJO算法求解函数得到最优换道轨迹。研究结果表明:该方法在商用车换道过程中横向跟踪精度提升了12.67%,侧向加速度变化率和质心侧偏角变化率分别降低了11.94%和12.65%,有效提升智能网联商用车换道安全性和平顺性,为智能网联商用车换道轨迹规划研究提供参考。展开更多
This paper proposes a modified golden jackal optimization(IGJO)algorithm to solve the OCL(which stands for optimal cooling load)problem to minimize energy consumption.In this algorithm,many tools have been developed,s...This paper proposes a modified golden jackal optimization(IGJO)algorithm to solve the OCL(which stands for optimal cooling load)problem to minimize energy consumption.In this algorithm,many tools have been developed,such as numerical visualization,local field method,competitive selectionmethod,and iterative strategy.The IGJO algorithm is used to improve the research capabilities of the algorithm in terms of global tuning and rotation speed.In order to fully utilize the effectiveness of the proposed algorithm,three famous examples of OCL problems in basic ventilation systems were studied and compared with some previously published works.The results show that the IGJO algorithm can find solutions equal to or better than other methods.Underpinning these studies is the need to reduce energy consumption in air conditioning systems,which is a critical business and environmental decision.The Optimal Chiller Load(OCL)problem is well-known in the industry.It is the best method of operation for the refrigeration plant to satisfy the requirement of cooling.In order to solve the OCL problem,an improved Golden Jackal optimization algorithm(IGJO)was proposed.The IGJO algorithm consists of a number of parts to improve the global optimization and rotation speed.These studies are intended to address more effectively the issue of OCL,which results in energy savings in air-conditioning systems.The performance of the proposed IGJO algorithm is evaluated,and the results are compared with the results of three known OCL problems in the ventilation system.The results indicate that the IGJO method has the same or better optimization ability as other methods and can improve the energy efficiency of the system’s cold air.展开更多
针对金豺优化算法(golden jackal optimization,GJO)在求解复杂优化问题时存在收敛速度慢和易陷入局部最优等不足,提出一种混合策略改进的金豺优化算法(improved golden jackal optimization,IGJO)。在算法的最优解停滞更新时,引入柯西...针对金豺优化算法(golden jackal optimization,GJO)在求解复杂优化问题时存在收敛速度慢和易陷入局部最优等不足,提出一种混合策略改进的金豺优化算法(improved golden jackal optimization,IGJO)。在算法的最优解停滞更新时,引入柯西变异策略,增强种群多样性和提升算法陷入局部最优的逃逸能力;提出一种基于权重的决策策略,通过对金豺个体赋予不同权重进行种群位置更新的决策,加快算法的收敛速度。对8个基准测试函数以及部分CEC2017测试函数进行寻优实验,结果表明改进算法具有更好的优化性能和收敛速度;进一步地,将改进算法应用于支持向量回归(support vector regression,SVR)模型的参数优化,并在选取的5个UCI(University of California,Irvine)数据集上进行实验,验证了改进算法的有效性。展开更多
Nowadays,optimization techniques are required in various engineering domains to find optimal solutions for complex problems.As a result,there is a growing tendency among scientists to enhance existing nature-inspired ...Nowadays,optimization techniques are required in various engineering domains to find optimal solutions for complex problems.As a result,there is a growing tendency among scientists to enhance existing nature-inspired algorithms using various evolutionary strategies and to develop new nature-inspired optimization methods that can properly explore the feature space.The recently designed nature-inspired meta-heuristic,named the Golden Jackal Optimization(GJO),was inspired by the collaborative hunting actions of the golden jackal in nature to solve various challenging problems.However,like other approaches,the GJO has the limitations of poor exploitation ability,the ease of getting stuck in a local optimal region,and an improper balancing of exploration and exploitation.To overcome these limitations,this paper proposes an improved GJO algorithm based on multi-strategy mixing(LGJO).First,using a chaotic mapping strategy to initialize the population instead of using random parameters,this algorithm can generate initial solutions with good diversity in the search space.Second,a dynamic inertia weight based on cosine variation is proposed to make the search process more realistic and effectively balance the algorithm's global and local search capabilities.Finally,a position update strategy based on Gaussian mutation was introduced,fully utilizing the guidance role of the optimal individual to improve population diversity,effectively exploring unknown regions,and avoiding the algorithm falling into local optima.To evaluate the proposed algorithm,23 mathematical benchmark functions,CEC-2019 and CEC2021 tests are employed.The results are compared to high-quality,well-known optimization methods.The results of the proposed method are compared from different points of view,including the quality of the results,convergence behavior,and robustness.The superiority and high-quality performance of the proposed method are demonstrated by comparing the results.Furthermore,to demonstrate its applicability,it is employed to solve four constrained industrial applications.The outcomes of the experiment reveal that the proposed algorithm can solve challenging,constrained problems and is very competitive compared with other optimization algorithms.This article provides a new approach to solving real-world optimization problems.展开更多
文摘针对网联商用车换道安全性、平顺性较低的问题,提出一种基于多策略改进金豺优化算法(multi-strategy improved golden jackal optimization,MSIGJO)的网联商用车换道轨迹规划方法。首先,基于V2X(vehicle to everything)技术获取智能网联商用车周围状态信息,建立商用车换道安全距离模型;其次,引入商用车换道平顺性、经济性和换道效率作为指标,构建多目标协同优化函数;最后,引入动态权重位置更新策略和翻转策略改进金豺优化算法(golden jackal optimization,GJO),进而提出MSIGJO算法,利用MSIGJO算法求解函数得到最优换道轨迹。研究结果表明:该方法在商用车换道过程中横向跟踪精度提升了12.67%,侧向加速度变化率和质心侧偏角变化率分别降低了11.94%和12.65%,有效提升智能网联商用车换道安全性和平顺性,为智能网联商用车换道轨迹规划研究提供参考。
文摘This paper proposes a modified golden jackal optimization(IGJO)algorithm to solve the OCL(which stands for optimal cooling load)problem to minimize energy consumption.In this algorithm,many tools have been developed,such as numerical visualization,local field method,competitive selectionmethod,and iterative strategy.The IGJO algorithm is used to improve the research capabilities of the algorithm in terms of global tuning and rotation speed.In order to fully utilize the effectiveness of the proposed algorithm,three famous examples of OCL problems in basic ventilation systems were studied and compared with some previously published works.The results show that the IGJO algorithm can find solutions equal to or better than other methods.Underpinning these studies is the need to reduce energy consumption in air conditioning systems,which is a critical business and environmental decision.The Optimal Chiller Load(OCL)problem is well-known in the industry.It is the best method of operation for the refrigeration plant to satisfy the requirement of cooling.In order to solve the OCL problem,an improved Golden Jackal optimization algorithm(IGJO)was proposed.The IGJO algorithm consists of a number of parts to improve the global optimization and rotation speed.These studies are intended to address more effectively the issue of OCL,which results in energy savings in air-conditioning systems.The performance of the proposed IGJO algorithm is evaluated,and the results are compared with the results of three known OCL problems in the ventilation system.The results indicate that the IGJO method has the same or better optimization ability as other methods and can improve the energy efficiency of the system’s cold air.
文摘针对金豺优化算法(golden jackal optimization,GJO)在求解复杂优化问题时存在收敛速度慢和易陷入局部最优等不足,提出一种混合策略改进的金豺优化算法(improved golden jackal optimization,IGJO)。在算法的最优解停滞更新时,引入柯西变异策略,增强种群多样性和提升算法陷入局部最优的逃逸能力;提出一种基于权重的决策策略,通过对金豺个体赋予不同权重进行种群位置更新的决策,加快算法的收敛速度。对8个基准测试函数以及部分CEC2017测试函数进行寻优实验,结果表明改进算法具有更好的优化性能和收敛速度;进一步地,将改进算法应用于支持向量回归(support vector regression,SVR)模型的参数优化,并在选取的5个UCI(University of California,Irvine)数据集上进行实验,验证了改进算法的有效性。
基金support of the special project for collaborative innovation of science and technology in 2021(No:202121206)Henan Province University Scientific and Technological Innovation Team(No:18IRTSTHN009).
文摘Nowadays,optimization techniques are required in various engineering domains to find optimal solutions for complex problems.As a result,there is a growing tendency among scientists to enhance existing nature-inspired algorithms using various evolutionary strategies and to develop new nature-inspired optimization methods that can properly explore the feature space.The recently designed nature-inspired meta-heuristic,named the Golden Jackal Optimization(GJO),was inspired by the collaborative hunting actions of the golden jackal in nature to solve various challenging problems.However,like other approaches,the GJO has the limitations of poor exploitation ability,the ease of getting stuck in a local optimal region,and an improper balancing of exploration and exploitation.To overcome these limitations,this paper proposes an improved GJO algorithm based on multi-strategy mixing(LGJO).First,using a chaotic mapping strategy to initialize the population instead of using random parameters,this algorithm can generate initial solutions with good diversity in the search space.Second,a dynamic inertia weight based on cosine variation is proposed to make the search process more realistic and effectively balance the algorithm's global and local search capabilities.Finally,a position update strategy based on Gaussian mutation was introduced,fully utilizing the guidance role of the optimal individual to improve population diversity,effectively exploring unknown regions,and avoiding the algorithm falling into local optima.To evaluate the proposed algorithm,23 mathematical benchmark functions,CEC-2019 and CEC2021 tests are employed.The results are compared to high-quality,well-known optimization methods.The results of the proposed method are compared from different points of view,including the quality of the results,convergence behavior,and robustness.The superiority and high-quality performance of the proposed method are demonstrated by comparing the results.Furthermore,to demonstrate its applicability,it is employed to solve four constrained industrial applications.The outcomes of the experiment reveal that the proposed algorithm can solve challenging,constrained problems and is very competitive compared with other optimization algorithms.This article provides a new approach to solving real-world optimization problems.
