Optimization problems are crucial for a wide range of engineering applications,as efficient solutions lead to better performance.This study introduces an improved coati optimization algorithm(ICOA)that overcomes the p...Optimization problems are crucial for a wide range of engineering applications,as efficient solutions lead to better performance.This study introduces an improved coati optimization algorithm(ICOA)that overcomes the primary limitations of the original coati optimization algorithm(COA),notably its insufficient population diversity and propensity to become trapped in local optima.To address these issues,the ICOA integrates three innovative strategies:Latin hypercube sampling(LHS),Lévyflight,and an adaptive local search.LHS is employed to ensure a diverse initial population,thereby laying a foundation for the optimization.Lévy-flight is utilized to facilitate an efficient global search,enhancing the algorithm’s ability to explore the solution space.The adaptive local search is designed to refine solutions,enabling more precise local exploration.Together,these strategies significantly improve the population’s quality and diversity,thereby improving the algorithm’s convergence accuracy and optimization capabilities.The performance of the ICOA is tested against several established algorithms,using 12 benchmark functions.Additionally,the ICOA’s practicality and effectiveness are demonstrated through application to a real-world engineering problem,specifically the design optimization of tension/compression springs.Simulation results show that the ICOA consistently outperforms the other algorithms,providing robust solutions for a wide range of optimization problems.展开更多
针对5G通信基站负载预测精度不足与能耗过高的问题,研究提出将深度学习与改进灰狼优化(Grey Wolf Optimizer,GWO)算法相结合的方法。通过构建基于生成对抗网络(Generative Adversarial Network,GAN)的负载预测模型,利用改进GWO算法优化...针对5G通信基站负载预测精度不足与能耗过高的问题,研究提出将深度学习与改进灰狼优化(Grey Wolf Optimizer,GWO)算法相结合的方法。通过构建基于生成对抗网络(Generative Adversarial Network,GAN)的负载预测模型,利用改进GWO算法优化网络参数,并设计智能节能控制策略。实验结果表明,该模型短期误差均值为0.015,长期误差均值为0.052,均低于对比模型。在节能控制方面,实验组低负载平均功率为35.2 W,较对照组显著降低,且通信质量无明显下降。研究表明,该方法有效提升了负载预测准确性,降低了基站能耗,为5G基站高效运营提供了可行方案。展开更多
针对复杂环境下四旋翼无人机三维航迹规划问题,提出了一种改进的事件触发灰狼优化算法(event triggered grey wolf optimization,ETGWO)。引入球面矢量刻画飞行路径的生成,通过减少搜索空间提升搜索能力;设计自适应权重动态调整飞行航...针对复杂环境下四旋翼无人机三维航迹规划问题,提出了一种改进的事件触发灰狼优化算法(event triggered grey wolf optimization,ETGWO)。引入球面矢量刻画飞行路径的生成,通过减少搜索空间提升搜索能力;设计自适应权重动态调整飞行航迹成本适应度函数,以提高航迹规划效率和准确性;在灰狼优化算法(grey wolf optimization,GWO)基础上,选择使用改进的非线性收敛因子,提升算法的鲁棒性;为了更好地平衡算法的全局搜索和局部搜索能力,通过引入基于事件触发机制的灰狼个体位置更新速度来改进GWO算法的位置更新策略。仿真对比实验表明,所提出ETGWO算法在四旋翼无人机(quadrotor unmanned aerial vehicles,QUAV)飞行航迹规划方面具有更优越的性能。展开更多
针对工业机器人在高度制造领域精度不高的问题,本文提出了一种基于POE模型的工业机器人运动学参数二次辨识方法。阐述了基于指数积(Product of exponential, POE)模型的运动学误差模型构建方法,并建立基于POE误差模型的适应度函数;为实...针对工业机器人在高度制造领域精度不高的问题,本文提出了一种基于POE模型的工业机器人运动学参数二次辨识方法。阐述了基于指数积(Product of exponential, POE)模型的运动学误差模型构建方法,并建立基于POE误差模型的适应度函数;为实现高精度的参数辨识,提出了一种二次辨识方法,先利用改进灰狼优化算法(Improved grey wolf optimizer, IGWO)实现运动学参数误差的粗辨识,初步将Staubli TX60型机器人的平均位置误差和平均姿态误差分别从(0.648 mm, 0.212°)降低为(0.457 mm, 0.166°);为进一步提高机器人的精度性能,再通过LM(Levenberg-Marquard)算法进行参数误差的精辨识,最终将Staubli TX60型机器人平均位置误差和平均姿态误差进一步降低为(0.237 mm, 0.063°),机器人平均位置误差和平均姿态误差分别降低63.4%和70.2%。为了验证上述二次辨识方法的稳定性,随机选取5组辨识数据集和验证数据集进行POE误差模型的参数误差辨识,结果表明提出的二次辨识方法能够稳定、精确地辨识工业机器人运动学参数误差。展开更多
高压脉冲放电破碎岩石的过程是复杂的非线性过程,存在放电时间短且破岩效果难以预测的问题。因此,建立高压脉冲破岩放电回路等效模型来描述破岩放电过程,提出基于改进的混沌灰狼优化(Gray wolf optimization,GWO)算法进行等效模型参数...高压脉冲放电破碎岩石的过程是复杂的非线性过程,存在放电时间短且破岩效果难以预测的问题。因此,建立高压脉冲破岩放电回路等效模型来描述破岩放电过程,提出基于改进的混沌灰狼优化(Gray wolf optimization,GWO)算法进行等效模型参数辨识。首先采用改进的奇异值分解算法对破碎不同岩石过程的电流进行滤波。然后通过6种标准测试函数,证明了与非线性最小二乘(Nonlinear least square,NLS)法、遗传算法(Genetic algorithm,GA)、粒子群优化(Particle swarm optimization,PSO)算法和GWO算法相比,改进的混沌GWO算法具有更好的寻优性能。最后将改进的混沌GWO算法的参数辨识结果与其他四种算法进行对比,结果验证了放电回路等效模型的准确性,也证明了该算法在辨识高压脉冲破岩放电回路等效模型时具有更快的收敛速度和更高的精度。同时,可求解出冲击波,从而能够分析高压脉冲破岩的动态过程。展开更多
基金supported by the Natural Science Foundation of Hunan Province of China(Nos.2021JJ10045 and 2025JJ60072)the Open Research Subject of State Key Laboratory of Intelligent Game(No.ZBKF-24-01)+1 种基金the Postdoctoral Fellowship Program of CPSF(No.GZB20240989)the China Postdoctoral Science Foundation(No.2024M754304).
文摘Optimization problems are crucial for a wide range of engineering applications,as efficient solutions lead to better performance.This study introduces an improved coati optimization algorithm(ICOA)that overcomes the primary limitations of the original coati optimization algorithm(COA),notably its insufficient population diversity and propensity to become trapped in local optima.To address these issues,the ICOA integrates three innovative strategies:Latin hypercube sampling(LHS),Lévyflight,and an adaptive local search.LHS is employed to ensure a diverse initial population,thereby laying a foundation for the optimization.Lévy-flight is utilized to facilitate an efficient global search,enhancing the algorithm’s ability to explore the solution space.The adaptive local search is designed to refine solutions,enabling more precise local exploration.Together,these strategies significantly improve the population’s quality and diversity,thereby improving the algorithm’s convergence accuracy and optimization capabilities.The performance of the ICOA is tested against several established algorithms,using 12 benchmark functions.Additionally,the ICOA’s practicality and effectiveness are demonstrated through application to a real-world engineering problem,specifically the design optimization of tension/compression springs.Simulation results show that the ICOA consistently outperforms the other algorithms,providing robust solutions for a wide range of optimization problems.
文摘针对复杂环境下四旋翼无人机三维航迹规划问题,提出了一种改进的事件触发灰狼优化算法(event triggered grey wolf optimization,ETGWO)。引入球面矢量刻画飞行路径的生成,通过减少搜索空间提升搜索能力;设计自适应权重动态调整飞行航迹成本适应度函数,以提高航迹规划效率和准确性;在灰狼优化算法(grey wolf optimization,GWO)基础上,选择使用改进的非线性收敛因子,提升算法的鲁棒性;为了更好地平衡算法的全局搜索和局部搜索能力,通过引入基于事件触发机制的灰狼个体位置更新速度来改进GWO算法的位置更新策略。仿真对比实验表明,所提出ETGWO算法在四旋翼无人机(quadrotor unmanned aerial vehicles,QUAV)飞行航迹规划方面具有更优越的性能。
文摘针对工业机器人在高度制造领域精度不高的问题,本文提出了一种基于POE模型的工业机器人运动学参数二次辨识方法。阐述了基于指数积(Product of exponential, POE)模型的运动学误差模型构建方法,并建立基于POE误差模型的适应度函数;为实现高精度的参数辨识,提出了一种二次辨识方法,先利用改进灰狼优化算法(Improved grey wolf optimizer, IGWO)实现运动学参数误差的粗辨识,初步将Staubli TX60型机器人的平均位置误差和平均姿态误差分别从(0.648 mm, 0.212°)降低为(0.457 mm, 0.166°);为进一步提高机器人的精度性能,再通过LM(Levenberg-Marquard)算法进行参数误差的精辨识,最终将Staubli TX60型机器人平均位置误差和平均姿态误差进一步降低为(0.237 mm, 0.063°),机器人平均位置误差和平均姿态误差分别降低63.4%和70.2%。为了验证上述二次辨识方法的稳定性,随机选取5组辨识数据集和验证数据集进行POE误差模型的参数误差辨识,结果表明提出的二次辨识方法能够稳定、精确地辨识工业机器人运动学参数误差。
文摘高压脉冲放电破碎岩石的过程是复杂的非线性过程,存在放电时间短且破岩效果难以预测的问题。因此,建立高压脉冲破岩放电回路等效模型来描述破岩放电过程,提出基于改进的混沌灰狼优化(Gray wolf optimization,GWO)算法进行等效模型参数辨识。首先采用改进的奇异值分解算法对破碎不同岩石过程的电流进行滤波。然后通过6种标准测试函数,证明了与非线性最小二乘(Nonlinear least square,NLS)法、遗传算法(Genetic algorithm,GA)、粒子群优化(Particle swarm optimization,PSO)算法和GWO算法相比,改进的混沌GWO算法具有更好的寻优性能。最后将改进的混沌GWO算法的参数辨识结果与其他四种算法进行对比,结果验证了放电回路等效模型的准确性,也证明了该算法在辨识高压脉冲破岩放电回路等效模型时具有更快的收敛速度和更高的精度。同时,可求解出冲击波,从而能够分析高压脉冲破岩的动态过程。
