基于混合人工蜂群和人工鱼群优化的LSSVM脉动风速预测

发布时间：2018-04-17 15:52

本文选题：人工蜂群算法 + 人工鱼群算法　；参考：《振动与冲击》2017年15期

【摘要】：考虑人工蜂群(ABC)和人工鱼群(AFS)算法的各自优势,提出混合智能算法(ABC+AFS)优化选择最小二乘支持向量机(LSSVM)参数的方法,以提高其脉动风速预测模型的性能。AFS算法有较强的全局寻优能力,混合智能算法以AFS算法中的人工鱼寻优方式代替ABC算法中的引领蜂寻优方式,克服ABC算法易陷入局部最优的问题。同时,ABC算法中的正负反馈机制可以克服AFS算法的后期盲目寻优、收敛速度下降的问题。运用基于混合ABC、AFS优化的LSSVM对脉动风速进行了预测,并与基于ABC、AFS和粒子群(PSO)算法优化的LSSVM脉动风速预测结果进行了比较。数值结果表明,基于混合ABC+AFS优化的LSSVM脉动风速预测模型有更好性能,具有工程应用前景。
[Abstract]:Considering the respective advantages of artificial bee colony (ABC) and artificial fish swarm (AFS) algorithms, a hybrid intelligent algorithm (ABC AFS) is proposed to optimize the selection of LSSVMs parameters.In order to improve the performance of its fluctuating wind speed prediction model, the hybrid intelligent algorithm has a strong global optimization ability. The hybrid intelligent algorithm uses artificial fish in the AFS algorithm instead of the lead bee optimization method in the ABC algorithm.To overcome the problem that ABC algorithm is easy to fall into local optimum.At the same time, the positive and negative feedback mechanism of AFS algorithm can overcome the problem of blind optimization and slow convergence of AFS algorithm.The pulsating wind speed is predicted by LSSVM based on the hybrid AFS algorithm, and compared with the prediction results of LSSVM pulsating wind speed based on the AFS algorithm and particle swarm optimization algorithm (PSO).The numerical results show that the LSSVM fluctuating wind speed prediction model based on mixed ABC AFS has better performance and has the prospect of engineering application.
【作者单位】：上海大学土木工程系;同济大学建筑工程系;上海飞虹钢结构工程有限公司;
【基金】：国家自然科学基金(51378304)
【分类号】：TP18;TU317

【相似文献】