基于混合预测策略与改进社会学习优化算法的动态多目标优化方法

近年来,国内外学者针对基于预测的动态多目标优化算法开展了深入研究,并提出了一系列有效的算法,然而已有的研究工作通常采用单一的预测策略,使得算法不能有效地应对剧烈的环境变化。针对上述问题,提出了一种基于混合预测策略与改进社会学习优化算法的动态多目标优化方法。具体地,当环境发生变化时,该方法首先基于代表性个体预测策略生成一部分群体;其次,基于拐点预测策略生成一部分新群体,特别地,为了提高种群的多样性,根据算法迭代的历史信息和环境变化情况随机地生成一定数量的新个体;为了提高问题的求解效率,对社会学习优化算法进行了改进,为每个进化空间设计了适用于动态多目标优化问题的算子;最后,将混合预测策略与改进的社会学习优化算法结合,构成了一种新的动态多目标优化方法。以FDA、DMOP和F函数集作为实验测试函数集,与四种代表性算法进行了性能对比;并以反向世代距离(inverted generational distance, IGD)对该方法的性能进行了深入的分析。实验结果表明所提方法具有较好的收敛性和鲁棒性。

基于混合预测策略的改进型并联有源电力滤波器无差拍控制

针对传统的无差拍电流跟踪控制受时延影响实际上是差一拍控制,提出一种改进的无差拍控制.该方法提前两个采样周期预测出有源电力滤波器(APF)指令电流,提前一个采样周期预测出逆变器输出电流,从而实现真正意义上的无差拍控制.同时,提出一种综合考虑负载谐波电流稳态和动态过程的混合预测策略,使上述预测过程更加准确、快速.仿真实验结果表明,基于该方法的APF在负载稳态和变化时均具有良好的补偿效果.

Hybrid optimization model and its application in prediction of gas emission

According to the complex nonlinear relationship between gas emission and its effect factors, and the shortcomings that basic colony algorithm is slow, prone to early maturity and stagnation during the search, we introduced a hybrid optimization strategy into a max-rain ant colony algorithm, then use this improved ant colony algorithm to estimate the scope of RBF network parameters. According to the amount of pheromone of discrete points, the authors obtained from the interval of net- work parameters, ants optimize network parameters. Finally, local spatial expansion is introduced to get further optimization of the network. Therefore, we obtain a better time efficiency and solution efficiency optimization model called hybrid improved max-min ant system （H1-MMAS）. Simulation experiments, using these theory to predict the gas emission from the working face, show that the proposed method have high prediction feasibility and it is an effective method to predict gas emission.