CAJ | 학술논문

针对分数阶达尔文粒子群算法收敛性能依赖于分数阶次α，易陷入局部最优的特点，提出了一种自适应的分数阶达尔文粒子群优化（AFO-DPSO）算法，利用粒子的位置和速度信息来动态调整分数阶次α，并引入自适应的加速系数控制策略和变异处理机制，以获取更优的收敛性能。对几种典型函数的测试结果表明，相比于现有的粒子群算法，所提的 AFO-DPSO 算法的搜索精度、收敛速度和稳定性都有了显著提高，全局寻优能力得到了进一步提高。
침대분수계체이문입자군산법수렴성능의뢰우분수계차α，역함입국부최우적특점，제출료일충자괄응적분수계체이문입자군우화（AFO-DPSO）산법，이용입자적위치화속도신식래동태조정분수계차α，병인입자괄응적가속계수공제책략화변이처리궤제，이획취경우적수렴성능。대궤충전형함수적측시결과표명，상비우현유적입자군산법，소제적 AFO-DPSO 산법적수색정도、수렴속도화은정성도유료현저제고，전국심우능력득도료진일보제고。
The convergence performance of the fractional-order Darwinian particle swarm optimization (FO-DPSO) al-gorithm depends on the fractional-orderα, and it can easily get trapped in the local optima. To overcome such shortcom-ing, an adaptive fractional-order Darwinian particle swarm optimization (AFO-DPSO) algorithm was proposed. In AFO-DPSO, both particle’s position and velocity information were utilized adequately, together an adaptive acceleration coefficient control strategy and mutation processing mechanism were introduced for better convergence performance. Testing results on several well-known functions demonstrate that AFO-DPSO substantially enhances the performance in terms of convergence speed, solution accuracy and algorithm stability. Compared with PSO, HPSO, DPSO, APSO, FO-PSO, FO-DPSO and NCPSO, the global optimality of AFO-DPSO are greatly improved.