NSGA-Ⅱ多目標優(yōu)化算法的改進及應用研究
發(fā)布時間:2019-01-05 19:12
【摘要】:實際生活中,常會遇到關(guān)于多個目標同時優(yōu)化的各種問題。比如大眾消費時都想以便宜的價格買到優(yōu)質(zhì)的商品,這個“矛盾”就是一個關(guān)于多目標優(yōu)化的典型事例。在生活中眾多領(lǐng)域,多目標優(yōu)化問題皆扮演著重要角色,包括制造業(yè)、運輸業(yè)、服務業(yè)、電信業(yè)等行業(yè),多目標優(yōu)化問題無處不在。為了解決此類多個目標間相互“矛盾”的問題,常常需要將與這些問題相關(guān)的多個子目標轉(zhuǎn)化為與之對應的函數(shù)表達式,然后再對其進行優(yōu)化求解,這就是多目標問題的優(yōu)化。遺傳算法(GA)在多目標優(yōu)化方法中具有獨特的優(yōu)勢,特別是近年來廣泛研究和應用的多目標優(yōu)化遺傳算法(MOGA)及其相關(guān)的衍生算法,以非支配排序遺傳算法-Ⅱ(NSGA-Ⅱ)為代表。然而,傳統(tǒng)的NSGA-Ⅱ受限于模擬二進制交叉算子(SBX)和多項式變異算子,使非支配個體的全局搜索能力較弱,種群的多樣性較差等。針對傳統(tǒng)NSGA-Ⅱ中存在的諸多問題,本文提出了一種改進的NSGA-Ⅱ多目標優(yōu)化算法,經(jīng)過仿真實驗得到滿意的Pareto最優(yōu)解集,并通過實際應用驗證了改進的理論成果,解決了多目標優(yōu)化問題。本文提出改進的NSGA-Ⅱ多目標優(yōu)化算法,具體研究內(nèi)容主要體現(xiàn)在以下幾個方面:(1)針對不同的多目標優(yōu)化問題建立數(shù)學模型,并結(jié)合正交實驗法獲取實驗樣本,確定最佳優(yōu)化參數(shù),提升算法效率,節(jié)省運算時間。(2)在進化過程中引入正態(tài)分布交叉算子(NDX),有效解決了傳統(tǒng)的NSGA-Ⅱ算法中利用模擬二進制交叉算子(SBX)引起的搜索空間狹窄、容易陷入局部最優(yōu)等問題,增強了算法的空間搜索能力。(3)提出改進的自適應調(diào)整變異方式,提高了種群取優(yōu)速度。對于復雜的非線性優(yōu)化問題,傳統(tǒng)的NSGA-Ⅱ算法采用Deb提出的多項式變異方式,由于這種變異算子中含有隨機參數(shù)和主觀參數(shù),使其隨機性較大,收斂速度較慢。改進的自適應調(diào)整變異方式能夠通過其作用機理得到更好的收斂效果,不僅加快了種群的收斂速度,還維持了種群個體的多樣性,使得Pareto邊界分布更優(yōu)。(4)通過改進的NSGA-Ⅱ算法優(yōu)化聚硅氧烷的合成過程中反應溫度、反應時間、催化劑及其助劑的量,得到單分子轉(zhuǎn)化率的最大值和粘度分子量的期望值。實驗中定義了解集覆蓋度和空間分布量來衡量Pareto解的性能,并采用正交實驗法確定最優(yōu)進化參數(shù)。仿真測試結(jié)果用量化標準對比證明了改進的NSGA-Ⅱ算法取優(yōu)特性高于傳統(tǒng)的MOGA及其衍生算法,Pareto最優(yōu)前沿進一步顯示改進算法的解集分布更加均勻、連續(xù),驗證了本文提出改進的NSGA-Ⅱ多目標優(yōu)化算法理論在聚合優(yōu)化中應用的正確性及合理性。
[Abstract]:In real life, there are often problems with multiple goals being optimized at the same time. For example, when people consume, they want to buy quality goods at a low price. This contradiction is a typical example of multi-objective optimization. In many fields of life, multi-objective optimization problems play an important role, including manufacturing, transportation, service, telecommunications and other industries, multi-objective optimization problems everywhere. In order to solve this kind of "contradiction" between multiple objectives, it is often necessary to transform multiple sub-objectives related to these problems into corresponding functional expressions, and then optimize them. This is the optimization of multi-objective problems. Genetic algorithm (GA) has unique advantages in multi-objective optimization, especially (MOGA) and its related derivative algorithms, which have been widely studied and applied in recent years. Undominated sorting genetic algorithm-鈪,
本文編號:2402187
[Abstract]:In real life, there are often problems with multiple goals being optimized at the same time. For example, when people consume, they want to buy quality goods at a low price. This contradiction is a typical example of multi-objective optimization. In many fields of life, multi-objective optimization problems play an important role, including manufacturing, transportation, service, telecommunications and other industries, multi-objective optimization problems everywhere. In order to solve this kind of "contradiction" between multiple objectives, it is often necessary to transform multiple sub-objectives related to these problems into corresponding functional expressions, and then optimize them. This is the optimization of multi-objective problems. Genetic algorithm (GA) has unique advantages in multi-objective optimization, especially (MOGA) and its related derivative algorithms, which have been widely studied and applied in recent years. Undominated sorting genetic algorithm-鈪,
本文編號:2402187
本文鏈接:http://www.wukwdryxk.cn/shoufeilunwen/xixikjs/2402187.html
最近更新
教材專著