混沌系統(tǒng)智能辨識與控制研究
發(fā)布時間:2018-08-01 12:26
【摘要】:混沌是自然界中廣泛存在的一種復(fù)雜運動形式。近些年來,混沌與其它學(xué)科互相滲透,無論是在物理學(xué)、生物學(xué)、數(shù)學(xué)、電子學(xué)、心理學(xué)、信息科學(xué),還是在氣象學(xué)、經(jīng)濟(jì)學(xué)、天文學(xué),甚至在音樂、藝術(shù)等領(lǐng)域都得到了廣泛的應(yīng)用。為了更好地利用混沌或者消除混沌的不良影響,辨識混沌系統(tǒng)的模型并實施相應(yīng)的控制具有重要的意義。近些年來,以神經(jīng)網(wǎng)絡(luò)和模糊理論為代表的智能控制理論在復(fù)雜系統(tǒng)建模、控制方面得到了長足發(fā)展。本文采用智能控制理論研究了混沌系統(tǒng)的辨識與控制,具體研究工作如下:首先,提出了一種基于區(qū)間Ⅱ型模糊系統(tǒng)的混沌系統(tǒng)辨識方法。該方法采用網(wǎng)格對角線法來劃分模糊空間,Ⅱ型模糊集主隸屬度函數(shù)為對稱三角形隸屬函數(shù)。在保持前件參數(shù)不變的情況下,采用帶遺忘因子的遞推最小二乘法辨識結(jié)論參數(shù)。為了解決采樣數(shù)據(jù)受到噪聲污染的問題,對采樣數(shù)據(jù)進(jìn)行Sigmoid數(shù)據(jù)變換,并采用粒子群算法優(yōu)化變換函數(shù)的關(guān)鍵參數(shù)和隸屬函數(shù)寬度,避免了隸屬函數(shù)的調(diào)整,提高了Ⅱ型模糊模型的辨識精度。此方法應(yīng)用到Mackey-Glass混沌系統(tǒng)的建模中,仿真結(jié)果驗證了本文方法的有效性。其次,利用混沌系統(tǒng)的部分結(jié)構(gòu)信息,提出了一種基于Wiener-LSSVM模型的混沌系統(tǒng)辨識方法。Wiener-LSSVM模型由一個線性動態(tài)子系統(tǒng)和LSSVM組成,比較適合描述大部分的混沌系統(tǒng)。給出了同時辨識線性動態(tài)部分和最小二乘支持向量機(jī)的最小二乘算法。然后,提出了一種基于Hammerstein-ELM模型的混沌系統(tǒng)辨識方法。Hammerstein-ELM模型由一個極值學(xué)習(xí)機(jī)神經(jīng)網(wǎng)絡(luò)和一個線性動態(tài)部分組成。推導(dǎo)出了用于同時辨識ELM神經(jīng)網(wǎng)絡(luò)和線性動態(tài)子系統(tǒng)參數(shù)的廣義極值學(xué)習(xí)算法。該算法采用矩陣偽逆確定辨識參數(shù),提高了辨識的準(zhǔn)確性。最后,基于模糊理論,提出了兩種Hénon混沌系統(tǒng)的控制與同步算法。第一種方法采用T-S模型來辨識Hénon混沌系統(tǒng),得到Hénon混沌系統(tǒng)的局部動態(tài)線性模型,基于此模型設(shè)計了模糊廣義預(yù)測控制算法來實現(xiàn)Hénon混沌系統(tǒng)的跟蹤與同步控制。第二種方法采用模糊逆方法建立Hénon混沌系統(tǒng)的模糊逆模型,基于此模糊逆模型設(shè)計了Hénon混沌系統(tǒng)的自適應(yīng)逆控制與同步算法。仿真結(jié)果驗證了所提方法的有效性。
[Abstract]:Chaos is a complex form of motion widely existing in nature. In recent years, chaos has interpenetrated with other disciplines, whether in physics, biology, mathematics, electronics, psychology, information science, meteorology, economics, astronomy, or even music. Art and other fields have been widely used. In order to make better use of chaos or eliminate the bad effects of chaos, it is of great significance to identify the model of chaotic system and implement the corresponding control. In recent years, intelligent control theory, represented by neural network and fuzzy theory, has made great progress in complex system modeling and control. In this paper, the identification and control of chaotic systems are studied by using intelligent control theory. The research work is as follows: firstly, a chaotic system identification method based on interval 鈪,
本文編號:2157574
[Abstract]:Chaos is a complex form of motion widely existing in nature. In recent years, chaos has interpenetrated with other disciplines, whether in physics, biology, mathematics, electronics, psychology, information science, meteorology, economics, astronomy, or even music. Art and other fields have been widely used. In order to make better use of chaos or eliminate the bad effects of chaos, it is of great significance to identify the model of chaotic system and implement the corresponding control. In recent years, intelligent control theory, represented by neural network and fuzzy theory, has made great progress in complex system modeling and control. In this paper, the identification and control of chaotic systems are studied by using intelligent control theory. The research work is as follows: firstly, a chaotic system identification method based on interval 鈪,
本文編號:2157574
本文鏈接:http://sikaile.net/shoufeilunwen/jckxbs/2157574.html
最近更新
教材專著