本文關(guān)鍵詞：基于M-矩陣?yán)碚摰拿}沖時(shí)滯神經(jīng)網(wǎng)絡(luò)穩(wěn)定性分析與同步控制　出處：《電子科技大學(xué)》2015年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： M-矩陣 時(shí)滯神經(jīng)網(wǎng)絡(luò) 指數(shù)穩(wěn)定 脈沖擾動(dòng)和鎮(zhèn)定 同步控制

【摘要】：神經(jīng)網(wǎng)絡(luò)的研究經(jīng)過(guò)不斷發(fā)展和完善,現(xiàn)已被成功地應(yīng)用到計(jì)算機(jī)科學(xué)、人工智能、自動(dòng)控制、模式識(shí)別、圖像處理、組合最優(yōu)化、聯(lián)想記憶等學(xué)科研究領(lǐng)域。而這些應(yīng)用的關(guān)鍵依賴于神經(jīng)網(wǎng)絡(luò)的動(dòng)力學(xué)行為。在實(shí)際中,由于時(shí)滯的客觀存在性和脈沖現(xiàn)象的普遍性,且時(shí)滯和脈沖對(duì)神經(jīng)網(wǎng)絡(luò)動(dòng)力學(xué)行為有著不可忽視的影響。因此,兼具時(shí)滯和脈沖神經(jīng)網(wǎng)絡(luò)的動(dòng)力學(xué)研究引起了眾多學(xué)者的關(guān)注,并成為非線性系統(tǒng)動(dòng)力學(xué)研究方面的重要課題之一。本文系統(tǒng)地研究了脈沖影響下具有不同時(shí)滯類型的幾類神經(jīng)網(wǎng)絡(luò)的動(dòng)力學(xué)行為。概括地講,研究?jī)?nèi)容包括脈沖擾動(dòng)下平衡點(diǎn)、周期軌的穩(wěn)定性;脈沖控制下平衡點(diǎn)的指數(shù)鎮(zhèn)定,脈沖擾動(dòng)和脈沖鎮(zhèn)定下混沌同步控制。具體地講,本文的研究工作可歸納為如下的六個(gè)方面:(一)研究了一類以Hopfield神經(jīng)網(wǎng)絡(luò)、細(xì)胞神經(jīng)網(wǎng)絡(luò)為背景的更一般的神經(jīng)網(wǎng)絡(luò)模型在具有連續(xù)分布時(shí)滯和非線性脈沖干擾下平衡點(diǎn)的穩(wěn)定性問(wèn)題。運(yùn)用拓?fù)涠壤碚�、M-矩陣?yán)碚摵筒坏仁郊记?獲得了保證網(wǎng)絡(luò)模型平衡點(diǎn)存在性和唯一性的M-矩陣新判據(jù);在該M-矩陣條件下,利用分析的方法證明了網(wǎng)絡(luò)平衡點(diǎn)在一定的非線性脈沖干擾下仍然能保持全局指數(shù)穩(wěn)定性;通過(guò)一個(gè)具體例子驗(yàn)證了理論結(jié)果的有效性和優(yōu)越性。(二)作為上述研究?jī)?nèi)容的繼續(xù)和深入,進(jìn)一步討論了(一)中的神經(jīng)網(wǎng)絡(luò)模型在具有變時(shí)滯和更具一般性的非線性脈沖擾動(dòng)下平衡點(diǎn)的穩(wěn)定性問(wèn)題。與(一)中所運(yùn)用到的拓?fù)涠确椒ú煌?基于同胚映射原理,M-矩陣?yán)碚摵筒坏仁郊记?給出了網(wǎng)絡(luò)模型平衡點(diǎn)存在且唯一的更一般形式的M-矩陣判定標(biāo)準(zhǔn);在該M-矩陣條件下,利用分析的方法證明了網(wǎng)絡(luò)平衡點(diǎn)在更一般非線性脈沖擾動(dòng)下仍然是全局指數(shù)穩(wěn)定的;通過(guò)兩個(gè)具體例子驗(yàn)證了理論結(jié)果的有效性和優(yōu)越性。(三)研究了一類以神經(jīng)元的狀態(tài)直接作為基本變量所得到的靜態(tài)神經(jīng)網(wǎng)絡(luò)模型在具有比例時(shí)滯和線性脈沖干擾下平衡點(diǎn)的穩(wěn)定性問(wèn)題。這里所考慮的時(shí)滯類型既不同于(一)中所討論的連續(xù)分布時(shí)滯,也不同于(二)中所考慮的有界變時(shí)滯,它是一種無(wú)界的時(shí)變時(shí)滯�；趶V義的矩陣測(cè)度和推廣的Halanay不等式,得到了所考慮網(wǎng)絡(luò)模型平衡點(diǎn)全局指數(shù)穩(wěn)定矩陣測(cè)度形式的判定標(biāo)準(zhǔn)。通過(guò)兩個(gè)具體例子驗(yàn)證了理論結(jié)果的有效性和優(yōu)越性。(四)在原始雙向聯(lián)想記憶(BAM)神經(jīng)網(wǎng)絡(luò)的基礎(chǔ)上,研究了一類更為復(fù)雜(具有周期性變系數(shù)和外界輸入,連續(xù)分布時(shí)滯,非線性脈沖干擾和高階項(xiàng))BAM神經(jīng)網(wǎng)絡(luò)模型的周期振蕩動(dòng)力學(xué)行為�；贛-矩陣?yán)碚�、�?gòu)造Lyapunov-Krasovskii泛函、不等式技巧和分析的方法,給出了所研究網(wǎng)絡(luò)模型周期解存在唯一且全局指數(shù)穩(wěn)定的充分條件。通過(guò)一個(gè)具體例子驗(yàn)證了理論結(jié)果的有效性和優(yōu)越性。(五)研究了一類憶阻神經(jīng)網(wǎng)絡(luò)模型(即用新的非線性電子元件憶阻器代替?zhèn)鹘y(tǒng)神經(jīng)網(wǎng)絡(luò)模型中的電阻所得到的一種新的神經(jīng)網(wǎng)絡(luò)模型)在脈沖控制下平衡點(diǎn)的鎮(zhèn)定性問(wèn)題�；诿}沖控制的觀點(diǎn),聯(lián)合運(yùn)用集值映射和脈沖微分包含理論、非光滑分析及新建立的脈沖微分不等式,給出了所考慮網(wǎng)絡(luò)模型可全局指數(shù)鎮(zhèn)定到平衡點(diǎn)零解的代數(shù)不等式判定準(zhǔn)則。通過(guò)兩個(gè)數(shù)值例子驗(yàn)證了理論結(jié)果的有效性和可行性。(六)基于兩種不同形式的脈沖影響(脈沖擾動(dòng)和脈沖控制),首先研究了以混沌憶阻神經(jīng)網(wǎng)絡(luò)為驅(qū)動(dòng)系統(tǒng)并受到外界脈沖干擾時(shí)與其響應(yīng)系統(tǒng)的同步問(wèn)題,然后討論了只在響應(yīng)系統(tǒng)中加入適當(dāng)脈沖控制時(shí)驅(qū)動(dòng)-響應(yīng)系統(tǒng)的同步問(wèn)題。針對(duì)這兩類問(wèn)題,綜合運(yùn)用脈沖擾動(dòng)型和脈沖鎮(zhèn)定型的Halanay不等式及前面(二)和(五)中的思想方法,分別獲得了狀態(tài)反饋和脈沖控制下的同步標(biāo)準(zhǔn)。最后,通過(guò)一個(gè)數(shù)值例子驗(yàn)證了這兩種同步標(biāo)準(zhǔn)的有效性和可行性。
[Abstract]:The research of neural network through the continuous development and improvement, has been successfully applied to computer science, artificial intelligence, automatic control, pattern recognition, image processing, combinatorial optimization, associative memory and other research fields. The dynamic behavior and the key of these applications depends on the neural network. In practice, due to the universal existence time delay and pulse delay and pulse phenomenon, and has an important influence on the dynamic behavior of the neural network. Therefore, both the kinetics of delay and impulsive neural network has attracted the attention of many scholars, and has become one of the important issue of nonlinear dynamic system. Dynamics with several kinds of neural networks of different types of delay this paper systematically studied the effect of pulse condition. Generally speaking, the research content including pulse disturbance equilibrium, stability of periodic orbits; pulse Under the control of the equilibrium point of exponential stabilization, impulsive perturbations and Impulsive Stabilization of chaotic synchronization control. Specifically, the research work of this paper can be summarized into six aspects as follows: (a) to study a class of Hopfield neural network, the neural network model of general cellular neural network as the background of the continuous distribution delay and nonlinear in the impulsive stability problem under the equilibrium point. By using the theory of topological degree, M- matrix theory and inequality technique, the new criterion of M- matrix to guarantee the existence and uniqueness of the network equilibrium; in the condition of the M- matrix, it is proved that network equilibrium can still maintain global exponential stability in certain nonlinear pulse the interference by using the method of analysis; through a concrete example to verify the validity and superiority of the theoretical results. (two) as to the above research contents and in-depth, further discussed ( A) neural network model with time-varying delays and general nonlinear impulsive stability problem of equilibrium point in it. (a) with different topological method used in the homeomorphism mapping based on the principle of M- matrix theory and inequality technique, gives the network model equilibrium exists and criteria only the more general form of M- matrix; in condition of the M- matrix, it is proved that network equilibrium in pulse more general nonlinear perturbation is globally exponentially stable by using the method of analysis; through two specific examples to verify the theoretical validity and superiority of the results. (three) studied the static neural network a class of models directly to the states of the neurons as the basic variables obtained with proportional delays and linear pulse interference under the stability problem of the equilibrium point. The delay type considered here is different from (a) in the sea Continuous distributed delay theory, but also different from (two) in consideration of the bounded delay, it is a kind of unbounded time-varying delay. Halanay inequalities of matrix measure and generalized based on the network model considering the globally exponential stability of the equilibrium point matrix measure form criteria by two. An example shows the effectiveness and superiority of the theoretical results. (four) in the original bidirectional associative memory (BAM) based on neural network is studied for a class of more complex (with periodic coefficients and external input, continuous distribution delay, nonlinear pulse interference and high order) periodic oscillation dynamics of BAM the neural network model. The M- matrix based on the theory of constructing Lyapunov-Krasovskii functional method and inequality analysis, gives the research cycle network model with sufficient conditions for the existence and uniqueness and global exponential stability. Through a Body examples to verify the validity and superiority of the theoretical results. (five) studied a class of memristive neural network model (the resistance of new nonlinear electronic components memristor instead of the traditional neural network model obtained by a new neural network model) in the impulsive control stabilization problem under equilibrium the pulse control. Based on the view of the joint use of set-valued mapping and impulsive differential inclusions theory, nonsmooth analysis and new impulsive differential inequality, given the network model decidable algebraic inequalities global exponential stabilization to the equilibrium point of the zero solution criterion. Through two numerical examples verify the effectiveness of the theoretical results and feasibility. (six) effects of two kinds of pulse (pulse and pulse control based on disturbance), first studies on chaotic memristive neural network driven system and external interference and pulse response Synchronization of system, and then discusses the synchronization in the response system with appropriate pulse control when the drive response system. According to the two kinds of problems, the integrated use of pulse Halanay inequality and disturbance type and pulse shaping in front of the town (two) and (five) thought method, were given the standard synchronization state feedback and impulsive control. Finally, through a numerical example to verify the effectiveness of the two kinds of synchronization standard and feasibility.

【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：O175

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李寶麟;王蓉;;離散時(shí)刻Cohen-Grossberg時(shí)滯神經(jīng)網(wǎng)絡(luò)周期解的存在性與穩(wěn)定性[J];西北師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2009年02期

2 陳萬(wàn)義;關(guān)于時(shí)滯神經(jīng)網(wǎng)絡(luò)的全局漸近穩(wěn)定性[J];南開大學(xué)學(xué)報(bào)(自然科學(xué)版);1999年04期

3 邱亞林;一類時(shí)滯神經(jīng)網(wǎng)絡(luò)模型的穩(wěn)定性[J];四川師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2000年01期

4 向紅軍,王金華;多時(shí)滯神經(jīng)網(wǎng)絡(luò)關(guān)于滯量上界的一個(gè)估計(jì)[J];河南師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2005年04期

5 郭美珍;盧金平;;一類二元時(shí)滯神經(jīng)網(wǎng)絡(luò)模型同步解的收斂性[J];河南科學(xué);2008年12期

6 張芬;張艷邦;;一類時(shí)滯神經(jīng)網(wǎng)絡(luò)系統(tǒng)漸近穩(wěn)定的新判據(jù)[J];西北師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年03期

7 章毅,鐘守銘,王莉;無(wú)窮時(shí)滯神經(jīng)網(wǎng)絡(luò)的全局穩(wěn)定性[J];控制理論與應(yīng)用;1998年02期

8 朱文莉,張杰;變系數(shù)時(shí)滯神經(jīng)網(wǎng)絡(luò)的周期解與穩(wěn)定性[J];電子科技大學(xué)學(xué)報(bào);2005年01期

9 張皓;嚴(yán)懷成;陳啟軍;;隨機(jī)混沌時(shí)滯神經(jīng)網(wǎng)絡(luò)的指數(shù)同步[J];控制理論與應(yīng)用;2009年02期

10 劉群;祝紅芳;;慣性時(shí)滯神經(jīng)網(wǎng)絡(luò)共振余維二分岔[J];南昌大學(xué)學(xué)報(bào)(理科版);2009年05期

相關(guān)會(huì)議論文 前2條

1 茅曉晨;;時(shí)滯耦合神經(jīng)網(wǎng)絡(luò)的非線性動(dòng)力學(xué)[A];The 5th 全國(guó)動(dòng)力學(xué)與控制青年學(xué)者研討會(huì)論文摘要集[C];2011年

2 陳萬(wàn)義;;關(guān)于一類Hopfield型時(shí)滯神經(jīng)網(wǎng)絡(luò)模型的全局漸近穩(wěn)定性[A];第二十二屆中國(guó)控制會(huì)議論文集（上）[C];2003年

相關(guān)博士學(xué)位論文 前10條

1 侯利元;時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性分析及濾波器設(shè)計(jì)[D];電子科技大學(xué);2015年

2 楊昌波;基于M-矩陣?yán)碚摰拿}沖時(shí)滯神經(jīng)網(wǎng)絡(luò)穩(wěn)定性分析與同步控制[D];電子科技大學(xué);2015年

3 周小兵;時(shí)滯神經(jīng)網(wǎng)絡(luò)的動(dòng)力學(xué)研究[D];電子科技大學(xué);2008年

4 劉群;外部激勵(lì)和慣性項(xiàng)對(duì)時(shí)滯神經(jīng)網(wǎng)絡(luò)動(dòng)力學(xué)行為的影響研究[D];重慶大學(xué);2008年

5 高明;時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性與同步研究[D];江南大學(xué);2009年

6 田俊康;幾類變時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性研究[D];電子科技大學(xué);2013年

7 董滔;時(shí)滯神經(jīng)網(wǎng)絡(luò)的動(dòng)力學(xué)行為分析[D];重慶大學(xué);2013年

8 劉德友;幾類時(shí)滯神經(jīng)網(wǎng)絡(luò)穩(wěn)定性的研究[D];燕山大學(xué);2006年

9 李傳東;時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性和混沌同步[D];重慶大學(xué);2005年

10 涂風(fēng)華;時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性研究[D];重慶大學(xué);2005年

相關(guān)碩士學(xué)位論文 前10條

1 范陳新;基于分割方法的時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性分析[D];大連理工大學(xué);2015年

2 許李;一類具有變時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性研究[D];電子科技大學(xué);2015年

3 黃優(yōu)良;幾類具混合時(shí)滯神經(jīng)網(wǎng)絡(luò)的同步分析[D];揚(yáng)州大學(xué);2008年

4 吳桂華;脈沖時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性分析[D];重慶大學(xué);2009年

5 穆文英;時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性與混沌同步及其應(yīng)用[D];江南大學(xué);2011年

6 陳雯雯;幾類時(shí)滯神經(jīng)網(wǎng)絡(luò)系統(tǒng)的穩(wěn)定性分析[D];杭州電子科技大學(xué);2011年

7 盧金平;兩類二元時(shí)滯神經(jīng)網(wǎng)絡(luò)模型解的定性研究[D];湖南大學(xué);2007年

8 張國(guó)光;一類時(shí)滯神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性分析[D];中國(guó)海洋大學(xué);2011年

9 張靜文;基于時(shí)滯神經(jīng)網(wǎng)絡(luò)的二次規(guī)劃的全局最優(yōu)性條件[D];燕山大學(xué);2012年

10 吳文娟;幾類時(shí)滯神經(jīng)網(wǎng)絡(luò)穩(wěn)定性的分析[D];燕山大學(xué);2012年

，

本文編號(hào)：1397469