發(fā)布時間：2018-10-18 11:51

【摘要】：近年來,隨著神經(jīng)網(wǎng)絡(luò)的快速發(fā)展,其在工程方面的應(yīng)用也變得越來越多,但在實(shí)際的工程應(yīng)用中,總會不可避免的出現(xiàn)諸如脆弱性、非線性、時滯等問題,此類問題的存在將直接導(dǎo)致只有部分神經(jīng)元的狀態(tài)信息可以通過網(wǎng)絡(luò)輸出。由此可見,盡可能準(zhǔn)確的估計神經(jīng)元的狀態(tài)具有重要的科研價值以及實(shí)際意義。本文研究的內(nèi)容是針對連續(xù)神經(jīng)網(wǎng)絡(luò)系統(tǒng)進(jìn)行建模,并且基于Lyapunov穩(wěn)定性定理,結(jié)合線性矩陣不等式(Linear Matrix Inequality,LMI)技術(shù)、矩陣分析技術(shù)等,討論系統(tǒng)的穩(wěn)定性并且對非脆弱性狀態(tài)估計器設(shè)計方法進(jìn)行驗(yàn)證。首先,針對具有時變時滯的連續(xù)神經(jīng)網(wǎng)絡(luò)系統(tǒng),進(jìn)行系統(tǒng)穩(wěn)定性分析,并且討論考慮加性增益變化的非脆弱性狀態(tài)估計器研究方法。采用LMI方法,獲得保證系統(tǒng)漸近穩(wěn)定和滿足其他約束條件的非脆弱性狀態(tài)估計器存在的充分條件,以及狀態(tài)估計器的增益,并對研究結(jié)果進(jìn)行分析。其次,建立一類具有加性增益變化和時變時滯的連續(xù)神經(jīng)網(wǎng)絡(luò)模型,分析系統(tǒng)穩(wěn)定性并設(shè)計非脆弱性狀態(tài)估計器。定義連續(xù)神經(jīng)網(wǎng)絡(luò)增廣系統(tǒng)和約束條件,選取李雅普諾夫函數(shù)并按照其穩(wěn)定性定理,分析得到系統(tǒng)漸近穩(wěn)定及狀態(tài)估計器增益存在的充分條件。此時,非脆弱性狀態(tài)估計器的設(shè)計實(shí)現(xiàn)就轉(zhuǎn)化為求解相應(yīng)LMI的可行解。再次,考慮到時變時滯的神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性和非脆弱性狀態(tài)估計算法。采用乘性范數(shù)有界形式的估計器增益變化,利用Lipschitz條件刻畫神經(jīng)元狀態(tài)依賴非線性擾動,研究帶有非脆弱性的狀態(tài)估計器。利用Lyapunov穩(wěn)定性定理、矩陣分析技術(shù)、LMI技術(shù)、Leibniz-Newton公式,得到非脆弱性狀態(tài)估計器存在的充分條件,以及標(biāo)準(zhǔn)LMI問題的可行解。最后,研究伴隨噪聲的連續(xù)神經(jīng)網(wǎng)絡(luò)系統(tǒng)穩(wěn)定性和非脆弱性狀態(tài)估計算法。利用兩個不同的函數(shù)表示噪聲,即系統(tǒng)產(chǎn)生的噪聲序列和系統(tǒng)的觀測噪聲序列。結(jié)合上述神經(jīng)網(wǎng)絡(luò)模型,設(shè)計具有增益變量的非脆弱性狀態(tài)估計器。通過分析誤差動態(tài)增廣系統(tǒng)的穩(wěn)定性以及H?性能,得到非脆弱性狀態(tài)估計器存在并且需要滿足的LMI,即將非脆弱性狀態(tài)估計器設(shè)計變換成用標(biāo)準(zhǔn)線性矩陣不等式方法解決凸優(yōu)化問題,并通過實(shí)際算例說明研究的準(zhǔn)確性。
[Abstract]:In recent years, with the rapid development of neural network, its application in engineering has become more and more, but in practical engineering applications, there are always inevitable problems such as vulnerability, nonlinearity, time-delay and so on. The existence of this kind of problem will directly result in the state information of some neurons can be outputted through the network. It can be seen that estimating the state of neurons as accurately as possible has important scientific research value and practical significance. The content of this paper is to model the continuous neural network system, and based on the Lyapunov stability theorem, combining with the linear matrix inequality (Linear Matrix Inequality,LMI) technology, matrix analysis technology, etc. The stability of the system is discussed and the design method of the non-fragile state estimator is verified. Firstly, the stability of continuous neural network systems with time-varying delays is analyzed, and the research method of non-vulnerability state estimators considering additive gain variation is discussed. By using the LMI method, the sufficient conditions for the existence of a non-fragile state estimator, which guarantees the asymptotic stability of the system and satisfies other constraints, are obtained, as well as the gain of the state estimator. The results of the study are analyzed. Secondly, a class of continuous neural network models with additive gain variation and time-varying delay are established to analyze the stability of the system and to design a non-fragile state estimator. The continuous neural network augmented system and its constraint conditions are defined. The Lyapunov function is selected and the sufficient conditions for the asymptotic stability of the system and the existence of the gain of the state estimator are obtained according to its stability theorem. In this case, the design and implementation of the non-vulnerability state estimator is transformed into a feasible solution to solve the corresponding LMI. Thirdly, the stability and non-vulnerability state estimation algorithms of neural networks with time-varying delays are considered. The gain variation of the estimator in the bounded form of multiplicative norm is used to characterize the neuron state dependent nonlinear disturbance by using the Lipschitz condition. The state estimator with non-vulnerability is studied. By using the Lyapunov stability theorem, matrix analysis technique, LMI technique and Leibniz-Newton formula, the sufficient conditions for the existence of non-fragile state estimators and the feasible solutions of the standard LMI problem are obtained. Finally, the stability and non-vulnerability state estimation algorithms for continuous neural networks with noise are studied. Two different functions are used to represent the noise, that is, the noise sequence generated by the system and the observed noise sequence of the system. Based on the above neural network model, a non-vulnerability state estimator with gain variables is designed. By analyzing the stability of dynamic augmentation system with error and H? The performance of the non-fragile state estimator is obtained and the LMI, that needs to be satisfied is transformed into a standard linear matrix inequality (LMI) method to solve the convex optimization problem. An example is given to illustrate the accuracy of the study.
【學(xué)位授予單位】：東北石油大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 屈百達(dá);徐培培;;不確定線性時變時滯系統(tǒng)的非脆弱魯棒H_∞控制器設(shè)計[J];計算機(jī)工程與應(yīng)用;2015年10期

2 許研;張煒;;基于噪聲濾波的非線性系統(tǒng)故障診斷方法研究[J];計算機(jī)測量與控制;2014年09期

3 劉國權(quán);周書民;;一類含有時變時滯的不確定中立型Hopfield神經(jīng)網(wǎng)絡(luò)的魯棒穩(wěn)定性判據(jù)[J];自動化學(xué)報;2013年09期

4 尹正男;蘇劍波;高秀行;;保證閉環(huán)系統(tǒng)魯棒穩(wěn)定性的干擾觀測器系統(tǒng)性設(shè)計方法[J];自動化學(xué)報;2012年01期

5 李亞軍;鄧飛其;彭云建;;變時滯模糊隨機(jī)細(xì)胞神經(jīng)網(wǎng)絡(luò)新的魯棒穩(wěn)定性[J];控制與決策;2011年08期

6 褚東升;王紅都;張玲;;帶乘性噪聲系統(tǒng)的最優(yōu)方差約束魯棒狀態(tài)估計算法[J];中國海洋大學(xué)學(xué)報(自然科學(xué)版);2011年04期

7 馬大中;王占山;馮健;;非線性無窮分布時滯系統(tǒng)的非脆弱控制[J];東北大學(xué)學(xué)報(自然科學(xué)版);2009年11期

8 陳云;薛安克;王俊宏;;隨機(jī)時滯系統(tǒng)的時滯相關(guān)無源控制[J];自動化學(xué)報;2009年03期

9 冉華軍;蔡逢煌;王武;楊富文;;具有參數(shù)攝動離散系統(tǒng)的魯棒非脆弱H_∞濾波[J];福州大學(xué)學(xué)報(自然科學(xué)版);2008年03期

10 李旭光;朱新堅;曹廣益;;時滯系統(tǒng)穩(wěn)定性分析:一種積分等式方法[J];控制與決策;2008年04期

相關(guān)博士學(xué)位論文 前2條

1 劉一莎;幾類隨機(jī)非線性時滯系統(tǒng)的可靠控制和濾波[D];大連理工大學(xué);2011年

2 肖伸平;不確定線性時滯系統(tǒng)時滯相關(guān)非脆弱魯棒控制[D];中南大學(xué);2008年

相關(guān)碩士學(xué)位論文 前4條

1 邱彬;時滯復(fù)值神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性分析及狀態(tài)估計[D];西南大學(xué);2016年

2 段琪輝;時滯神經(jīng)網(wǎng)絡(luò)系統(tǒng)的狀態(tài)估計與濾波[D];浙江大學(xué);2013年

3 王紅;時滯神經(jīng)網(wǎng)絡(luò)系統(tǒng)的穩(wěn)定性及狀態(tài)估計研究[D];大連理工大學(xué);2008年

4 趙睿;捷聯(lián)慣性系統(tǒng)初始對準(zhǔn)研究[D];東南大學(xué);2006年

，

本文編號：2279042