【摘要】：搬運(yùn)介質(zhì)、搬運(yùn)方式、沉積環(huán)境和氣候等因素控制著沉積物粒度參數(shù)的變化,因此,沉積物粒度分析對(duì)揭示氣候變化和環(huán)境的演變具有重要意義。粒度參數(shù)中平均粒徑、標(biāo)準(zhǔn)偏差、偏差和峰值是沉積物粒度的四個(gè)重要參數(shù)。不同粒度組分的形成與搬運(yùn)均與沉積環(huán)境密切相關(guān),處理、分析粒度數(shù)據(jù)有利于進(jìn)一步確定沉積環(huán)境,這對(duì)于現(xiàn)代沉積學(xué)研究,乃至古代沉積物的沉積環(huán)境分析無(wú)疑都具有重要的理論和現(xiàn)實(shí)意義。模糊神經(jīng)系統(tǒng)是這樣一個(gè)模糊系統(tǒng),它在處理數(shù)據(jù)樣本過(guò)程中,使用某種學(xué)習(xí)算法去確定系統(tǒng)中的各項(xiàng)參數(shù)如模糊集和模糊規(guī)則,而該學(xué)習(xí)算法則由神經(jīng)網(wǎng)絡(luò)原理學(xué)習(xí)或激發(fā)出來(lái)的。利用模糊技術(shù)與神經(jīng)網(wǎng)絡(luò)的結(jié)合,我們可以充分發(fā)揮兩者的優(yōu)勢(shì),有效彌補(bǔ)各自的不足,這使得有關(guān)模糊神經(jīng)系統(tǒng)的研究得到追捧,在包括自動(dòng)控制、聚類分析和模式識(shí)別等領(lǐng)域中已得到成功應(yīng)用,為人工智能的發(fā)展又增添了新的方向。本文是以諾姆·喬姆斯基提出的Chomsky體系文法為基礎(chǔ)的,通過(guò)引入模糊自動(dòng)機(jī)基本理論,簡(jiǎn)要概述了當(dāng)前模糊自動(dòng)機(jī)研究中有關(guān)神經(jīng)網(wǎng)絡(luò)技術(shù)的應(yīng)用情況,這其中主要是以模糊有限狀態(tài)自動(dòng)機(jī)、模糊文法和神經(jīng)網(wǎng)絡(luò)這三者的關(guān)系為主線的,而通過(guò)對(duì)相關(guān)的神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練,我們就可以抽取出所需的自動(dòng)機(jī),然后利用抽取的自動(dòng)機(jī)進(jìn)行文法的推導(dǎo),以及對(duì)沉積環(huán)境進(jìn)行判別分析。有關(guān)模糊神經(jīng)系統(tǒng)的研究與應(yīng)用已經(jīng)具有一定的規(guī)模,但對(duì)于本論文來(lái)說(shuō),主要是研究基于神經(jīng)網(wǎng)絡(luò)的模糊正則文法推導(dǎo)算法以及模糊自動(dòng)機(jī)的判別方法相關(guān)的問(wèn)題。在模糊正則文法推導(dǎo)中,訓(xùn)練用于抽取模糊自動(dòng)機(jī)的二階反饋神經(jīng)網(wǎng)絡(luò)的算法主要有實(shí)時(shí)遞歸學(xué)習(xí)算法(RTRL)和實(shí)數(shù)編碼基因遺傳算法(RCGA),但是這兩種算法存在通�。簳r(shí)間復(fù)雜度高,訓(xùn)練速度極慢。另外針對(duì)模糊有限態(tài)自動(dòng)機(jī)(FSA)樣本,兩種算法都有不同種類的異常情況出現(xiàn),也就是說(shuō)泛化性很弱。最后,RTRL穩(wěn)定性很弱；RCGA早熟現(xiàn)象經(jīng)常出現(xiàn)。因而本文給出針對(duì)RCGA的改進(jìn)算法：Levesbeg-Marguard Genetic Algorithm(LMGA),改進(jìn)了訓(xùn)練速度以及解決了早熟的問(wèn)題；針對(duì)RTRL算法,第七章給出了Levesbeg-Marguard Back Propagation(LMBP)算法,不僅加快了訓(xùn)練速度,增加了吞吐量,而且還能處理特殊情況下的字符串,比如超長(zhǎng)串的情況。本文還給出了實(shí)驗(yàn)仿真與驗(yàn)證,并歸納了本文的結(jié)論。
[Abstract]:Factors such as transport medium, handling mode, sedimentary environment and climate control the change of grain size parameters. Therefore, sediment grain size analysis is of great significance to reveal climate change and environmental evolution. The average particle size, standard deviation, deviation and peak in grain size parameters are four important parameters of sediment granularity. The formation and transportation are closely related to the sedimentary environment. Processing and analyzing the grain size data are beneficial to further determine the sedimentary environment. This is of great theoretical and practical significance for modern sedimentology research and even the sedimentary environment analysis of ancient sediments. Fuzzy neural system is such a fuzzy system, which is dealing with data samples. In the process, some learning algorithms are used to determine the parameters of the system, such as fuzzy sets and fuzzy rules, and the learning algorithm is learned or excited by the principle of neural network. By combining the fuzzy technology with the neural network, we can make full use of the advantages of the two and make up for their own shortcomings, which makes the fuzzy God concerned. After systematic research, it has been successfully applied in the fields of automatic control, cluster analysis and pattern recognition. It has added a new direction to the development of artificial intelligence. This paper is based on the Chomsky system grammar proposed by Norm Chomsky, and briefly outlines the current theory of fuzzy automata by introducing the basic theory of fuzzy automata. In the study of fuzzy automata, the application of neural network technology is mainly based on the relationship between fuzzy finite state automata, fuzzy grammar and neural network, and by training the related neural networks, we can extract the required automata, and then use the extracted automata to carry out the text. The derivation of the method and the discriminant analysis of the sedimentary environment. The research and application of the fuzzy neural system have already had a certain scale. However, for this paper, it is mainly to study the fuzzy regular grammar derivation algorithm based on neural network and the related problems of the discriminant square method of fuzzy automata. The algorithms for training two order feedback neural networks for extracting fuzzy automata mainly include real time recursive learning algorithm (RTRL) and real coded genetic genetic algorithm (RCGA), but these two algorithms have common faults: time complexity is high, and training speed is very slow. In addition, the two algorithms have different kinds of algorithms for fuzzy finite state automata (FSA) samples. The exception of the class, that is to say, the generalization is very weak. Finally, the RTRL stability is very weak; the RCGA precocious phenomenon often appears. Therefore, this paper gives an improved algorithm for RCGA: Levesbeg-Marguard Genetic Algorithm (LMGA), improves the training speed and solves the problem of precocious. For RTRL algorithm, the seventh chapter gives Levesbeg-Ma The rguard Back Propagation (LMBP) algorithm not only speeds up the training speed, increases the throughput, but also can handle the strings in special cases, such as the super long string. This paper also gives the experimental simulation and verification, and concludes the conclusion of this paper.
【學(xué)位授予單位】：廣東工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：P512.2;TP301.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 周寧;傅鶴林;袁勇;;基于模糊神經(jīng)網(wǎng)絡(luò)的邊坡穩(wěn)定性評(píng)價(jià)方法[J];地下空間與工程學(xué)報(bào);2009年S2期

2 董文娟;朱遠(yuǎn)鑫;萬(wàn)明剛;呂一兵;;沉積環(huán)境判別與分類的Bayes判別分析法[J];成都大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年02期

3 董文娟;朱遠(yuǎn)鑫;萬(wàn)明剛;;基于Fisher判別準(zhǔn)則的沉積環(huán)境判別與分類方法[J];長(zhǎng)江大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年05期

4 薛清太;;低滲透砂巖油藏沉積物粒度分布特征研究[J];沉積學(xué)報(bào);2006年03期

5 張平;宋春暉;楊用彪;高紅山;張紅艷;劉維明;潘美慧;劉平;胡思虎;夏維民;;穩(wěn)定湖相沉積物和風(fēng)成黃土粒度判別函數(shù)的建立及其意義[J];沉積學(xué)報(bào);2008年03期

6 曲政;沉積物粒度數(shù)據(jù)表征方法的研究[J];中國(guó)粉體技術(shù);2001年04期

7 薛新華;姚曉東;;邊坡穩(wěn)定性預(yù)測(cè)的模糊神經(jīng)網(wǎng)絡(luò)模型[J];工程地質(zhì)學(xué)報(bào);2007年01期

8 劉偉;蔡前鳳;;決策模型的神經(jīng)網(wǎng)絡(luò)表示[J];廣東工業(yè)大學(xué)學(xué)報(bào);2007年03期

9 邢�；�;余先川;胡丹;王根霞;;Takagi-Sugeno型分層混合模糊-神經(jīng)網(wǎng)絡(luò)訓(xùn)練算法研究[J];北京師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年04期

10 呂林濤;安婧;;一種自組織雙模糊神經(jīng)網(wǎng)絡(luò)控制算法[J];計(jì)算機(jī)工程與應(yīng)用;2011年17期

相關(guān)碩士學(xué)位論文 前2條

1 張?jiān)婌o;基于詞計(jì)算的Fuzzy有限自動(dòng)機(jī)的最小化問(wèn)題[D];電子科技大學(xué);2007年

2 楊卓東;基于神經(jīng)網(wǎng)絡(luò)的模糊有限狀態(tài)自動(dòng)機(jī)研究[D];電子科技大學(xué);2009年

，

本文編號(hào)：2148419