本文關(guān)鍵詞： 碳纖維凝固過(guò)程 動(dòng)態(tài)數(shù)據(jù)建模 免疫優(yōu)化 滑動(dòng)窗口 多核支持向量機(jī)　出處：《東華大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：碳纖維復(fù)合材料是一種力學(xué)性能優(yōu)異的新材料,它具有強(qiáng)度高,模量大,密度小等特點(diǎn),同時(shí)還具有較高的比強(qiáng)度和很高的比模量。由于碳纖維優(yōu)異的性能與廣泛的應(yīng)用,其紡絲凝固過(guò)程也便備受?chē)?guó)內(nèi)外學(xué)者的關(guān)注。目前國(guó)內(nèi)外對(duì)碳纖維凝固過(guò)程的研究大多停留在機(jī)理建模層面,采用數(shù)據(jù)建模的相對(duì)較少,尤其對(duì)凝固過(guò)程中的動(dòng)態(tài)變化進(jìn)行動(dòng)態(tài)數(shù)據(jù)建模更是少有涉及。近幾年,隨著統(tǒng)計(jì)學(xué)習(xí)與機(jī)器學(xué)習(xí)的興起,如何利用數(shù)據(jù),建立更加高效的模型成為非常必要的研究課題。本文利用碳纖維凝固過(guò)程中多項(xiàng)指標(biāo)的動(dòng)態(tài)數(shù)據(jù),充分結(jié)合纖維凝固成形的機(jī)理,設(shè)計(jì)了高效、準(zhǔn)確的動(dòng)態(tài)數(shù)據(jù)模型,進(jìn)行準(zhǔn)確、穩(wěn)定的凝固過(guò)程濃度預(yù)測(cè),從而可以實(shí)時(shí)地幫助提高碳纖維原絲生產(chǎn)的產(chǎn)品性能。本論文的主要貢獻(xiàn)如下:(1)分析了碳纖維凝固過(guò)程中的各項(xiàng)參數(shù)指標(biāo)的數(shù)據(jù)特征以及它們之間的相關(guān)關(guān)系,針對(duì)原絲內(nèi)部溶劑濃度變化的數(shù)據(jù)特征多樣性問(wèn)題,提出了一種多核支持向量機(jī)數(shù)據(jù)模型(MKSVM)。相比于采用單核的傳統(tǒng)支持向量機(jī)模型,MKSVM更加適用于具有多樣數(shù)據(jù)特征的纖維內(nèi)部溶劑濃度變化。仿真對(duì)比實(shí)驗(yàn)結(jié)果進(jìn)一步證明所建立的模型的準(zhǔn)確性和優(yōu)越性。(2)碳纖維的凝固過(guò)程是一個(gè)隨時(shí)間連續(xù)變化的動(dòng)態(tài)過(guò)程,本論文對(duì)凝固過(guò)程中的各項(xiàng)動(dòng)態(tài)數(shù)據(jù)進(jìn)行聚類(lèi)分析,利用聚類(lèi)結(jié)果訓(xùn)練出核矩陣切換機(jī)(KSM),核矩陣切換機(jī)可以在每次窗口滑動(dòng)時(shí)候,根據(jù)當(dāng)前載入到窗口的數(shù)據(jù),判斷該組數(shù)據(jù)的類(lèi)別,然后將核矩陣切換到最佳,這里提到的核矩陣是MKSVM利用類(lèi)別中心的數(shù)據(jù)訓(xùn)練而得。接著,引入滑動(dòng)窗口理論,提出了一種基于滑動(dòng)窗口多核支持向量機(jī)的動(dòng)態(tài)數(shù)據(jù)模型(SWMKSVM)。實(shí)驗(yàn)結(jié)果表明,在凝固過(guò)程的動(dòng)態(tài)變化中,該模型仍然保持了令人滿(mǎn)意的準(zhǔn)確性。(3)為了使得動(dòng)態(tài)模型在整個(gè)動(dòng)態(tài)過(guò)程中的效果達(dá)到最優(yōu),本論文使用免疫算法優(yōu)化SWMKSVM的參數(shù),提出了一種免疫滑動(dòng)優(yōu)化多核支持向量機(jī)模型(ISAMKSVM),利用免疫算法的尋優(yōu)機(jī)制,確�？焖俣行У貙ふ业饺肿顑�(yōu)解,保證了滑窗在整個(gè)滑動(dòng)過(guò)程中的整體最優(yōu),而不僅僅是是每次滑動(dòng)的最優(yōu),并且相比采用傳統(tǒng)方式優(yōu)化核權(quán)重系數(shù),可以明顯提高效率。經(jīng)實(shí)驗(yàn)仿真測(cè)試表明,利用ISAMKSVM的動(dòng)態(tài)數(shù)據(jù)模型時(shí),與傳統(tǒng)粒子群優(yōu)化參數(shù)方法的模型相比較,該模型能夠快速而有效地尋找到最優(yōu)參數(shù),而且算法穩(wěn)定性強(qiáng),在模型準(zhǔn)確率方面有明顯的優(yōu)勢(shì)。最后,對(duì)全論文的研究工作進(jìn)行了總結(jié),指出了工作中存在的不足,并對(duì)有待進(jìn)一步研究的方向和方法進(jìn)行了展望。
[Abstract]:Carbon fiber composite is a new material with excellent mechanical properties. It has the characteristics of high strength, high modulus and low density, and also has high specific strength and high specific modulus. At present, most of the researches on the solidification process of carbon fiber stay at the level of mechanism modeling, and the data modeling is relatively few. In recent years, with the rise of statistical learning and machine learning, how to use data, It is necessary to establish a more efficient model. Based on the dynamic data of many indexes in the process of carbon fiber solidification and the mechanism of fiber solidification forming, an efficient and accurate dynamic data model is designed in this paper. Accurate and stable concentration prediction of solidification process, The main contribution of this paper is as follows: 1) the main contribution of this paper is to analyze the data characteristics of the parameters during the solidification process of carbon fiber and the correlation between them. Aiming at the diversity of the data characteristics of solvent concentration change in the filament, A multi-core support vector machine data model (MKSVMN) is proposed. Compared with the traditional support vector machine (SVM) model with single core, MKSVM is more suitable for the change of solvent concentration in fibers with various data characteristics. The simulation results are compared with the experimental results. It is proved that the solidification process of the carbon fiber is a dynamic process with continuous change over time. In this paper, the dynamic data in solidification process are analyzed, and the kernel matrix switching machine is trained by clustering results. The kernel matrix switching machine can load the data to the window according to the data loaded into the window every time the window slips. Determine the category of the group of data, then switch the kernel matrix to the best. The kernel matrix mentioned here is trained by MKSVM using the data from the class center. Then, the sliding window theory is introduced. A dynamic data model based on sliding window multi-core support vector machine (SVM) is proposed. The experimental results show that, during the dynamic change of solidification process, In order to optimize the effect of the dynamic model in the whole dynamic process, the immune algorithm is used to optimize the parameters of SWMKSVM. An immune sliding optimization multi-kernel support vector machine model (ISAMKSVMM) is proposed. By using the optimization mechanism of the immune algorithm, the global optimal solution is found quickly and effectively, and the overall optimum of the sliding window in the whole sliding process is ensured. It is not only the optimum of each sliding, but also the efficiency can be improved obviously compared with the traditional way of optimizing the kernel weight coefficient. The experimental simulation results show that, when using the dynamic data model of ISAMKSVM, Compared with the traditional Particle Swarm Optimization (PSO) model, the model can find the optimal parameters quickly and effectively, and the algorithm is stable and has obvious advantages in the accuracy of the model. This paper summarizes the research work of the whole paper, points out the shortcomings of the work, and looks forward to the direction and methods to be further studied.
【學(xué)位授予單位】：東華大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TQ342.742;TB332

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 連峰;劉棟;陳秋飛;郭鵬宗;林康;;PAN原絲成形工藝與碳纖維晶體結(jié)構(gòu)和性能的關(guān)聯(lián)性研究[J];高科技纖維與應(yīng)用;2015年03期

2 沈志剛;;國(guó)內(nèi)外碳纖維技術(shù)進(jìn)展[J];玻璃鋼;2012年04期

3 林琳;陳虹;陳建;金煥梅;;基于多核SVM-GMM的短語(yǔ)音說(shuō)話人識(shí)別[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2013年02期

4 萬(wàn)源;童恒慶;朱映映;;基于遺傳算法的多核支持向量機(jī)的參數(shù)優(yōu)化[J];武漢大學(xué)學(xué)報(bào)(理學(xué)版);2012年03期

5 武征鵬;張學(xué)工;;彈性多核學(xué)習(xí)(英文)[J];自動(dòng)化學(xué)報(bào);2011年06期

6 歐陽(yáng)琴;陳友汜;莫高明;黃顯雯;張娜;馬洪波;;聚丙烯腈原絲中粘連的形成與控制[J];高科技纖維與應(yīng)用;2011年02期

7 任_g;梅盛鑫;;基于混合核函數(shù)支持向量機(jī)和遺傳算法的人臉識(shí)別[J];計(jì)算機(jī)應(yīng)用與軟件;2011年04期

8 汪洪橋;孫富春;蔡艷寧;陳寧;丁林閣;;多核學(xué)習(xí)方法[J];自動(dòng)化學(xué)報(bào);2010年08期

9 王s，

本文編號(hào)：1499046