本文選題：板形　切入點(diǎn)：閉環(huán)控制　出處：《燕山大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著國民經(jīng)濟(jì)的發(fā)展和現(xiàn)代生活水平的提高,板帶材的需求量在不斷增加,同時(shí)對(duì)板帶材產(chǎn)品質(zhì)量的要求也日益提高。板形是帶鋼的重要質(zhì)量指標(biāo),也是軋制領(lǐng)域研究的熱點(diǎn)。近年來,人工智能方法以其在建模和控制方面的優(yōu)勢(shì),在工業(yè)過程研究中得到了廣泛的應(yīng)用。首先,對(duì)一般的板形閉環(huán)控制的方法進(jìn)行了分類和對(duì)比研究,闡述一般控制方法的原理和提出存在的問題和不足。其次,建立機(jī)理板形預(yù)報(bào)模型。為了分析各種板形調(diào)控手段和帶鋼來料情況對(duì)板形影響矩陣的影響規(guī)律,基于輥系彈性變形和金屬模型相互耦合原理建立了板形機(jī)理預(yù)報(bào)模型,以1050六輥軋機(jī)為例,在此模型基礎(chǔ)上計(jì)算機(jī)理方法影響矩陣,為板形在線控制模型的建立實(shí)現(xiàn)提供了理論依據(jù)。然后,建立智能板形預(yù)報(bào)模型。針對(duì)傳統(tǒng)板形預(yù)報(bào)模型中采用的神經(jīng)網(wǎng)絡(luò)參數(shù)設(shè)置復(fù)雜,訓(xùn)練時(shí)間長,易陷入局部最小值缺點(diǎn),引用極限學(xué)習(xí)機(jī)(ELM,extreme learning machine)人工神經(jīng)網(wǎng)絡(luò)用于板形預(yù)測(cè),考慮到隨機(jī)輸入權(quán)值與偏置值對(duì)神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)精度的影響,采用差分進(jìn)化算法(DE,Differential Evolution)優(yōu)化ELM神經(jīng)網(wǎng)絡(luò),建立DE-ELM板形智能預(yù)測(cè)模型,在此模型基礎(chǔ)上計(jì)算智能方法影響矩陣。最后,建立機(jī)理和智能加權(quán)綜合影響矩陣控制模型。既發(fā)揮了機(jī)理模型的對(duì)軋制規(guī)律的把控,又利用智能模型對(duì)機(jī)理模型智能動(dòng)態(tài)的修正,于是建立了機(jī)理-智能加權(quán)影響矩陣控制模型,并且在1050六輥軋機(jī)上進(jìn)行了仿真,結(jié)果充分驗(yàn)證了本文提出的板形控制的動(dòng)態(tài)影響矩陣法的有效性。
[Abstract]:With the development of national economy and the improvement of modern living standard, the demand for strip material is increasing, and the demand for product quality is also increasing. In recent years, artificial intelligence (AI) has been widely used in industrial process research because of its advantages in modeling and control. This paper classifies and contrasts the general method of shape closed loop control, expounds the principle of the general control method and puts forward the existing problems and shortcomings. Secondly, In order to analyze the influence of various shape control methods and strip feed on shape matrix, the prediction model of shape mechanism is established based on the coupling principle of roll elastic deformation and metal model. Taking the 1050 six-high rolling mill as an example, the influence matrix of computer method is based on the model, which provides the theoretical basis for the establishment and realization of the on-line control model of flatness. The intelligent shape prediction model is established. The neural network used in the traditional shape prediction model is complex in setting, long training time and easy to fall into the defect of local minimum value. The artificial neural network of extreme learning machine (ELM) extreme learning machine is used to predict the shape of shape. Considering the influence of random input weights and bias values on the prediction accuracy of neural networks, the differential evolution algorithm is used to optimize ELM neural networks, and an intelligent prediction model of DE-ELM flatness is established. Based on this model, the influence matrix of intelligent methods is calculated. The mechanism and intelligent weighted comprehensive influence matrix control model is established, which not only controls the rolling law of the mechanism model, but also uses the intelligent model to modify the intelligent dynamic of the mechanism model. A mechanism-intelligent weighted influence matrix control model is established and simulated on 1050 six-high rolling mill. The results fully verify the effectiveness of the dynamic influence matrix method proposed in this paper for shape control.
【學(xué)位授予單位】：燕山大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TG334.9

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 劉建昌,王柱;基于神經(jīng)網(wǎng)絡(luò)模式識(shí)別的板形模糊控制器[J];東北大學(xué)學(xué)報(bào);2005年08期

2 王秀梅,王國棟,劉相華;模糊控制在帶鋼軋制中的應(yīng)用[J];鋼鐵研究;1999年03期

3 何海濤;李楠;;基于SVM的改進(jìn)RBF網(wǎng)絡(luò)板形模式識(shí)別方法[J];自動(dòng)化儀表;2007年05期

4 何海濤;張?zhí)m;薛玉琦;李艷;田霞;;一種基于聚類的板形控制模糊神經(jīng)網(wǎng)絡(luò)模型[J];重型機(jī)械;2008年02期

5 王杰;畢浩洋;;一種基于粒子群優(yōu)化的極限學(xué)習(xí)機(jī)[J];鄭州大學(xué)學(xué)報(bào)(理學(xué)版);2013年01期

相關(guān)博士學(xué)位論文 前2條

1 何海濤;寬帶鋼冷軋機(jī)板形在線控制智能模型的研究與應(yīng)用[D];燕山大學(xué);2005年

2 李志明;整輥鑲塊式板形儀信號(hào)處理及板形閉環(huán)控制方法研究[D];燕山大學(xué);2012年

相關(guān)碩士學(xué)位論文 前3條

1 周會(huì)鋒;板形識(shí)別·預(yù)測(cè)和控制仿真的智能方法研究[D];燕山大學(xué);2005年

2 李楠;板形模式識(shí)別與控制的智能方法研究[D];燕山大學(xué);2006年

3 左弟俊;極速學(xué)習(xí)理論與應(yīng)用研究[D];西安電子科技大學(xué);2012年

，

本文編號(hào)：1650465