本文關(guān)鍵詞：基于神經(jīng)網(wǎng)絡(luò)的多模型自適應(yīng)控制方法研究　出處：《北京科技大學(xué)》2017年博士論文　論文類(lèi)型：學(xué)位論文

  更多相關(guān)文章： 神經(jīng)網(wǎng)絡(luò) 多模型 非線性系統(tǒng) 自適應(yīng)控制

【摘要】：隨著經(jīng)濟(jì)的快速發(fā)展科技的進(jìn)步,生產(chǎn)制造過(guò)程逐漸變得復(fù)雜多變,生產(chǎn)工況環(huán)境也越來(lái)越多樣化,這就對(duì)控制品質(zhì)提出了新的嚴(yán)格要求。在某些實(shí)際控制過(guò)程中,一些偶然突發(fā)情況(如某一個(gè)零件磨損或突然脫落),都將使被控對(duì)象的模型瞬間發(fā)生劇烈變化。傳統(tǒng)自適應(yīng)控制方法針對(duì)的被控對(duì)象通常是基于一個(gè)參數(shù)不變或緩慢變化的模型,操作環(huán)境是時(shí)不變或慢時(shí)變的。然而在諸如零部件失靈,以及一些意想不到的故障發(fā)生時(shí),系統(tǒng)動(dòng)力學(xué)模型將發(fā)生突變。對(duì)于系統(tǒng)的突發(fā)性變化,瞬態(tài)誤差往往很大,傳統(tǒng)的自適應(yīng)控制算法收斂速度很低,控制效果往往表現(xiàn)不佳。多模型自適應(yīng)控制被視為是解決上述問(wèn)題最行之有效的方法,該方法的核心要點(diǎn)是:根據(jù)被控對(duì)象有可能存在的不同工作點(diǎn),構(gòu)建含有多個(gè)模型的模型集合覆蓋被控對(duì)象的不確定性;根據(jù)模型集合內(nèi)每一個(gè)模型設(shè)計(jì)相對(duì)應(yīng)的控制器,進(jìn)而形成控制器集;依據(jù)每個(gè)模型與被控對(duì)象之間的辨識(shí)誤差,設(shè)計(jì)基于此誤差的切換準(zhǔn)則。一旦被控系統(tǒng)參數(shù)發(fā)生變化,根據(jù)切換準(zhǔn)則,系統(tǒng)會(huì)從模型集中選擇最接近當(dāng)前被控系統(tǒng)的模型,并將控制器切換到該模型的控制器上�；诖怂枷�,本文重點(diǎn)針對(duì)實(shí)際生產(chǎn)過(guò)程中的大量非線性系統(tǒng),建立基于神經(jīng)網(wǎng)絡(luò)的多模型自適應(yīng)控制器,在被控對(duì)象不同的工作點(diǎn)處,建立多個(gè)模型,將被控對(duì)象參數(shù)的不確定性轉(zhuǎn)化為神經(jīng)網(wǎng)絡(luò)模型權(quán)值的不同。主要研究成果如下:1.基于動(dòng)態(tài)神經(jīng)網(wǎng)絡(luò)(Dynamic Neural Networks),分別從動(dòng)態(tài)神經(jīng)網(wǎng)絡(luò)的兩種典型結(jié)構(gòu):并行結(jié)構(gòu)和串并結(jié)構(gòu)兩種形式出發(fā),考慮系統(tǒng)的有無(wú)未建模動(dòng)態(tài)情況,建立了多個(gè)動(dòng)態(tài)神經(jīng)網(wǎng)絡(luò)辨識(shí)模型(自適應(yīng)模型、固定模型、重新賦初值自適應(yīng)模型),并對(duì)多種動(dòng)態(tài)神經(jīng)網(wǎng)絡(luò)辨識(shí)模型進(jìn)行組合,構(gòu)建了多種動(dòng)態(tài)神經(jīng)網(wǎng)絡(luò)組合下的模型集、控制器集以及相應(yīng)的切換準(zhǔn)則,給出了多種組合下控制效果的對(duì)比。同時(shí)給出了系統(tǒng)的穩(wěn)定性和切換穩(wěn)定性的證明。2.基于靜態(tài)神經(jīng)網(wǎng)絡(luò),提出了基于OS-ELM(On-line Sequence Extreme Learning Machine)神經(jīng)網(wǎng)絡(luò)的多模型自適應(yīng)控制。給出了基于OS-ELM神經(jīng)網(wǎng)絡(luò)的模型集、控制器集及切換準(zhǔn)則,同時(shí)給出了系統(tǒng)的穩(wěn)定性和切換穩(wěn)定性證明。3.基于 OS-ELM 和 EM-ELM(Error Minimum Extreme Learning Machine)神經(jīng)網(wǎng)絡(luò),提出了一種自組織神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)即OEM-ELM(On-line Error Minimum Extreme Learning Machine)神經(jīng)網(wǎng)絡(luò)。OEM-ELM 算法的核心思想是:在線學(xué)習(xí)、網(wǎng)絡(luò)性能評(píng)價(jià)、動(dòng)態(tài)增加隱層節(jié)點(diǎn)數(shù)。它將OS-ELM和EM-ELM的優(yōu)點(diǎn)相結(jié)合,既提高了網(wǎng)絡(luò)的辨識(shí)能力又避免了網(wǎng)絡(luò)節(jié)點(diǎn)的冗余。給出了基于OEM-ELM神經(jīng)網(wǎng)絡(luò)自適應(yīng)控制的應(yīng)用,同時(shí)分析了節(jié)點(diǎn)變化對(duì)系統(tǒng)的影響。4.在鋼鐵廢渣循環(huán)利用礦渣微粉生產(chǎn)系統(tǒng)中,將本文的研究成果進(jìn)行應(yīng)用。分析了礦渣微粉的生產(chǎn)工藝流程,梳理了影響礦渣微粉比表面積、磨內(nèi)壓差的關(guān)鍵因素。由于實(shí)際驗(yàn)證的局限性,本文基于現(xiàn)場(chǎng)采集的大量實(shí)際生產(chǎn)數(shù)據(jù)建立組涵蓋多個(gè)工況的動(dòng)態(tài)神經(jīng)網(wǎng)絡(luò)模型作為生產(chǎn)運(yùn)行環(huán)境�；诖松a(chǎn)運(yùn)行環(huán)境,構(gòu)建了一種基于OEM-ELM神經(jīng)網(wǎng)絡(luò)自適應(yīng)控制器,在測(cè)試驗(yàn)證環(huán)境中進(jìn)一步驗(yàn)證本文提出算法的有效性。
[Abstract]:With the rapid development of economy and the progress of technology, the manufacturing process becomes complicated, production environment is becoming more and more diversified, the quality control strictly required new. In some actual control process, some accidental contingencies (such as some parts wear or suddenly fall off), will make the object the model of controlled moment change dramatically. The traditional adaptive control method for the controlled object is usually based on a constant or slowly changing parameters of the model, the operating environment is time invariant or slowly time-varying. However, such as zero component failures, and some unexpected failures, the system dynamics model for the burst will change. The change of the system, the transient error is often large, the convergence speed of the traditional adaptive control algorithm is very low, the control effect is often poor performance. Multi model adaptive control As is the most effective way to solve the above problems, the core point of this method is: according to the object may have different working points, constructing a set covering the uncertainty of the controlled object with multiple model controller; according to the model set in each model is designed correspondingly, and the formation of controller basis; the identification error between each model and object design, the error based on the switching rule. Once the parameters of the controlled system change, according to a switching rule, the system will choose the most close to the current control system model from the model, and the controller is switched to the controller model. Based on this idea, this paper focuses on the nonlinear the system in actual production process, establish a multiple model adaptive controller based on neural network, the object in different work point, build multiple models, The object parameter uncertainty into the neural network model of different weights. The main research results are as follows: 1. based on dynamic neural network (Dynamic Neural Networks), respectively from the two kinds of typical structure of dynamic neural network: parallel structure and string and the structure of two forms of the system without considering unmodeled dynamics. To establish a number of dynamic neural network model (adaptive model, fixed model, rein itialized model), and the combination of a variety of dynamic neural network model, constructed a combination of dynamic neural network model set, the controller set and the corresponding switching rule, contrast gives the effect of a variety of combinations under control. At the same time proved the stability and stability of the system of the.2. static switch based on neural network is proposed based on OS-ELM (On-line Sequence Extreme Learning Machine) Multi model adaptive neural network control is presented. The OS-ELM neural network model based on set, controller and switching criterion, and the stability and stability of switching system prove that the OS-ELM and.3. based on EM-ELM (Error Minimum Extreme Learning Machine) neural network, a self-organizing neural network structure which is OEM-ELM (On-line Error Minimum Extreme Learning Machine) the core idea of.OEM-ELM algorithm of neural network is: online learning, network performance evaluation, the dynamic increase of the number of hidden nodes. The advantages of OS-ELM and EM-ELM combination, the identification ability of the network is improve and avoid redundant network nodes. The application of OEM-ELM neural network based on adaptive control is given. At the same time, analysis of the node changes the influence on the system of.4. in iron and steel slag recycling slag powder production system, this paper will research into The fruit of the application. Analyzed the production process of slag powder, analyzes the impact of slag powder specific surface area, the key factors in the grinding pressure. Due to the limitation of the actual verification, the large number of actual production data collected based on the dynamic conditions of God Group covers a number of the network as a production environment. This based on the production environment, to construct a neural network OEM-ELM controller based on adaptive, further verify the effectiveness of the proposed algorithm in the test environment.

【學(xué)位授予單位】：北京科技大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP273.2;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王康;李曉理;賈超;宋桂芝;;基于自適應(yīng)動(dòng)態(tài)規(guī)劃的礦渣微粉生產(chǎn)過(guò)程跟蹤控制[J];自動(dòng)化學(xué)報(bào);2016年10期

2 陳杰;陳偉;孫健;;多模型自適應(yīng)控制研究概述[J];系統(tǒng)科學(xué)與數(shù)學(xué);2014年12期

3 張維存;;參數(shù)不確定離散隨機(jī)系統(tǒng)的加權(quán)多模型自適應(yīng)控制[J];自動(dòng)化學(xué)報(bào);2015年03期

4 李曉理;劉德馨;賈超;丁大偉;;基于自適應(yīng)動(dòng)態(tài)規(guī)劃的多設(shè)定值跟蹤控制方法[J];控制理論與應(yīng)用;2013年06期

5 劉德馨;李曉理;丁大偉;陳先中;;基于雷達(dá)觀測(cè)數(shù)據(jù)的高爐料面多模型控制[J];控制理論與應(yīng)用;2012年10期

6 李曉理;石隴輝;丁大偉;;水箱液位系統(tǒng)多模型控制方法[J];控制理論與應(yīng)用;2011年03期

7 董志坤;王昕;王笑波;李少遠(yuǎn);鄭益慧;;多模型加權(quán)自適應(yīng)控制在中厚板層流冷卻系統(tǒng)中的應(yīng)用(英文)[J];自動(dòng)化學(xué)報(bào);2010年08期

8 劉圣照;劉家祥;郭麗杰;;渦流空氣分級(jí)機(jī)理論切割粒徑計(jì)算的研究[J];有色礦冶;2006年S1期

9 李曉理;張維存;王偉;;基于有界擾動(dòng)分區(qū)的多模型自適應(yīng)控制[J];控制理論與應(yīng)用;2006年02期

10 李曉理,王書(shū)寧;含有界擾動(dòng)系統(tǒng)的多模型自適應(yīng)控制[J];控制理論與應(yīng)用;2003年04期

相關(guān)博士學(xué)位論文 前2條

1 滿紅;CSTR過(guò)程的模型辨識(shí)及其非線性預(yù)測(cè)控制方法研究[D];大連理工大學(xué);2014年

2 孫亞忠;大型立磨特性數(shù)值分析方法及應(yīng)用[D];武漢理工大學(xué);2011年

相關(guān)碩士學(xué)位論文 前1條

1 王維;連續(xù)攪拌反應(yīng)釜（CSTR）控制方法研究[D];北京交通大學(xué);2013年

，

本文編號(hào)：1393410