發(fā)布時(shí)間：2018-06-03 07:02

  本文選題：極限學(xué)習(xí)機(jī) + 游離氧化鈣　； 參考：《湖南大學(xué)》2015年碩士論文

【摘要】：游離氧化鈣(f-CaO)是指水泥熟料中以游離形式存在而沒(méi)有和其他物質(zhì)結(jié)合的氧化鈣,其含量是判斷水泥熟料質(zhì)量的重要指標(biāo)之一。目前大部分水泥廠采用離線方法在實(shí)驗(yàn)室對(duì)f-CaO含量進(jìn)行人工測(cè)量,且每小時(shí)只檢測(cè)一次,影響中控室操作工人對(duì)熟料煅燒工況的及時(shí)判斷和調(diào)節(jié),因此,急需研究一種f-CaO含量的自動(dòng)預(yù)報(bào)方法。但是,由于水泥生產(chǎn)過(guò)程機(jī)理復(fù)雜,且具有大滯后、非線性、強(qiáng)耦合和時(shí)變等特點(diǎn),因此很難建立準(zhǔn)確的機(jī)理模型對(duì)水泥熟料中的f-CaO含量進(jìn)行預(yù)報(bào)。極限學(xué)習(xí)機(jī)是一種基于數(shù)據(jù)驅(qū)動(dòng)的建模方法,是一種改進(jìn)的單隱層前饋神經(jīng)網(wǎng)絡(luò),具有參數(shù)設(shè)置簡(jiǎn)單、學(xué)習(xí)速度快、泛化性能好的優(yōu)點(diǎn),在復(fù)雜過(guò)程建模領(lǐng)域得到了越來(lái)越多的運(yùn)用。本文依托國(guó)家自然科學(xué)基金項(xiàng)目及湖南省自然科學(xué)基金項(xiàng)目,以江西某水泥廠熟料煅燒過(guò)程為具體對(duì)象,研究基于極限學(xué)習(xí)機(jī)的水泥熟料f-CaO含量預(yù)報(bào)方法,具有較高的理論價(jià)值和工程意義。論文完成的主要工作和結(jié)論如下:(1)根據(jù)水泥熟料煅燒過(guò)程中物料的運(yùn)動(dòng)、氣流的運(yùn)動(dòng)和燃料的運(yùn)動(dòng)對(duì)水泥熟料煅燒工藝進(jìn)行了詳細(xì)分析,并介紹了熟料煅燒過(guò)程的重要過(guò)程設(shè)備以及f-CaO含量的人工檢測(cè)方法。(2)基于水泥熟料煅燒工藝機(jī)理,結(jié)合現(xiàn)場(chǎng)的實(shí)際經(jīng)驗(yàn),選取了主機(jī)電流、分解爐溫度和篦冷機(jī)二室風(fēng)壓強(qiáng)三個(gè)易測(cè)量的過(guò)程參數(shù)作為極限學(xué)習(xí)機(jī)的輸入變量,并設(shè)計(jì)了f-CaO含量預(yù)報(bào)極限學(xué)習(xí)機(jī)模型;針對(duì)水泥熟料煅燒過(guò)程時(shí)滯性特點(diǎn),重點(diǎn)研究了極限學(xué)習(xí)機(jī)輸入輸出變量之間時(shí)間匹配的問(wèn)題。(3)在江西某水泥廠采集了一個(gè)多月的現(xiàn)場(chǎng)數(shù)據(jù),包括生料進(jìn)入預(yù)熱器到熟料出篦冷機(jī)之間所有過(guò)程參數(shù)、化驗(yàn)室每個(gè)小時(shí)記錄的f-CaO含量等重要工況數(shù)據(jù)。對(duì)采集的原始數(shù)據(jù)進(jìn)行了預(yù)處理,并且剔除了由于設(shè)備故障等原因產(chǎn)生的異常數(shù)據(jù),獲得720組可靠的訓(xùn)練和測(cè)試樣本集。(4)用MATLAB語(yǔ)言編程實(shí)現(xiàn)了極限學(xué)習(xí)機(jī)對(duì)水泥熟料f-CaO含量的預(yù)報(bào)算法。分別采用訓(xùn)練樣本及測(cè)試樣本對(duì)建立的模型進(jìn)行驗(yàn)證,預(yù)報(bào)的均方誤差分別為0.247和0.196,低于已有文獻(xiàn)報(bào)導(dǎo)中其他算法(BP神經(jīng)網(wǎng)絡(luò)和支持向量機(jī))的均方誤差(0.5左右),效果良好。(5)分析研究了預(yù)測(cè)結(jié)果的影響因素,包括隱層節(jié)點(diǎn)個(gè)數(shù)的選取、不同的數(shù)據(jù)濾波處理算法以及輸入輸出變量之間時(shí)間間隔的選取。分析結(jié)果表明,隱層節(jié)點(diǎn)個(gè)數(shù)設(shè)置為310,對(duì)原始數(shù)據(jù)進(jìn)行5分鐘均值濾波,時(shí)間匹配選取方案C得到的預(yù)測(cè)結(jié)果更好。(6)將ELM模型預(yù)測(cè)結(jié)果與支持向量機(jī)預(yù)測(cè)結(jié)果進(jìn)行了對(duì)比,結(jié)果表明,ELM模型預(yù)測(cè)結(jié)果在最大絕對(duì)誤差、平均絕對(duì)誤差和均方誤差指標(biāo)上均優(yōu)于支持向量機(jī)。
[Abstract]:Free calcium oxide (f-CaO) is a calcium oxide in cement clinker, which is free in the form of free form and is not combined with other substances. Its content is one of the important indexes to judge the quality of cement clinker. At present, most cement plants use off-line method in the laboratory to measure the content of f-CaO in the laboratory, and only once per hour, affecting the control room operation. For workers to judge and adjust the calcining conditions of clinker in time, it is urgent to study an automatic prediction method of f-CaO content. However, it is difficult to establish an accurate mechanism model to predict the content of f-CaO in cement clinker because of the complex mechanism of the cement production process and the characteristics of large lag, nonlinear, strong coupling and time-varying characteristics. The limit learning machine is a data driven modeling method. It is an improved single hidden layer feedforward neural network. It has the advantages of simple parameter setting, fast learning speed and good generalization performance. It has been used more and more in the field of complex process modeling. This paper relies on the National Natural Science Foundation Project and the natural science foundation of Hunan province. The gold project, taking the calcining process of clinker in a cement plant in Jiangxi as the specific object, studies the prediction method of f-CaO content of cement clinker based on extreme learning machine, which has high theoretical value and engineering significance. The main work and conclusion are as follows: (1) according to the movement of material, the movement of air flow and the transportation of fuel in the process of calcining of cement clinker. The process of calcining of cement clinker is analyzed in detail, and the important process equipment of clinker calcination process and the artificial detection method of f-CaO content are introduced. (2) based on the process mechanism of cement clinker calcining and the actual experience of the field, three easy measurement processes are selected, the main current of the host, the temperature of the calciner and the strong pressure of the two chamber air pressure of the grate cooler. The parameter is the input variable of the limit learning machine, and the f-CaO content prediction limit learning machine model is designed. According to the time delay characteristic of the calcining process of cement clinker, the problem of time matching between the input and output variables of the limit learning machine is studied. (3) a month's field data is collected in a cement plant in Jiangxi, including the entry of raw material. The data of all process parameters between the heater to the clinker grate cooler and the f-CaO content recorded in the laboratory per hour. Preprocessing the collected raw data and eliminating the abnormal data caused by equipment failure. 720 groups of reliable training and test samples are obtained. (4) programming by MATLAB language The prediction algorithm for the f-CaO content of cement clinker by the limit learning machine is verified by training samples and test samples respectively. The mean square error of the prediction is 0.247 and 0.196 respectively, which is lower than the mean square error (about 0.5) of other algorithms in the literature (BP neural network and support vector machine), and the effect is good. (5) analysis and research. The factors affecting the prediction results, including the selection of the number of hidden layer nodes, the different data filtering algorithms and the selection of the time interval between the input and output variables, show that the number of nodes of the hidden layer is set to 310, the mean value of the original data is 5 minutes, and the time matching selection scheme C is better. (6 Compared with the prediction results of the ELM model and the support vector machine, the results show that the prediction results of the ELM model are better than the support vector machines in the maximum absolute error, the mean absolute error and the mean square error index.
【學(xué)位授予單位】：湖南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：TQ172.6;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 蔡鑫;馬永亮;;水泥預(yù)分解爐內(nèi)流場(chǎng)及溫度場(chǎng)的數(shù)值模擬[J];環(huán)境工程學(xué)報(bào);2014年10期

2 李洪林;;基于BP神經(jīng)網(wǎng)絡(luò)的熟料fCaO指標(biāo)預(yù)測(cè)[J];新世紀(jì)水泥導(dǎo)報(bào);2014年04期

3 王瑩瑩;;游離氧化鈣含量對(duì)水泥安定性和強(qiáng)度的影響[J];福建建材;2012年10期

4 陳文仲;王春華;田遠(yuǎn)航;王立軍;;回轉(zhuǎn)窯熱工狀況影響參數(shù)的數(shù)值模擬[J];化工學(xué)報(bào);2011年01期

5 顧幸生;潘曄;盧勝利;;基于改進(jìn)支持向量機(jī)的作物葉水勢(shì)軟測(cè)量建模[J];同濟(jì)大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年11期

6 樓波;羅玉和;;回轉(zhuǎn)窯內(nèi)生物質(zhì)高溫空氣燃燒過(guò)程數(shù)值模擬[J];太陽(yáng)能學(xué)報(bào);2010年09期

7 王春華;陳文仲;賈馮睿;田遠(yuǎn)航;劉裕;;回轉(zhuǎn)窯內(nèi)傳熱及燃燒過(guò)程的數(shù)值模擬[J];化工學(xué)報(bào);2010年06期

8 畢文彥;管學(xué)茂;邢鋒;劉小星;王歡;;水泥礦物游離氧化鈣含量測(cè)定方法的評(píng)價(jià)及探討[J];混凝土;2008年12期

9 劉文光;王孝紅;于宏亮;吳敬建;;基于LS-SVM的水泥熟料煅燒過(guò)程f-CaO軟測(cè)量研究[J];控制工程;2008年S2期

10 李坤;翟剛;;游離氧化鈣的測(cè)定誤差分析[J];水泥;2007年11期

相關(guān)博士學(xué)位論文 前2條

1 陳思維;窯尾預(yù)分解系統(tǒng)冷模流場(chǎng)研究[D];武漢理工大學(xué);2005年

2 楊力遠(yuǎn);預(yù)分解窯煅燒過(guò)程計(jì)算機(jī)模擬[D];武漢理工大學(xué);2004年

相關(guān)碩士學(xué)位論文 前1條

1 周生健;回轉(zhuǎn)窯物料運(yùn)動(dòng)特征信息及其測(cè)量[D];湖南大學(xué);2010年

，

本文編號(hào)：1971918