發(fā)布時(shí)間：2018-04-23 10:01

  本文選題：神經(jīng)網(wǎng)絡(luò) + SCR脫硝　； 參考：《華北電力大學(xué)》2017年碩士論文

【摘要】：隨著社會(huì)的發(fā)展,環(huán)境面臨著嚴(yán)峻的問題,大氣污染作為環(huán)境問題的一部分也越來越受關(guān)注,燃煤發(fā)電作為我國的主要電力來源,這在短期內(nèi)是無法改變的事實(shí)。因?yàn)榈趸锸窃斐纱髿馕廴镜闹饕蛩刂?所以國家對(duì)氮氧化物排放量的標(biāo)準(zhǔn)也更加嚴(yán)厲。因此,如何經(jīng)濟(jì)有效的降低燃煤機(jī)組氮氧化物排放已經(jīng)刻不容緩。SCR脫硝技術(shù)是目前國內(nèi)燃煤機(jī)組應(yīng)用最為廣泛的脫硝方法,因此,對(duì)SCR脫硝過程進(jìn)行建模及控制具有一定的研究意義。SCR脫硝過程是一個(gè)大滯后、大慣性、非線性且容易受很多因素?cái)_動(dòng)的復(fù)雜過程,因此采用傳統(tǒng)的建模方法對(duì)其建模是很困難的�；贐P神經(jīng)網(wǎng)絡(luò)具有的高度自學(xué)習(xí)自適應(yīng)能力,適用于非線性系統(tǒng)以及具有一定的容錯(cuò)能力,這些特點(diǎn)使其特別適合求解內(nèi)部機(jī)制復(fù)雜的問題。因此本文采用BP神經(jīng)網(wǎng)絡(luò)建模方法對(duì)SCR脫硝過程進(jìn)行建模,然后根據(jù)建立好的模型,采用神經(jīng)網(wǎng)絡(luò)自適應(yīng)控制來實(shí)現(xiàn)對(duì)SCR出口氮氧化物濃度的控制。本文首先介紹了課題的研究背景及意義還有神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)、算法及建模步驟,然后對(duì)SCR脫硝過程進(jìn)行機(jī)理分析,分析影響出口煙氣濃度的影響因素。確定輸入輸出變量,根據(jù)采集某燃煤電廠600MW機(jī)組所配備的SCR脫硝系統(tǒng)的現(xiàn)場(chǎng)數(shù)據(jù)為基礎(chǔ),先對(duì)數(shù)據(jù)進(jìn)行選取和預(yù)處理,再選取合適的神經(jīng)網(wǎng)絡(luò)模型結(jié)構(gòu)和參數(shù),對(duì)模型進(jìn)行訓(xùn)練。然后采集一部分現(xiàn)場(chǎng)數(shù)據(jù)對(duì)模型的準(zhǔn)確性進(jìn)行驗(yàn)證,結(jié)果證明誤差在可接受的范圍內(nèi),這時(shí)基于SCR脫硝過程的BP神經(jīng)網(wǎng)絡(luò)模型建立完成。所建立的BP神經(jīng)網(wǎng)絡(luò)模型能正確的反映脫硝系統(tǒng)的動(dòng)態(tài)特性。最后把建立好的BP神經(jīng)網(wǎng)絡(luò)模型作為被控對(duì)象,采用了神經(jīng)網(wǎng)絡(luò)模型參考自適應(yīng)控制的方法,來實(shí)現(xiàn)對(duì)SCR脫硝過程出口NOx濃度的控制。利用BP神經(jīng)網(wǎng)絡(luò)作為控制器,通過不斷修改神經(jīng)網(wǎng)絡(luò)的權(quán)值來減小被控對(duì)象輸出與參考模型輸出之間的差值,使被控對(duì)象的輸出能快速的響應(yīng)參考模型的輸出,最終使得控制達(dá)到理想的要求。仿真結(jié)果表明,出口NOx濃度具有良好的響應(yīng)特性,說明這種控制方案是可行的,為其在實(shí)際的應(yīng)用打下了基礎(chǔ)。
[Abstract]:With the development of society, the environment is faced with severe problems, air pollution as a part of the environmental problem is more and more concerned, coal-fired power generation as the main source of power in China, this is a fact that can not be changed in the short term. Because nitrogen oxides are one of the main causes of air pollution, national standards for nitrogen oxides emissions are more stringent. Therefore, how to reduce NOx emission of coal-fired units economically and effectively is the most widely used denitrification method in China. The modeling and control of SCR denitrification process has certain significance. SCR denitrification process is a complex process with large lag, large inertia, nonlinear and easily disturbed by many factors. Therefore, it is very difficult to use the traditional modeling method to model it. Based on the high self-learning adaptive ability of BP neural network, it is suitable for nonlinear systems and has certain fault-tolerant ability, which makes it especially suitable for solving complex problems with internal mechanism. In this paper, BP neural network modeling method is used to model the denitrification process of SCR, and then according to the established model, neural network adaptive control is used to realize the control of nitrogen oxide concentration at the outlet of SCR. In this paper, the background and significance of the research are introduced, and the structure, algorithm and modeling steps of neural network are also introduced. Then, the mechanism of SCR denitrification process is analyzed, and the influencing factors of flue gas concentration at outlet are analyzed. The input and output variables are determined. Based on the field data of the SCR denitrification system equipped with the 600MW unit in a coal-fired power plant, the data are selected and preprocessed first, and then the appropriate neural network model structure and parameters are selected. Train the model. Then some field data are collected to verify the accuracy of the model. The results show that the error is within the acceptable range. Then the BP neural network model based on SCR denitrification process is established. The BP neural network model can accurately reflect the dynamic characteristics of denitrification system. Finally, the BP neural network model is taken as the controlled object, and the neural network model reference adaptive control method is adopted to control the NOx concentration at the outlet of SCR denitrification process. BP neural network is used as the controller to reduce the difference between the output of the controlled object and the output of the reference model by constantly modifying the weights of the neural network, so that the output of the controlled object can respond to the output of the reference model quickly. Ultimately, the control meets the desired requirements. The simulation results show that the outlet NOx concentration has good response characteristics, which shows that this control scheme is feasible and lays a foundation for its practical application.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP183;TM621.8

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張敏;徐啟華;;基于改進(jìn)BP的神經(jīng)網(wǎng)絡(luò)模型參考自適應(yīng)控制[J];軟件;2015年07期

2 李健勇;趙峰;丁青青;;基于模型參考自適應(yīng)的網(wǎng)絡(luò)控制系統(tǒng)隨機(jī)時(shí)延補(bǔ)償[J];鄭州大學(xué)學(xué)報(bào)(工學(xué)版);2015年04期

3 馮連臣;王章生;;國內(nèi)燃煤機(jī)組脫硝技術(shù)發(fā)展現(xiàn)狀及建議[J];電源技術(shù)應(yīng)用;2013年03期

4 柳小桐;;BP神經(jīng)網(wǎng)絡(luò)輸入層數(shù)據(jù)歸一化研究[J];機(jī)械工程與自動(dòng)化;2010年03期

5 秦富童;岳麗華;萬壽紅;;應(yīng)用BP神經(jīng)網(wǎng)絡(luò)的目標(biāo)識(shí)別效果評(píng)估[J];計(jì)算機(jī)工程與應(yīng)用;2010年05期

6 林建勇;;選擇性催化還原脫硝工藝及控制系統(tǒng)[J];太原科技;2007年09期

7 馬忠云;檀國彪;;燃煤鍋爐煙氣脫硝(SCR法)工藝及特性[J];節(jié)能與環(huán)保;2006年02期

8 賈雙燕,路濤,李曉蕓,寧獻(xiàn)武;選擇性催化還原煙氣脫硝技術(shù)及其在我國的應(yīng)用研究[J];電力環(huán)境保護(hù);2004年01期

9 張秀玲,高美靜,谷芳春;新型神經(jīng)網(wǎng)絡(luò)模型參考自適應(yīng)控制系統(tǒng)設(shè)計(jì)[J];系統(tǒng)工程學(xué)報(bào);2003年02期

10 張德賢;前向神經(jīng)網(wǎng)絡(luò)合理隱含層結(jié)點(diǎn)個(gè)數(shù)估計(jì)[J];計(jì)算機(jī)工程與應(yīng)用;2003年05期

相關(guān)會(huì)議論文 前2條

1 樸世揚(yáng);楊煜普;;一種基于神經(jīng)網(wǎng)絡(luò)的非線性模型參考自適應(yīng)控制方法[A];中國計(jì)量協(xié)會(huì)冶金分會(huì)2015年會(huì)論文集[C];2015年

2 李春雨;;我國火電廠SCR煙氣脫硝技術(shù)研究及應(yīng)用現(xiàn)狀分析[A];第十五屆中國科協(xié)年會(huì)第9分會(huì)場(chǎng)：火電廠煙氣凈化與節(jié)能技術(shù)研討會(huì)論文集[C];2013年

相關(guān)博士學(xué)位論文 前2條

1 董建勛;燃煤電廠SCR煙氣脫硝試驗(yàn)研究及數(shù)學(xué)模型建立[D];華北電力大學(xué)（河北）;2007年

2 王俊國;基于神經(jīng)網(wǎng)絡(luò)的建模方法與控制策略研究[D];華中科技大學(xué);2004年

相關(guān)碩士學(xué)位論文 前7條

1 曹宏芳;火電機(jī)組SCR脫硝系統(tǒng)性能監(jiān)測(cè)與優(yōu)化方法的研究[D];華北電力大學(xué);2015年

2 王婷;模型預(yù)測(cè)控制在電廠選擇性催化還原脫硝系統(tǒng)中的應(yīng)用研究[D];浙江大學(xué);2015年

3 王博;基于神經(jīng)網(wǎng)絡(luò)的鍋爐多工況燃燒建模研究[D];華北電力大學(xué);2014年

4 劉莉萍;選擇性催化還原法煙氣脫硝系統(tǒng)的建模與仿真研究[D];華北電力大學(xué);2012年

5 趙敏;基于神經(jīng)網(wǎng)絡(luò)的電廠鍋爐燃燒系統(tǒng)建模及優(yōu)化研究[D];浙江大學(xué);2010年

6 李菲;基于BP神經(jīng)網(wǎng)絡(luò)的字符識(shí)別技術(shù)研究[D];電子科技大學(xué);2009年

7 胡學(xué)聰;SCR法煙氣脫硝數(shù)值模擬及先進(jìn)控制[D];上海交通大學(xué);2009年

，

本文編號(hào)：1791480