本文選題：神經(jīng)網(wǎng)絡(luò) + 鍋爐燃燒優(yōu)化　； 參考：《北京交通大學(xué)》2014年碩士論文

【摘要】：隨著“節(jié)能減排”政策要求加強(qiáng),在保證安全生產(chǎn)和滿足負(fù)荷需求前提下,應(yīng)努力提高火電廠運(yùn)行效率、降低煤耗,控制并減少污染排放。本文針對(duì)火電廠鍋爐燃燒系統(tǒng)進(jìn)行了基于數(shù)據(jù)驅(qū)動(dòng)的建模和優(yōu)化研究。 本文以中國(guó)華電一300MW機(jī)組為研究對(duì)象,給出了電廠鍋爐的數(shù)據(jù)采集、預(yù)處理、優(yōu)化指標(biāo)選取的步驟和神經(jīng)網(wǎng)絡(luò)穩(wěn)態(tài)建模過(guò)程及其評(píng)價(jià)。以降低單位相對(duì)煤耗和降低氮氧化物(NOx)排放量?jī)烧呒骖欁鰹殄仩t優(yōu)化運(yùn)行的評(píng)價(jià)指標(biāo)。在兩個(gè)典型負(fù)荷處分負(fù)荷點(diǎn)建模。比較了不同的神經(jīng)網(wǎng)絡(luò)建模訓(xùn)練算法的異同并對(duì)其泛化能力進(jìn)行了評(píng)價(jià)。 對(duì)電廠鍋爐運(yùn)行這一非線性動(dòng)態(tài)工業(yè)過(guò)程,討論和研究了在離散狀態(tài)下一種基于數(shù)據(jù)驅(qū)動(dòng)的建模方式,通過(guò)對(duì)鍋爐燃燒過(guò)程的穩(wěn)態(tài)建模和動(dòng)態(tài)建模區(qū)別對(duì)待,給出了穩(wěn)態(tài)和動(dòng)態(tài)相結(jié)合的建模思想。給出了穩(wěn)態(tài)過(guò)程和動(dòng)態(tài)過(guò)程的定義、辨識(shí)方法、增益計(jì)算方法。 在前向神經(jīng)網(wǎng)絡(luò)只能構(gòu)建穩(wěn)態(tài)模型和現(xiàn)場(chǎng)采集得到的數(shù)據(jù)存在動(dòng)態(tài)特性的情況下,給出一種前向神經(jīng)網(wǎng)絡(luò)和一階自回歸模型相結(jié)合的混合模型。一階自回歸模型的存在使該混合模型能夠描述動(dòng)態(tài)特性,并推導(dǎo)出了其訓(xùn)練算法。將該模型運(yùn)用到了火電廠的氮氧化物排放量建模中并對(duì)其建模能力進(jìn)行了評(píng)價(jià)。結(jié)果表明加入的一階自回歸模型能夠使混合模型提高擬合精度,說(shuō)明在氮氧化物的形成過(guò)程中存在動(dòng)態(tài)特性。 最后采用遺傳算法得到了兩個(gè)典型負(fù)荷下的以降低煤耗和降低氮氧化物為目標(biāo)的優(yōu)化結(jié)果,基于神經(jīng)網(wǎng)絡(luò)模型得到了優(yōu)化結(jié)果。并在濾除氮氧化物排放量數(shù)據(jù)中存在的擾動(dòng)后得到了新的優(yōu)化結(jié)果。對(duì)基于不同的模型得到的優(yōu)化結(jié)果進(jìn)行了比較和分析。結(jié)合現(xiàn)場(chǎng)數(shù)據(jù)給出了氮氧化物排放量相對(duì)增益計(jì)算的分析結(jié)果。利用數(shù)據(jù)庫(kù)和動(dòng)態(tài)網(wǎng)頁(yè)技術(shù)制作了優(yōu)化結(jié)果發(fā)布的動(dòng)態(tài)網(wǎng)頁(yè),用以指導(dǎo)電廠機(jī)組人員對(duì)機(jī)組進(jìn)行優(yōu)化運(yùn)行。
[Abstract]:With the strengthening of "energy saving and emission reduction" policy, under the premise of ensuring safe production and satisfying load demand, it is necessary to improve the operation efficiency of thermal power plants, reduce coal consumption, control and reduce pollution emissions. In this paper, data-driven modeling and optimization of boiler combustion system in thermal power plant are studied. This paper takes Huadian-300MW unit as the research object, gives the steps of data acquisition, preprocessing, optimization index selection and neural network steady-state modeling process and its evaluation of boiler in power plant. Both reducing the relative coal consumption per unit and reducing the no _ x emissions are considered as the evaluation indexes for the optimal operation of the boiler. Modeling at two typical load disposal points. The similarities and differences of different neural network modeling training algorithms are compared and their generalization ability is evaluated. For the nonlinear dynamic industrial process of power plant boiler, a data-driven modeling method based on discrete state is discussed and studied. The steady state modeling and dynamic modeling of boiler combustion process are treated differently. The idea of combining steady-state and dynamic modeling is presented. The definition, identification method and gain calculation method of steady and dynamic processes are given. Under the condition that the feedforward neural network can only construct the steady model and the data collected in the field have dynamic characteristics, a hybrid model combining the feedforward neural network and the first order autoregressive model is presented. The existence of the first order autoregressive model enables the hybrid model to describe the dynamic characteristics, and its training algorithm is derived. The model is applied to the modeling of NOx emissions in thermal power plants and its modeling ability is evaluated. The results show that the first order autoregressive model can improve the fitting accuracy of the mixed model, which indicates that there are dynamic characteristics in the formation of nitrogen oxides. Finally, genetic algorithm is used to obtain the optimization results with the goal of reducing coal consumption and nitrogen oxides under two typical loads, and the optimization results are obtained based on the neural network model. The new optimization results are obtained after filtering the disturbance in the nitrogen oxide emission data. The optimization results based on different models are compared and analyzed. The results of calculation of the relative gain of NOx emissions are given based on the field data. Using database and dynamic web technology, the dynamic web page of the optimization result is made to guide the crew of the power plant to operate optimally.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TM621.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 孔亮;張毅;丁艷軍;吳占松;;電站鍋爐燃燒優(yōu)化控制技術(shù)綜述[J];電力設(shè)備;2006年02期

2 王軍;章正林;姜書(shū)敏;;SmartProcess燃燒優(yōu)化系統(tǒng)及其應(yīng)用[J];電力設(shè)備;2006年02期

3 張毅,丁艷軍,張鴻泉,吳占松;環(huán)保與經(jīng)濟(jì)相協(xié)調(diào)的鍋爐運(yùn)行優(yōu)化控制[J];動(dòng)力工程;2005年05期

4 趙勇綱,任潤(rùn)平,張存柱;電站鍋爐熱效率計(jì)算通用軟件制作[J];發(fā)電設(shè)備;2003年03期

5 牛擁軍;優(yōu)化燃燒技術(shù)在鄒縣電廠中的應(yīng)用[J];發(fā)電設(shè)備;2004年S1期

6 許昌;呂劍虹;鄭源;;基于效率與NO_x排放的鍋爐燃燒優(yōu)化試驗(yàn)及分析[J];鍋爐技術(shù);2006年05期

7 胡建根,黃郁明,吳煜忠;雙調(diào)風(fēng)燃燒器鍋爐燃燒參數(shù)的優(yōu)化[J];華東電力;1998年12期

8 徐軍偉,宋兆龍,王磊;電站鍋爐燃燒優(yōu)化技術(shù)現(xiàn)狀和發(fā)展動(dòng)向[J];江蘇電機(jī)工程;2005年03期

9 李軍;張宇;王紀(jì)森;;基于DRNN的非線性模型預(yù)測(cè)控制研究[J];計(jì)算機(jī)仿真;2010年08期

10 楊鵬;劉品杰;張燕;李永富;;基于RBF神經(jīng)網(wǎng)絡(luò)的改進(jìn)多變量預(yù)測(cè)控制[J];控制工程;2009年01期

，

本文編號(hào)：1881023