《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 基于特征優(yōu)化和ISSA-LSTM的脫硝系統(tǒng)入口NOx濃度預(yù)測(cè)模型
基于特征優(yōu)化和ISSA-LSTM的脫硝系統(tǒng)入口NOx濃度預(yù)測(cè)模型
網(wǎng)絡(luò)安全與數(shù)據(jù)治理 4期
王淵博,金秀章
(華北電力大學(xué)控制與計(jì)算機(jī)工程學(xué)院,河北保定071003)
摘要: 針對(duì)電廠脫硝系統(tǒng)入口NOx濃度受較多因素的影響波動(dòng)較大,且CEMS檢測(cè)儀表有很大遲延難以精準(zhǔn)測(cè)量的問(wèn)題,提出了一種基于隨機(jī)森林算法(RF)和改進(jìn)麻雀搜索算法(ISSA) 優(yōu)化長(zhǎng)短時(shí)記憶神經(jīng)網(wǎng)絡(luò)(LSTM)的脫硝系統(tǒng)入口NOx濃度預(yù)測(cè)模型。首先,通過(guò)機(jī)理和相關(guān)性分析確定與SCR入口NOx質(zhì)量濃度相關(guān)的初始輔助變量,并利用RF算法對(duì)輔助變量進(jìn)行特征優(yōu)化選擇,然后通過(guò)互信息(MI)對(duì)各輔助變量與輸出變量之間進(jìn)行遲延估計(jì)并提取時(shí)序特征,并通過(guò)小波濾波對(duì)輸入變量進(jìn)行降噪處理,建立LSTM神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型。利用ISSA算法確定LSTM模型的最優(yōu)組合參數(shù),最后與傳統(tǒng)的LSSVM、RBF、BP模型的預(yù)測(cè)結(jié)果進(jìn)行對(duì)比。實(shí)驗(yàn)結(jié)果證明,特征優(yōu)化后的ISSALSTM神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型的決定系數(shù)(R2)最大,均方根誤差(RMSE)和平均絕對(duì)百分比誤差(MAPE)最小,具備很強(qiáng)的擬合和泛化能力,可以精準(zhǔn)預(yù)測(cè)脫硝系統(tǒng)入口氮氧化物的質(zhì)量濃度。
中圖分類號(hào):TP183
文獻(xiàn)標(biāo)識(shí)碼:A
DOI:10.19358/j.issn.2097-1788.2023.04.012
引用格式:王淵博,金秀章.基于特征優(yōu)化和ISSALSTM的脫硝系統(tǒng)入口NOx濃度預(yù)測(cè)模型[J].網(wǎng)絡(luò)安全與數(shù)據(jù)治理,2023,42(4):70-77,84.
Prediction model of NOx concentration at the inlet of the denitration system based on feature optimization and ISSALSTM
Wang Yuanbo,Jin Xiuzhang
(School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China)
Abstract: Aiming at the problem that the NOx concentration at the inlet of the denitrification system in power plants is greatly affected by many factors and fluctuates greatly, and the CEMS detection instruments have great delays and are difficult to accurately measure, a prediction model for the NOx concentration at the inlet of the denitrification system based on the random deep forest algorithm (RF) and the improved sparrow search algorithm (ISSA) optimized longterm and shortterm memory neural network (LSTM) was proposed. Firstly, the initial auxiliary variables related to the mass concentration of NOx at the SCR inlet were determined by mechanism and correlation analysis, and the auxiliary variables were selected for feature optimization using the RF algorithm, then the delay between each auxiliary variable and the output variables were estimated by mutual information (MI) and the timing features were extracted, and the LSTM neural network prediction model was established by denoising the input variables through wavelet filtering. The modified sparrow search algorithm was used to determine the optimal combination parameters of the LSTM model and finally contrasted with the prediction results of the traditional LSSVM, RBF and BP models. The experimental results proved that the ISSALSTM neural network prediction model after feature optimization had the largest coefficient of determination (R2) and the smallest root mean square error (RMSE) and mean absolute percentage error (MAPE), which exhibited strong fitting and generalization ability to accurately predict the mass concentration of NOx at the inlet of the denitrification system.
Key words : NOx concentration prediction;feature optimization; mutual information; sparrow search algorithm;LSTM neural network;random forest

0    引言

為了實(shí)現(xiàn)碳中和的目標(biāo),我國(guó)近年來(lái)積極推進(jìn)能源轉(zhuǎn)型,優(yōu)化能源結(jié)構(gòu)。根據(jù)國(guó)家統(tǒng)計(jì)局最新公布的數(shù)據(jù),2022年火電的裝機(jī)容量仍然占比52%左右,是我國(guó)發(fā)電領(lǐng)域中的領(lǐng)頭羊?;鹆Πl(fā)電機(jī)組的主要燃料來(lái)源是煤炭,而煤炭在燃燒過(guò)程中會(huì)產(chǎn)生大量的NOx,NOx是造成大氣污染的主要污染物之一。

當(dāng)前我國(guó)電廠常用的煙氣脫硝方法主要分為兩種,分別為選擇性催化還原(SCR)脫硝系統(tǒng)和選擇性非催化還原(SNCR)脫硝系統(tǒng)。兩種方法各有優(yōu)劣, 前者具有工藝成熟、安全穩(wěn)定且脫硝效率超過(guò)90%等優(yōu)點(diǎn),是當(dāng)前電廠煙氣脫硝技術(shù)的首選,后者由于脫硝效率低,在煙氣脫硝中一般只用作輔助手段。本文研究的燃煤電站采用SCR技術(shù)對(duì)尾部煙氣中的氮氧化物進(jìn)行脫銷處理。

由于燃煤電站鍋爐燃燒系統(tǒng)是一個(gè)具有大延遲、大慣性的非線性系統(tǒng),SCR入口NOx濃度容易受不同因素的影響而波動(dòng)較大,使得精準(zhǔn)SCR入口氮氧化物濃度的獲取變得困難,進(jìn)而很難對(duì)噴氨量進(jìn)行精準(zhǔn)的控制。噴氨量過(guò)低,脫銷效果不好,會(huì)造成NOx排放不達(dá)標(biāo);過(guò)量噴氨不但影響脫硝效率,又造成巨大的資源消耗,提高運(yùn)行成本。因此,建立精準(zhǔn)有效的脫硝系統(tǒng)SCR入口氮氧化物預(yù)測(cè)模型,不僅可以幫助脫硝系統(tǒng)精準(zhǔn)調(diào)控噴氨量,提升脫硝品質(zhì),又可以降低電廠的脫硝成本。



本文詳細(xì)內(nèi)容請(qǐng)下載:http://ihrv.cn/resource/share/2000005271




作者信息:

王淵博,金秀章

(華北電力大學(xué)控制與計(jì)算機(jī)工程學(xué)院,河北保定071003)



微信圖片_20210517164139.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。