本文選題：PM2.5　切入點(diǎn)：Hammerstein模型　出處：《寧波大學(xué)》2017年碩士論文

【摘要】：隨著人類(lèi)生活水平的不斷提高和科學(xué)技術(shù)的不斷進(jìn)步,工業(yè)生產(chǎn)和生活造成的大氣污染愈發(fā)嚴(yán)重。近年來(lái),霧霾天氣對(duì)人體健康產(chǎn)生了巨大威脅,而導(dǎo)致霧霾天氣的首要污染物就是PM2.5。因此,對(duì)PM2.5的監(jiān)測(cè)和預(yù)報(bào)研究顯得尤為重要。本文通過(guò)觀察寧波市2013至2014年全年P(guān)M2.5的日平均濃度實(shí)際觀測(cè)值變化曲線發(fā)現(xiàn),其變化趨勢(shì)大致呈周期性,且以一年為周期。因此,本文將以2013年除PM2.5實(shí)際觀測(cè)值以外的全年空氣質(zhì)量指標(biāo)作為樣本數(shù)據(jù),建立數(shù)學(xué)模型,對(duì)某天的PM2.5平均濃度值進(jìn)行預(yù)測(cè)。文中首先對(duì)樣本數(shù)據(jù)進(jìn)行歸一化處理和主成分分析(Principal Component Analysis,PCA),將實(shí)際觀測(cè)的13維數(shù)據(jù)降至6維,大大簡(jiǎn)化了系統(tǒng)復(fù)雜度;其次將預(yù)處理后的6維數(shù)據(jù)作為輸入,PM2.5預(yù)測(cè)值作為輸出,建立多輸入單輸出ARMA模型,對(duì)空氣中PM2.5的日平均濃度進(jìn)行初步預(yù)測(cè),并通過(guò)將預(yù)測(cè)結(jié)果的殘差平方和、絕對(duì)誤差、相對(duì)誤差等作為目標(biāo)函數(shù),來(lái)檢驗(yàn)預(yù)測(cè)精度;由于實(shí)際問(wèn)題通常具有非線性特性,嘗試將ARMA模型的輸入中加入非線性環(huán)節(jié)來(lái)構(gòu)建Hammerstein模型發(fā)現(xiàn),預(yù)測(cè)精度由ARMA模型的0.3028左右提高到0.1910左右,預(yù)測(cè)效果有顯著提高。群智能優(yōu)化算法是近些年處理極值問(wèn)題或優(yōu)化問(wèn)題時(shí)較為先進(jìn)且高效的方法,其中粒子群優(yōu)化(Particle Swarm Optimization,PSO)算法思想簡(jiǎn)單易實(shí)現(xiàn),是進(jìn)行模型辨識(shí)的首選算法。本課題中模型階數(shù)的確定和參數(shù)的估計(jì)都是較為復(fù)雜的辨識(shí)過(guò)程,利用PSO算法可以較為高效地解決這些問(wèn)題。但在實(shí)際應(yīng)用時(shí)發(fā)現(xiàn),傳統(tǒng)的PSO算法收斂速度較慢,且預(yù)測(cè)精度不是很高,因此本文對(duì)傳統(tǒng)PSO算法進(jìn)行改進(jìn),有效地提高了收斂速度和預(yù)測(cè)精度。針對(duì)PM2.5建模的具體實(shí)現(xiàn)架構(gòu)和思想是本文的新意所在。
[Abstract]:With the continuous improvement of human living standard and the progress of science and technology, the air pollution caused by industrial production and living is becoming more and more serious. In recent years, haze weather has posed a great threat to human health. PM2.5is the main pollutant causing haze weather. Therefore, it is very important to study the monitoring and forecasting of PM2.5. By observing the daily average concentration of PM2.5 in Ningbo from 2013 to 2014, it is found that, The variation trend is generally periodic and takes one year as the cycle. Therefore, the annual air quality index, other than the actual PM2.5 observations, will be taken as the sample data in this paper, and the mathematical model will be established. The average concentration of PM2.5 is predicted. Firstly, the sample data are normalized and principal component analysis (PCA) is used to reduce the observed 13 dimensional data to 6 dimension, which greatly simplifies the system complexity. Secondly, the pretreated 6-D data is taken as the input PM2.5 prediction value as the output, and the multi-input single-output ARMA model is established. The daily average concentration of PM2.5 in air is preliminarily predicted, and the absolute error is calculated by the sum of squared residuals of the predicted results. The relative error is used as the objective function to test the prediction accuracy. Because the practical problems are usually nonlinear, the nonlinear link is added to the input of the ARMA model to construct the Hammerstein model. The prediction accuracy is increased from about 0.3028 to 0.1910 of ARMA model, and the prediction effect is improved significantly. Swarm intelligence optimization algorithm is an advanced and efficient method in dealing with extreme value problem or optimization problem in recent years. Particle Swarm Optimization (PSO) algorithm is simple and easy to realize, and is the first choice for model identification. In this paper, the determination of model order and the estimation of parameters are more complex identification processes. These problems can be solved efficiently by using PSO algorithm, but in practical application, it is found that the convergence speed of traditional PSO algorithm is slow and the prediction accuracy is not very high. Therefore, the traditional PSO algorithm is improved in this paper. The convergence speed and prediction accuracy are improved effectively. The concrete implementation framework and idea of PM2.5 modeling is the new idea of this paper.
【學(xué)位授予單位】：寧波大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：X513;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鄭毅;朱成璋;;基于深度信念網(wǎng)絡(luò)的PM_(2.5)預(yù)測(cè)[J];山東大學(xué)學(xué)報(bào)(工學(xué)版);2014年06期

2 顧勝;魏蛟龍;皮德常;;一種粒子群模糊支持向量機(jī)的航天器參量預(yù)測(cè)方法[J];宇航學(xué)報(bào);2014年11期

3 彭斯俊;沈加超;朱雪;;基于ARIMA模型的PM_(2.5)預(yù)測(cè)[J];安全與環(huán)境工程;2014年06期

4 黃國(guó)健;陳永當(dāng);陳博敏;胡婷婷;;西安市PM_(2.5)時(shí)空分布模型研究[J];環(huán)境科學(xué)與管理;2014年09期

5 史勉;宋昭崢;楊春鵬;;基于BP模型的北京PM＿(2.5)年均值預(yù)測(cè)研究[J];電腦知識(shí)與技術(shù);2014年25期

6 谷文成;柴寶仁;滕艷平;;基于粒子群優(yōu)化算法的支持向量機(jī)研究[J];北京理工大學(xué)學(xué)報(bào);2014年07期

7 張藝耀;苗冠鴻;閆劍詩(shī);王景麗;王哲琪;王德輝;;影響PM2.5因素的多元統(tǒng)計(jì)分析與預(yù)測(cè)[J];資源節(jié)約與環(huán)保;2013年11期

8 王敏;鄒濱;郭宇;何晉強(qiáng);;基于BP人工神經(jīng)網(wǎng)絡(luò)的城市PM_(2.5)濃度空間預(yù)測(cè)[J];環(huán)境污染與防治;2013年09期

9 郭冬冬;夏筱筠;;基于主分量分析的缺陷識(shí)別研究[J];計(jì)算機(jī)工程與設(shè)計(jì);2012年05期

10 林衛(wèi)星;陳炎海;;一種快速收斂的改進(jìn)粒子群優(yōu)化算法[J];系統(tǒng)仿真學(xué)報(bào);2011年11期

相關(guān)博士學(xué)位論文 前1條

1 蔣志方;城市空氣質(zhì)量預(yù)測(cè)模型與數(shù)據(jù)可視化方法研究[D];山東大學(xué);2011年

相關(guān)碩士學(xué)位論文 前4條

1 陳艷華;基于人工智能優(yōu)化的支持向量機(jī)算法研究和應(yīng)用[D];蘭州大學(xué);2014年

2 秦珊珊;懸浮顆粒物PM10與PM2.5的統(tǒng)計(jì)分析與預(yù)測(cè)[D];蘭州大學(xué);2014年

3 劉鈺;基于遺傳算法的支持向量機(jī)在空氣質(zhì)量評(píng)價(jià)中的應(yīng)用[D];東北財(cái)經(jīng)大學(xué);2013年

4 朱憲春;上海市可吸入顆粒物（PM_(10)）預(yù)報(bào)方法的研究與比較[D];華東師范大學(xué);2012年

，

本文編號(hào)：1660365