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

【摘要】：隨著人類生活水平的不斷提高和科學技術的不斷進步,工業(yè)生產(chǎn)和生活造成的大氣污染愈發(fā)嚴重。近年來,霧霾天氣對人體健康產(chǎn)生了巨大威脅,而導致霧霾天氣的首要污染物就是PM2.5。因此,對PM2.5的監(jiān)測和預報研究顯得尤為重要。本文通過觀察寧波市2013至2014年全年PM2.5的日平均濃度實際觀測值變化曲線發(fā)現(xiàn),其變化趨勢大致呈周期性,且以一年為周期。因此,本文將以2013年除PM2.5實際觀測值以外的全年空氣質量指標作為樣本數(shù)據(jù),建立數(shù)學模型,對某天的PM2.5平均濃度值進行預測。文中首先對樣本數(shù)據(jù)進行歸一化處理和主成分分析(Principal Component Analysis,PCA),將實際觀測的13維數(shù)據(jù)降至6維,大大簡化了系統(tǒng)復雜度;其次將預處理后的6維數(shù)據(jù)作為輸入,PM2.5預測值作為輸出,建立多輸入單輸出ARMA模型,對空氣中PM2.5的日平均濃度進行初步預測,并通過將預測結果的殘差平方和、絕對誤差、相對誤差等作為目標函數(shù),來檢驗預測精度;由于實際問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)來構建Hammerstein模型發(fā)現(xiàn),預測精度由ARMA模型的0.3028左右提高到0.1910左右,預測效果有顯著提高。群智能優(yōu)化算法是近些年處理極值問題或優(yōu)化問題時較為先進且高效的方法,其中粒子群優(yōu)化(Particle Swarm Optimization,PSO)算法思想簡單易實現(xiàn),是進行模型辨識的首選算法。本課題中模型階數(shù)的確定和參數(shù)的估計都是較為復雜的辨識過程,利用PSO算法可以較為高效地解決這些問題。但在實際應用時發(fā)現(xiàn),傳統(tǒng)的PSO算法收斂速度較慢,且預測精度不是很高,因此本文對傳統(tǒng)PSO算法進行改進,有效地提高了收斂速度和預測精度。針對PM2.5建模的具體實現(xiàn)架構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.
【學位授予單位】：寧波大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：X513;TP18

【參考文獻】

相關期刊論文 前10條

1 鄭毅;朱成璋;;基于深度信念網(wǎng)絡的PM_(2.5)預測[J];山東大學學報(工學版);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的航天器參量預測方法[J];宇航學報;2014年11期

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

4 黃國健;陳永當;陳博敏;胡婷婷;;西安市PM_(2.5)時空分布模型研究[J];環(huán)境科學與管理;2014年09期

5 史勉;宋昭崢;楊春鵬;;基于BP模型的北京PM＿(2.5)年均值預測研究[J];電腦知識與技術;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研究[J];北京理工大學學報;2014年07期

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

8 王敏;鄒濱;郭宇;何晉強;;基于BP人工神經(jīng)網(wǎng)絡的城市PM_(2.5)濃度空間預測[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別研究[J];計算機工程與設計;2012年05期

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

相關博士學位論文 前1條

1 蔣志方;城市空氣質量預測模型與數(shù)據(jù)可視化方法研究[D];山東大學;2011年

相關碩士學位論文 前4條

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

2 秦珊珊;懸浮顆粒物PM10與PM2.5的統(tǒng)計分析與預測[D];蘭州大學;2014年

3 劉鈺;基于遺傳算法的支持向量機在空氣質量評價中的應用[D];東北財經(jīng)大學;2013年

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

，

本文編號：1660365