發(fā)布時(shí)間：2018-04-08 09:47

  本文選題：大氣環(huán)境　切入點(diǎn)：污染物濃度　出處：《北京交通大學(xué)》2017年碩士論文

【摘要】：隨著我國(guó)環(huán)境監(jiān)測(cè)網(wǎng)絡(luò)覆蓋面的深入,各環(huán)境監(jiān)測(cè)站點(diǎn)產(chǎn)生并積累了大量的監(jiān)測(cè)數(shù)據(jù)。這些數(shù)據(jù)目前只是用來數(shù)據(jù)查詢,數(shù)據(jù)的潛在價(jià)值還沒有挖掘出來,因此利用這些歷史數(shù)據(jù)找到大氣污染物濃度變化的趨勢(shì)和規(guī)律,并且設(shè)計(jì)開發(fā)大氣環(huán)境預(yù)測(cè)系統(tǒng)是十分有必要的。本文對(duì)大氣環(huán)境預(yù)測(cè)模型展開細(xì)致分析和探討,提出兩種大氣環(huán)境預(yù)測(cè)模型,分別針對(duì)短期(1小時(shí)到4天)和中長(zhǎng)期(4天到21天)情況下的預(yù)測(cè),并在兩種預(yù)測(cè)模型基礎(chǔ)上搭建大氣環(huán)境預(yù)測(cè)系統(tǒng),方便用戶了解未來大氣污染物濃度。本文的主要研究工作有:(1)數(shù)據(jù)獲取與數(shù)據(jù)預(yù)處理。編寫網(wǎng)絡(luò)爬蟲腳本從北京市環(huán)境保護(hù)監(jiān)測(cè)中心獲取原始數(shù)據(jù),網(wǎng)絡(luò)爬蟲腳本使用HttpClient技術(shù)實(shí)現(xiàn)模擬瀏覽器發(fā)送請(qǐng)求,使用Jsoup技術(shù)完成對(duì)網(wǎng)頁源碼信息的解析。對(duì)得到的原始數(shù)據(jù)使用數(shù)據(jù)清洗的方法,刪除超出正常范圍和相互矛盾的數(shù)據(jù),使用數(shù)據(jù)變換的方法,完成不同量級(jí)、量綱的歸一化。(2)基于多元線性回歸的短期預(yù)測(cè)模型研究。通過優(yōu)化建模方法、增加輸入因子,提出多元線性回歸優(yōu)化模型。通過實(shí)驗(yàn)對(duì)比,建模方法為逐步線性回歸,增加季節(jié)因素和其他污染物濃度兩個(gè)輸入因子,能較為準(zhǔn)確的預(yù)測(cè)未來大氣污染物濃度并且適用于大氣污染物濃度的短期預(yù)測(cè)。(3)基于遺傳神經(jīng)網(wǎng)絡(luò)的中長(zhǎng)期預(yù)測(cè)模型研究。針對(duì)傳統(tǒng)BP神經(jīng)網(wǎng)絡(luò)全局搜索能力不足、容易陷入局部最優(yōu)、訓(xùn)練速度慢等問題,提出BP神經(jīng)網(wǎng)絡(luò)與遺傳算法相結(jié)合并且將遺傳算法的交叉概率和變異概率隨適應(yīng)度的變化而變化。經(jīng)過改進(jìn)的神經(jīng)網(wǎng)絡(luò)局部尋優(yōu)能力強(qiáng)、擅長(zhǎng)全局搜索、訓(xùn)練時(shí)間短并且適用于大氣污染物濃度的中長(zhǎng)期預(yù)測(cè)。(4)大氣環(huán)境預(yù)測(cè)系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)。該系統(tǒng)使用jQuery技術(shù)和Ajax技術(shù)將監(jiān)測(cè)點(diǎn)在地圖上展示,并在對(duì)應(yīng)的監(jiān)測(cè)點(diǎn)位置顯示未來大氣污染物濃度,使用Spring MVC框架實(shí)現(xiàn)后臺(tái)架構(gòu)設(shè)計(jì),將算法模塊與系統(tǒng)功能模塊結(jié)合,完成大氣環(huán)境預(yù)測(cè)模塊快速計(jì)算和直觀顯示預(yù)測(cè)結(jié)果的功能。
[Abstract]:With the development of environmental monitoring network in China, a large number of monitoring data have been generated and accumulated in environmental monitoring stations.These data are currently used only for querying data, and the potential value of the data has not yet been mined, so use these historical data to find trends and patterns of concentration changes in atmospheric pollutants.And it is necessary to design and develop the atmospheric environment prediction system.In this paper, the atmospheric environment prediction model is analyzed and discussed in detail, and two kinds of atmospheric environment prediction models are put forward, which are respectively for short term (1 hour to 4 days) and medium and long term (4 to 21 days).Based on the two prediction models, an atmospheric environment prediction system is built to facilitate users to understand the future concentration of atmospheric pollutants.The main research work in this paper is: 1) data acquisition and data preprocessing.The web crawler script is written to obtain the original data from Beijing Environmental Protection Monitoring Center. The web crawler script uses HttpClient technology to simulate the browser to send requests, and Jsoup technology is used to complete the analysis of the web page source code information.The method of data cleaning is used to remove the data beyond the normal range and the contradictory data, and the method of data transformation is used to complete the research on the short-term prediction model based on multivariate linear regression.By optimizing modeling method and adding input factor, a multivariate linear regression optimization model is proposed.Through experimental comparison, the modeling method is stepwise linear regression, adding two input factors of seasonal factor and other pollutant concentration.It can accurately predict the future concentration of atmospheric pollutants and is suitable for short-term prediction of the concentration of atmospheric pollutants. (3) based on genetic neural network, the study of medium and long term prediction model is carried out.The traditional BP neural network has insufficient global search ability, easy to fall into local optimum and slow training speed, etc.Combining BP neural network with genetic algorithm, the crossover probability and mutation probability of genetic algorithm are changed with fitness.The improved neural network has strong local optimization ability, is good at global search, has short training time and is suitable for medium and long term prediction of atmospheric pollutant concentration.The system uses jQuery technology and Ajax technology to display the monitoring points on the map, and shows the future concentration of air pollutants in the corresponding monitoring points. The system uses the Spring MVC framework to realize the background architecture design, and combines the algorithm module with the system function module.The function of fast calculation and visual display of prediction results is completed in the atmospheric environment prediction module.
【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】：2017
【分類號(hào)】：X831;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張平;賀亮;張濤;霍培書;危才亮;妙歡;;基于GIS和BP神經(jīng)網(wǎng)絡(luò)模型的PM_(10)濃度預(yù)測(cè)與空間分布研究[J];環(huán)境科學(xué)與管理;2016年05期

2 冷建飛;高旭;朱嘉平;;多元線性回歸統(tǒng)計(jì)預(yù)測(cè)模型的應(yīng)用[J];統(tǒng)計(jì)與決策;2016年07期

3 胡秀;;數(shù)據(jù)挖掘中數(shù)據(jù)預(yù)處理的研究[J];赤峰學(xué)院學(xué)報(bào)(自然科學(xué)版);2015年05期

4 朱劍明;;航空氣象數(shù)值預(yù)報(bào)釋用系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[J];電腦知識(shí)與技術(shù);2014年30期

5 汪劍峰;葛敏敏;;論數(shù)據(jù)倉(cāng)庫(kù)的區(qū)域環(huán)境質(zhì)量預(yù)測(cè)分析系統(tǒng)[J];華章;2012年18期

6 周濤;汝小龍;;北京市霧霾天氣成因及治理措施研究[J];華北電力大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2012年02期

7 焦寶玉;陳建文;但德忠;;我國(guó)空氣自動(dòng)監(jiān)測(cè)系統(tǒng)的現(xiàn)狀與發(fā)展趨勢(shì)[J];環(huán)境保護(hù)科學(xué);2011年06期

8 丑紀(jì)范;;天氣和氣候的可預(yù)報(bào)性[J];氣象科技進(jìn)展;2011年02期

9 張新民;柴發(fā)合;王淑蘭;孫新章;韓梅;;中國(guó)酸雨研究現(xiàn)狀[J];環(huán)境科學(xué)研究;2010年05期

10 于建軍;南凱;;北京奧運(yùn)大氣環(huán)境監(jiān)測(cè)協(xié)同平臺(tái)[J];科研信息化技術(shù)與應(yīng)用;2008年02期

相關(guān)碩士學(xué)位論文 前2條

1 易加仁;基于Web GIS的大氣環(huán)境分析預(yù)測(cè)系統(tǒng)研究[D];武漢科技大學(xué);2015年

2 李琳;基于.NET海洋動(dòng)力環(huán)境預(yù)測(cè)系統(tǒng)的搭建與實(shí)現(xiàn)[D];中國(guó)海洋大學(xué);2013年

，

本文編號(hào)：1721080