發(fā)布時(shí)間：2018-03-07 01:17

  本文選題：水質(zhì)預(yù)測(cè)　切入點(diǎn)：支持向量機(jī)回歸　出處：《浙江師范大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：水質(zhì)預(yù)測(cè)是水資源管理和污染控制的基礎(chǔ)性工作,準(zhǔn)確預(yù)測(cè)水體中污染物濃度隨時(shí)間發(fā)展變化的趨勢(shì)至關(guān)重要。目前國(guó)內(nèi)外有多種水質(zhì)預(yù)測(cè)方法,但這些方法仍存在一些缺點(diǎn)。本文討論了四種水質(zhì)預(yù)測(cè)模型,分別為支持向量回歸水質(zhì)預(yù)測(cè)模型、關(guān)聯(lián)向量機(jī)水質(zhì)預(yù)測(cè)模型、極限學(xué)習(xí)機(jī)水質(zhì)預(yù)測(cè)模型以及深度信念網(wǎng)絡(luò)水質(zhì)預(yù)測(cè)模型。本文在建立支持向量回歸水質(zhì)預(yù)測(cè)模型時(shí),采用了生物地理學(xué)優(yōu)化算法確定支持向量機(jī)的控制變量,并以該水質(zhì)預(yù)測(cè)模型對(duì)PH值、溶解氧、高錳酸鹽指數(shù)和氨氮四種重要水質(zhì)指標(biāo)進(jìn)行預(yù)測(cè)。采用國(guó)家環(huán)保部發(fā)布的四川攀枝花龍洞水質(zhì)監(jiān)測(cè)時(shí)間序列數(shù)據(jù)進(jìn)行實(shí)驗(yàn),并與支持向量機(jī)的傳統(tǒng)控制變量尋優(yōu)方法進(jìn)行比較,結(jié)果表明改進(jìn)生物地理學(xué)尋優(yōu)方法建立的水質(zhì)預(yù)測(cè)模型效果較好。支持向量機(jī)水質(zhì)預(yù)測(cè)模型中存在一些問(wèn)題,如核函數(shù)必須滿足Mercer條件,支持向量的個(gè)數(shù)會(huì)隨著訓(xùn)練樣本的增加呈線性增加,且只給出確定性的預(yù)測(cè)結(jié)果,沒(méi)有概率輸出,無(wú)法估計(jì)預(yù)測(cè)的不確定性。在此基礎(chǔ)上本文提出了一種基于關(guān)聯(lián)向量機(jī)回歸的水質(zhì)時(shí)間序列預(yù)測(cè)模型,并對(duì)該模型的有效性進(jìn)行了驗(yàn)證；然后將關(guān)聯(lián)向量機(jī)回歸預(yù)測(cè)模型與支持向量機(jī)回歸預(yù)測(cè)模型進(jìn)行比較。為了比較不同核函數(shù)的預(yù)測(cè)效果,實(shí)驗(yàn)中預(yù)測(cè)模型的核函數(shù)分別采用了線性函數(shù)和高斯函數(shù),并且在應(yīng)用關(guān)聯(lián)向量機(jī)回歸預(yù)測(cè)模型時(shí)給出了置信度95%的置信區(qū)間。實(shí)驗(yàn)結(jié)果表明,關(guān)聯(lián)向量機(jī)回歸模型的預(yù)測(cè)效果不亞于支持向量機(jī)回歸模型；且在給出預(yù)測(cè)值時(shí),還能同時(shí)給出預(yù)測(cè)結(jié)果的可信程度。人工神經(jīng)網(wǎng)絡(luò)算法易出現(xiàn)過(guò)學(xué)習(xí)或欠學(xué)習(xí)、局部極小、網(wǎng)絡(luò)結(jié)構(gòu)難以確定、推廣能力差等問(wèn)題。針對(duì)水質(zhì)指標(biāo)在線監(jiān)測(cè)的特點(diǎn),提出了一種基于在線貫序極限學(xué)習(xí)機(jī)算法的水質(zhì)時(shí)間序列預(yù)測(cè)模型,并以該模型對(duì)支持向量回歸模型采用過(guò)的數(shù)據(jù)進(jìn)行實(shí)驗(yàn),對(duì)該模型的有效性進(jìn)行了驗(yàn)證。然后將在線貫序極限學(xué)習(xí)機(jī)預(yù)測(cè)模型與人工神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型進(jìn)行比較。實(shí)驗(yàn)結(jié)果表明,在線貫序極限學(xué)習(xí)機(jī)預(yù)測(cè)模型的預(yù)測(cè)效果整體上優(yōu)于人工神經(jīng)網(wǎng)絡(luò),且預(yù)測(cè)精度高,訓(xùn)練時(shí)間短。此外本文還對(duì)基于深度信念網(wǎng)絡(luò)的水質(zhì)預(yù)測(cè)模型進(jìn)行了初步探討。
[Abstract]:Water quality prediction is the basic work of water resources management and pollution control. It is very important to accurately predict the trend of pollutant concentration in water body over time. At present, there are many water quality prediction methods at home and abroad. However, there are still some shortcomings in these methods. In this paper, four water quality prediction models, namely support vector regression water quality prediction model and correlation vector machine water quality prediction model, are discussed. The water quality prediction model of extreme learning machine and the water quality prediction model of depth belief network. In this paper, the control variables of support vector machine are determined by biogeographic optimization algorithm when establishing support vector regression water quality prediction model. The water quality prediction model was used to predict four important water quality indexes, such as PH value, dissolved oxygen, permanganate index and ammonia nitrogen. The experiment was carried out using the time series data of water quality monitoring in Panzhihua Longdong, Sichuan Province, issued by the Ministry of Environmental Protection. Compared with the traditional control variable optimization method of support vector machine, the results show that the water quality prediction model established by improved biogeographic optimization method is effective, and there are some problems in the water quality prediction model of support vector machine. If the kernel function must satisfy the Mercer condition, the number of support vectors will increase linearly with the increase of the training sample, and only the deterministic prediction results will be given, and there is no probability output. It is impossible to estimate the uncertainty of prediction. On this basis, a water quality time series prediction model based on correlation vector machine regression is proposed, and the validity of the model is verified. Then the correlation vector machine regression prediction model and support vector machine regression prediction model are compared. In order to compare the prediction effect of different kernel functions, the kernel function of the prediction model adopts linear function and Gao Si function, respectively. The confidence interval of confidence degree 95% is given when applying the regression prediction model of association vector machine. The experimental results show that the prediction effect of correlation vector machine regression model is no less than that of support vector machine regression model, and when the prediction value is given, At the same time, the reliability of the prediction results can be given. The artificial neural network algorithm is prone to some problems, such as learning or underlearning, local minima, hard to determine the network structure, poor generalization ability, etc. In view of the characteristics of on-line monitoring of water quality index, A water quality time series prediction model based on online sequential limit learning machine algorithm is proposed, and the model is used to test the data used in the support vector regression model. The validity of the model is verified. Then the on-line sequential learning machine prediction model is compared with the artificial neural network prediction model. The experimental results show that, The prediction effect of on-line sequential extreme learning machine is better than that of artificial neural network on the whole, and the prediction accuracy is high and the training time is short. In addition, the water quality prediction model based on depth belief network is discussed in this paper.
【學(xué)位授予單位】：浙江師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：X832;TP181

【共引文獻(xiàn)】

中國(guó)期刊全文數(shù)據(jù)庫(kù) 前2條

1 李夕兵;范昀;蘭明;尚雪義;;基于博弈論的磷石膏充填水質(zhì)物元評(píng)價(jià)[J];科技導(dǎo)報(bào);2015年15期

2 張磊;;基于灰色動(dòng)態(tài)預(yù)測(cè)模型的清河水庫(kù)水質(zhì)預(yù)測(cè)研究[J];吉林水利;2015年11期

，

本文編號(hào)：1577320