本文選題：水質(zhì)預(yù)測 + 支持向量回歸機(jī)　； 參考：《昆明理工大學(xué)》2017年碩士論文

【摘要】：水環(huán)境是全球自然生態(tài)環(huán)境中不可或缺的一部分。目前,我國愈發(fā)嚴(yán)峻的污染態(tài)勢,使水環(huán)境的保護(hù)和治理更加被重視。水質(zhì)預(yù)測是水環(huán)境研究的重要內(nèi)容,是現(xiàn)代環(huán)境科學(xué)理論研究的重要課題之一。針對洱海流域的彌苴河水質(zhì)的特點(diǎn),考慮到水環(huán)境系統(tǒng)的復(fù)雜性,提出了基于 PLS(Partial Least Squares)和 SVR(Support Vector Regression)彌苴河水質(zhì)預(yù)測模型,本文主要研究成果如下:針對主成分分析法在對水質(zhì)預(yù)測模型輸入變量提取主成分時(shí),對水質(zhì)預(yù)測模型輸出變量的解釋能力比較差而導(dǎo)致水質(zhì)預(yù)測模型預(yù)測精度下降的問題。本文采用偏最小二乘回歸法對水質(zhì)預(yù)測模型輸入變量進(jìn)行成分提取,使得提取出的成分在最大限度的解釋輸入變量的同時(shí)對輸出變量的解釋能力也達(dá)到最大。這樣,在減少水質(zhì)預(yù)測模型輸入變量的同時(shí)也提高了預(yù)測精度。針對BP神經(jīng)網(wǎng)絡(luò)(Back Propagation Nerual Network)對小樣本數(shù)據(jù)泛化能力差,模型輸出不穩(wěn)定的問題。本文采用支持向量回歸機(jī)對彌苴河水質(zhì)數(shù)據(jù)進(jìn)行非線性回歸,較好的解決了小樣本數(shù)據(jù)的訓(xùn)練學(xué)習(xí)以及預(yù)測精度的提高。針對遺傳算法的尋優(yōu)效率不高,容易陷入局部極小值的問題,本文提出了改進(jìn)型遺傳算法,動態(tài)調(diào)整交叉和變異的概率。在提高尋優(yōu)能力的同時(shí)對支持向量回歸機(jī)的初始參數(shù)進(jìn)行優(yōu)化。本文在大理州洱海水質(zhì)監(jiān)測站彌苴河水質(zhì)數(shù)據(jù)基礎(chǔ)上,將本文提出的模型應(yīng)用于彌苴河水質(zhì)預(yù)測,并和目前常用的基于PCA(Principal Component Analysis)和SVR水質(zhì)預(yù)測模型以及改進(jìn)型遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)水質(zhì)預(yù)測模型進(jìn)行對比。仿真實(shí)驗(yàn)結(jié)果表明,本文提出的水質(zhì)預(yù)測模型預(yù)測結(jié)果的準(zhǔn)確性和穩(wěn)定性相比于其他兩種模型都有了 一定的提高。
[Abstract]:Water environment is an indispensable part of the global natural ecological environment. At present, more and more serious pollution situation makes the protection and treatment of water environment more attention. Water quality prediction is an important content of water environment research and one of the important subjects of modern environmental science theory research. Considering the complexity of water environment system, the water quality prediction model of Miju River based on PLS(Partial Least Squares and SVR(Support Vector Regression is put forward according to the water quality characteristics of Miju River in Erhai River Basin. The main research results of this paper are as follows: when the principal component analysis is used to extract the principal components from the input variables of the water quality prediction model, the interpretation ability of the output variables of the water quality prediction model is relatively poor, which leads to the deterioration of the prediction accuracy of the water quality prediction model. In this paper, the partial least square regression method is used to extract the input variables of water quality prediction model, so that the extracted components can interpret the input variables as well as the output variables to the maximum extent. In this way, the input variables of water quality prediction model are reduced and the prediction accuracy is improved. In view of the problem of poor generalization ability of BP neural network back Propagation Nerual Network) to small sample data and instability of model output. In this paper, the support vector regression machine is used for nonlinear regression of water quality data of Miju River, which solves the problem of training and learning of small sample data and the improvement of prediction accuracy. Aiming at the problem that the optimization efficiency of genetic algorithm is not high and it is easy to fall into local minimum, this paper proposes an improved genetic algorithm to dynamically adjust the probability of crossover and mutation. At the same time, the initial parameters of support vector regression machine are optimized. Based on the water quality data of Miju River from Erhai River Monitoring Station in Dali Prefecture, the model presented in this paper is applied to the water quality prediction of Miju River. The model of water quality prediction based on PCA(Principal Component analysis, SVR and improved genetic algorithm is compared with BP neural network. The simulation results show that the accuracy and stability of the proposed water quality prediction model are better than those of the other two models.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：X52;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 郭婭;于革;;長江中下游典型湖泊營養(yǎng)鹽歷史變化模擬[J];湖泊科學(xué);2016年04期

2 呂蓓蓓;楊遠(yuǎn)斐;;偏最小二乘法與神經(jīng)網(wǎng)絡(luò)耦合的大壩監(jiān)測模型[J];人民黃河;2013年03期

3 武國正;徐宗學(xué);李暢游;;支持向量回歸機(jī)在水質(zhì)預(yù)測中的應(yīng)用與驗(yàn)證[J];中國農(nóng)村水利水電;2012年01期

4 于超;儲金宇;白曉華;劉偉龍;;洱海入湖河流彌苴河下游氮磷季節(jié)性變化特征及主要影響因素[J];生態(tài)學(xué)報(bào);2011年23期

5 楊桂山;馬榮華;張路;姜加虎;姚書春;張民;曾海鰲;;中國湖泊現(xiàn)狀及面臨的重大問題與保護(hù)策略[J];湖泊科學(xué);2010年06期

6 陳思;;BP神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)率參數(shù)改進(jìn)方法[J];長春師范學(xué)院學(xué)報(bào)(自然科學(xué)版);2010年02期

7 智晶;張冬梅;姜鵬飛;;基于主成分的遺傳神經(jīng)網(wǎng)絡(luò)股票指數(shù)預(yù)測研究[J];計(jì)算機(jī)工程與應(yīng)用;2009年26期

8 沈花玉;王兆霞;高成耀;秦娟;姚福彬;徐巍;;BP神經(jīng)網(wǎng)絡(luò)隱含層單元數(shù)的確定[J];天津理工大學(xué)學(xué)報(bào);2008年05期

9 宋哲;劉濤;王雪瑩;劉偉;;PLS方法應(yīng)用于T細(xì)胞表位定量構(gòu)效關(guān)系的研究[J];免疫學(xué)雜志;2007年02期

10 何宏;錢鋒;;一種新的種群數(shù)自適應(yīng)遺傳算法[J];計(jì)算機(jī)應(yīng)用研究;2006年10期

相關(guān)碩士學(xué)位論文 前1條

1 程庭莉;基于支持向量機(jī)的三峽庫區(qū)水質(zhì)預(yù)測與評價(jià)方法研究[D];重慶大學(xué);2013年

，

本文編號：1957833