本文選題：動(dòng)態(tài)可修正灰色預(yù)測(cè) + 動(dòng)態(tài)時(shí)變指數(shù)平滑預(yù)測(cè)��； 參考：《東北電力大學(xué)》2017年碩士論文

【摘要】：現(xiàn)階段對(duì)水質(zhì)預(yù)測(cè)與評(píng)價(jià)的研究已有一定成果,具有代表性的單項(xiàng)預(yù)測(cè)與評(píng)價(jià)模型被廣泛應(yīng)用于實(shí)際。但是各種單項(xiàng)預(yù)測(cè)模型分別從不同角度對(duì)樣本水質(zhì)進(jìn)行分析,會(huì)造成某些重要信息的遺缺。此外,水環(huán)境系統(tǒng)是一個(gè)動(dòng)態(tài)的復(fù)雜系統(tǒng),其相關(guān)水質(zhì)參數(shù)一直處于動(dòng)態(tài)變化之中。當(dāng)前的水質(zhì)預(yù)測(cè)與評(píng)價(jià)無法準(zhǔn)確的反映水質(zhì)的總體情況,故深入研究水質(zhì)預(yù)測(cè)與評(píng)價(jià)是十分必要與迫切的。針對(duì)所研究背景環(huán)境的復(fù)雜性,為適應(yīng)水質(zhì)變化的動(dòng)態(tài)特性,提高預(yù)測(cè)精度,結(jié)合人工智能算法在水質(zhì)智能化建模方面的較好應(yīng)用,于是提出動(dòng)態(tài)可修正灰色預(yù)測(cè)模型與動(dòng)態(tài)時(shí)變指數(shù)平滑預(yù)測(cè)模型作為研究水質(zhì)的單項(xiàng)預(yù)測(cè)模型。并將這兩種預(yù)測(cè)模型進(jìn)行組合,建立基于單項(xiàng)預(yù)測(cè)模型預(yù)測(cè)有效度的組合預(yù)測(cè)模型。該組合模型可以充分利用各單項(xiàng)模型的優(yōu)勢(shì),通過一個(gè)適當(dāng)?shù)臋?quán)重進(jìn)行組合,以單項(xiàng)模型的動(dòng)態(tài)更新來適應(yīng)水質(zhì)動(dòng)態(tài)變化的特點(diǎn)。為驗(yàn)證所建立模型的有效性,以吉林省某河段真實(shí)監(jiān)測(cè)的水質(zhì)數(shù)據(jù)為基礎(chǔ),對(duì)溶解氧、高錳酸鹽指數(shù)、氨氮、總磷、總氮五項(xiàng)水質(zhì)參數(shù)進(jìn)行水質(zhì)預(yù)測(cè)。實(shí)驗(yàn)結(jié)果表明,該組合模型與單項(xiàng)預(yù)測(cè)模型相比,其預(yù)測(cè)效果更為理想,樣本水質(zhì)的發(fā)展態(tài)勢(shì)與模型預(yù)測(cè)結(jié)果曲線的擬合性更好,在水質(zhì)預(yù)測(cè)方面具有較好的實(shí)用價(jià)值。在以上工作的基礎(chǔ)上,應(yīng)用支持向量機(jī)對(duì)相應(yīng)的水質(zhì)進(jìn)行水質(zhì)評(píng)價(jià)。介紹了支持向量機(jī)由二分類構(gòu)建多分類的方法,以及使用粒子群算法對(duì)支持向量機(jī)的相關(guān)參數(shù)進(jìn)行尋優(yōu)。實(shí)驗(yàn)結(jié)果表明,基于支持向量機(jī)的多分類應(yīng)用在水質(zhì)評(píng)價(jià)方面具有較高的分類精度。評(píng)價(jià)結(jié)果準(zhǔn)確、可靠,符合客觀實(shí)際。
[Abstract]:At present, the research on water quality prediction and evaluation has made some achievements, and the representative single prediction and evaluation model has been widely used in practice. However, a variety of single prediction models are used to analyze the sample water quality from different angles, which will lead to the absence of some important information. In addition, the water environment system is a dynamic complex system, and its water quality parameters are always changing dynamically. The current water quality prediction and evaluation can not accurately reflect the overall situation of water quality, so it is very necessary and urgent to study water quality prediction and evaluation in depth. In view of the complexity of the background environment, in order to adapt to the dynamic characteristics of water quality change and improve the prediction accuracy, combining with artificial intelligence algorithm in water quality intelligent modeling, The dynamic modifiable grey prediction model and the dynamic time-varying exponential smoothing prediction model are proposed as the single prediction models for the study of water quality. The two forecasting models are combined to establish a combined prediction model based on the prediction validity of single prediction model. The combined model can make full use of the advantages of each single model and can be combined with a proper weight to adapt to the characteristics of the dynamic change of water quality by the dynamic updating of the single model. In order to verify the validity of the established model, the water quality parameters of dissolved oxygen, permanganate index, ammonia nitrogen, total phosphorus and total nitrogen were forecasted on the basis of the water quality data of a river reach in Jilin Province. The experimental results show that the combined model is more effective than the single prediction model, and the development trend of the sample water quality is better than the curve of the model prediction results, and it has better practical value in water quality prediction. Based on the above work, support vector machine is used to evaluate the water quality. This paper introduces the method of constructing multi-classification by two-classification in support vector machine, and uses particle swarm optimization algorithm to optimize the related parameters of support vector machine. The experimental results show that the multi-classification based on support vector machine has higher classification accuracy in water quality assessment. The evaluation results are accurate, reliable and in line with the objective reality.
【學(xué)位授予單位】：東北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：X824;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳武;張山江;侯春華;陳塵;曾李晨;;二次指數(shù)平滑預(yù)測(cè)模型回歸系數(shù)計(jì)算方法探討[J];統(tǒng)計(jì)與決策;2016年19期

2 王志塏;張克峰;劉雷;;地下水污染評(píng)價(jià)中單因子指數(shù)法的優(yōu)化[J];環(huán)境工程;2016年S1期

3 曾波;孟偉;;基于灰色理論的小樣本振蕩序列區(qū)間預(yù)測(cè)建模方法[J];控制與決策;2016年07期

4 黃仁東;張海彬;楊志輝;周揚(yáng);張攀;;基于多準(zhǔn)則的組合預(yù)測(cè)模型權(quán)重研究及其應(yīng)用[J];中南大學(xué)學(xué)報(bào)(自然科學(xué)版);2015年05期

5 李龍;魏靖;黎燦兵;曹一家;宋軍英;方八零;;基于人工神經(jīng)網(wǎng)絡(luò)的負(fù)荷模型預(yù)測(cè)[J];電工技術(shù)學(xué)報(bào);2015年08期

6 徐寧;黨耀國;丁松;;基于誤差最小化的GM(1,1)模型背景值優(yōu)化方法[J];控制與決策;2015年02期

7 夏立榮;李潤學(xué);劉啟玉;耿志強(qiáng);;基于動(dòng)態(tài)層次分析的自適應(yīng)多目標(biāo)粒子群優(yōu)化算法及其應(yīng)用[J];控制與決策;2015年02期

8 呂鋒;李翔;杜文霞;;基于MultiBoost的集成支持向量機(jī)分類方法及其應(yīng)用[J];控制與決策;2015年01期

9 郝利霞;孫然好;陳利頂;;海河流域河流生態(tài)系統(tǒng)健康評(píng)價(jià)[J];環(huán)境科學(xué);2014年10期

10 孟洛明;朱杰輝;楊楊;孟玲莉;張平平;高志鵬;;支持向量機(jī)回歸預(yù)測(cè)在網(wǎng)絡(luò)故障檢測(cè)中的應(yīng)用[J];北京郵電大學(xué)學(xué)報(bào);2014年S1期

相關(guān)碩士學(xué)位論文 前2條

1 張文時(shí);基于EFDC模型的山地河流水動(dòng)力水質(zhì)模擬[D];重慶大學(xué);2014年

2 景曉林;濟(jì)南市錦繡川水庫水質(zhì)評(píng)價(jià)及風(fēng)險(xiǎn)分析[D];濟(jì)南大學(xué);2014年

，

本文編號(hào)：1784368