基于模擬退火算法的支持向量機(jī)在MBR膜污染中的應(yīng)用研究
發(fā)布時(shí)間：2019-07-02 13:27
【摘要】：膜生物反應(yīng)器(MBR)是污水處理工藝中一種重要的方式,具有處理效率高、出水水質(zhì)好、容易實(shí)現(xiàn)自動(dòng)控制等優(yōu)點(diǎn),應(yīng)用范圍不斷擴(kuò)大,規(guī)模也在逐年增加,越來(lái)越受到世界上各個(gè)國(guó)家的重視。但隨之而來(lái)的是膜污染問(wèn)題正在逐步成為阻礙MBR快速發(fā)展的一個(gè)主要因素,因?yàn)槟の廴緯?huì)直接導(dǎo)致膜通量的減小,因此如何有效的降低MBR膜污染開始成為一個(gè)熱點(diǎn)研究問(wèn)題。本文在研究了之前MBR領(lǐng)域中的各種模型的基礎(chǔ)上,針對(duì)傳統(tǒng)的神經(jīng)網(wǎng)絡(luò)模型在MBR膜污染研究中存在容易陷入局部極小值、參數(shù)難以確定的不足,閱讀并參考了大量的文獻(xiàn),提出使用模擬退火算法和支持向量機(jī)建立模型,即基于SA-SVM支持向量機(jī)的MBR膜污染預(yù)測(cè)模型。首先使用模擬退火算法對(duì)支持向量機(jī)的三個(gè)重要參數(shù)懲罰因子、不敏感系數(shù)和核參數(shù)進(jìn)行全域優(yōu)化搜索,然后將得到的最優(yōu)參數(shù)作為支持向量機(jī)的初始參數(shù)并建立MBR膜污染預(yù)測(cè)模型,最后使用主成分分析法對(duì)影響膜污染的因素進(jìn)行分析,選取主要影響因素作為模型的輸入,膜通量的大小作為輸出,進(jìn)行預(yù)測(cè)。實(shí)驗(yàn)研究表明,基于SA-SVM支持向量機(jī)的MBR膜污染預(yù)測(cè)模型在對(duì)膜通量進(jìn)行預(yù)測(cè)時(shí),有較好的擬合效果和較高的預(yù)測(cè)精確度,在穩(wěn)定性和泛化能力方面也比之前的神經(jīng)網(wǎng)絡(luò)模型也有了一定的提高。在使用模擬退火算法對(duì)MBR膜污染預(yù)測(cè)模型進(jìn)行初始參數(shù)尋優(yōu)的過(guò)程中,我們也發(fā)現(xiàn)了一些問(wèn)題,SA算法存在收斂速度慢、初始參數(shù)設(shè)置比較敏感等缺點(diǎn)。于是我們引入一種同時(shí)結(jié)合了 SA和GA算法的混合優(yōu)化算法對(duì)模型的參數(shù)進(jìn)行優(yōu)化,該算法既保留了 GA算法全局搜索能力強(qiáng)的特點(diǎn),又擁有SA算法局部尋優(yōu)的優(yōu)勢(shì)。實(shí)驗(yàn)研究表明,通過(guò)與SA-SVM模型相比較,ASAGA-SVM模型具有較高的擬合效果,平均相對(duì)誤差為0.0263,由此我們可以得出,在面對(duì)小樣本的膜通量數(shù)據(jù)時(shí),基于ASAGA-SVM的MBR膜污染預(yù)測(cè)模型比SA-SVM模型具有更好地預(yù)測(cè)精度。
[Abstract]:Membrane Bioreactor (MBR) is an important way in wastewater treatment process, which has the advantages of high treatment efficiency, good effluent quality and easy automatic control. The scope of application is expanding and the scale is increasing year by year. More and more countries in the world pay attention to it. However, the problem of membrane fouling is gradually becoming a major factor hindering the rapid development of MBR, because membrane fouling will directly lead to the reduction of membrane flux, so how to effectively reduce MBR membrane fouling began to become a hot research issue. Based on the study of various models in the field of MBR, aiming at the shortcomings of the traditional neural network model in the study of MBR membrane fouling, which is easy to fall into local minimum and difficult to determine the parameters, this paper reads and refers to a large number of literatures, and proposes to use simulated annealing algorithm and support vector machine to establish the model, that is, the prediction model of MBR membrane fouling based on SA-SVM support vector machine. Firstly, the simulated annealing algorithm is used to search the three important parameter penalty factors, insensitive coefficients and kernel parameters of support vector machine, and then the optimal parameters are taken as the initial parameters of support vector machine and the prediction model of MBR membrane fouling is established. Finally, the factors affecting membrane fouling are analyzed by principal component analysis, and the main influencing factors are selected as the input of the model and the size of membrane flux as the output. Make a prediction. The experimental results show that the MBR membrane fouling prediction model based on SA-SVM support vector machine has good fitting effect and high prediction accuracy, and also improves the stability and generalization ability of the previous neural network model. In the process of optimizing the initial parameters of MBR film fouling prediction model by simulated annealing algorithm, we also find some problems. SA algorithm has some shortcomings, such as slow convergence speed, sensitive initial parameter setting and so on. Therefore, we introduce a hybrid optimization algorithm which combines SA and GA algorithm to optimize the parameters of the model. The algorithm not only preserves the strong global search ability of GA algorithm, but also has the advantage of local optimization of SA algorithm. The experimental results show that compared with the SA-SVM model, the ASAGA-SVM model has a higher fitting effect, and the average relative error is 0.0263. It can be concluded that the MBR membrane fouling prediction model based on ASAGA-SVM has better prediction accuracy than the SA-SVM model when facing the membrane flux data of small samples.
【學(xué)位授予單位】：天津工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：X703;TP18
本文編號(hào)：2508969
[Abstract]:Membrane Bioreactor (MBR) is an important way in wastewater treatment process, which has the advantages of high treatment efficiency, good effluent quality and easy automatic control. The scope of application is expanding and the scale is increasing year by year. More and more countries in the world pay attention to it. However, the problem of membrane fouling is gradually becoming a major factor hindering the rapid development of MBR, because membrane fouling will directly lead to the reduction of membrane flux, so how to effectively reduce MBR membrane fouling began to become a hot research issue. Based on the study of various models in the field of MBR, aiming at the shortcomings of the traditional neural network model in the study of MBR membrane fouling, which is easy to fall into local minimum and difficult to determine the parameters, this paper reads and refers to a large number of literatures, and proposes to use simulated annealing algorithm and support vector machine to establish the model, that is, the prediction model of MBR membrane fouling based on SA-SVM support vector machine. Firstly, the simulated annealing algorithm is used to search the three important parameter penalty factors, insensitive coefficients and kernel parameters of support vector machine, and then the optimal parameters are taken as the initial parameters of support vector machine and the prediction model of MBR membrane fouling is established. Finally, the factors affecting membrane fouling are analyzed by principal component analysis, and the main influencing factors are selected as the input of the model and the size of membrane flux as the output. Make a prediction. The experimental results show that the MBR membrane fouling prediction model based on SA-SVM support vector machine has good fitting effect and high prediction accuracy, and also improves the stability and generalization ability of the previous neural network model. In the process of optimizing the initial parameters of MBR film fouling prediction model by simulated annealing algorithm, we also find some problems. SA algorithm has some shortcomings, such as slow convergence speed, sensitive initial parameter setting and so on. Therefore, we introduce a hybrid optimization algorithm which combines SA and GA algorithm to optimize the parameters of the model. The algorithm not only preserves the strong global search ability of GA algorithm, but also has the advantage of local optimization of SA algorithm. The experimental results show that compared with the SA-SVM model, the ASAGA-SVM model has a higher fitting effect, and the average relative error is 0.0263. It can be concluded that the MBR membrane fouling prediction model based on ASAGA-SVM has better prediction accuracy than the SA-SVM model when facing the membrane flux data of small samples.
【學(xué)位授予單位】：天津工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：X703;TP18
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 傅駿偉;張琪君;;基于BP神經(jīng)網(wǎng)絡(luò)和改進(jìn)遺傳算法的單晶硅生產(chǎn)調(diào)度算法[J];工業(yè)控制計(jì)算機(jī);2016年01期
2 楊敏;徐榮樂(lè);袁星;羅南;郁達(dá)偉;魏源送;樊耀波;;膜生物反應(yīng)器ASM-CFD耦合仿真研究進(jìn)展[J];膜科學(xué)與技術(shù);2015年06期
3 張博洋;;支持向量機(jī)理論與應(yīng)用研究綜述[J];無(wú)線互聯(lián)科技;2015年19期
4 李威威;李春青;聶敬云;王韜;;膜生物反應(yīng)器膜污染的隨機(jī)森林預(yù)測(cè)模型[J];計(jì)算機(jī)應(yīng)用;2015年S1期
5 聶敬云;李春青;李威威;王韜;;關(guān)于遺傳算法優(yōu)化的最小二乘支持向量機(jī)在MBR仿真預(yù)測(cè)中的研究[J];軟件;2015年05期
6 胡天騏;單劍鋒;宋曉濤;;基于改進(jìn)PSO-LSSVM的模擬電路診斷方法[J];計(jì)算機(jī)技術(shù)與發(fā)展;2015年06期
7 魏勝;;基于模擬退火算法支持向量機(jī)在枯水期月徑流預(yù)測(cè)中的應(yīng)用[J];水資源與水工程學(xué)報(bào);2015年02期
8 李金旭;黃悅悅;朱廣幀;;模擬退火算法及其改進(jìn)算法的研究[J];計(jì)算機(jī)光盤軟件與應(yīng)用;2014年22期
9 薛勇剛;官嵩;戴曉虎;吳冰;劉旭軍;;膜污染機(jī)制及其控制技術(shù)研究的新進(jìn)展[J];環(huán)境污染與防治;2014年09期
10 孫海濤;李仲秋;;模擬退火算法改進(jìn)BP算法的區(qū)域物流中心選址[J];計(jì)算機(jī)技術(shù)與發(fā)展;2014年09期
，本文編號(hào)：2508969
本文鏈接：http://www.sikaile.net/shengtaihuanjingbaohulunwen/2508969.html
最近更新
教材專著
