本文選題：膜生物反應(yīng)器 + Elman神經(jīng)網(wǎng)絡(luò)��； 參考：《天津工業(yè)大學(xué)》2017年碩士論文

【摘要】：膜生物反應(yīng)器(MBR)作為污水處理領(lǐng)域中的新興技術(shù),具有良好的發(fā)展前景,并且逐漸受到相關(guān)領(lǐng)域?qū)＜遗c學(xué)者的重視。然而,膜污染嚴(yán)重影響了 MBR技術(shù)的發(fā)展,如何調(diào)節(jié)系統(tǒng)運(yùn)行條件和參數(shù),減緩膜污染現(xiàn)象,以及如何建立膜污染的仿真模型已經(jīng)稱為研究熱點(diǎn)。本文旨在建立影響MBR膜污染因素與表征膜污染程度的膜通量間的非線性關(guān)系,從而完成對(duì)膜通量的預(yù)測(cè)。在建立仿真預(yù)測(cè)模型之前,需要對(duì)膜生物反應(yīng)器系統(tǒng)運(yùn)行過(guò)程中產(chǎn)生的數(shù)據(jù)進(jìn)行處理,從中提取出建模所需要的數(shù)據(jù)。隨著MBR的發(fā)展,系統(tǒng)產(chǎn)生的數(shù)據(jù)必然會(huì)越來(lái)越多,因此本文引入大數(shù)據(jù)分布式系統(tǒng)來(lái)完成對(duì)膜污染相關(guān)數(shù)據(jù)的存儲(chǔ)和處理分析。利用Hadoop常用組件建立完整的數(shù)據(jù)處理模型,并通過(guò)shell腳本完成數(shù)據(jù)的自動(dòng)處理。其中包括使用Flume組件完成數(shù)據(jù)的采集,使用MapReduce程序完成數(shù)據(jù)的清洗,使用Hive組件建立數(shù)據(jù)倉(cāng)庫(kù)并分析表中數(shù)據(jù),以及使用Sqoop組件將分析后的結(jié)果數(shù)據(jù)導(dǎo)入到關(guān)系型數(shù)據(jù)庫(kù)中。理論研究證明,神經(jīng)網(wǎng)絡(luò)能夠任意精度逼近任意連續(xù)函數(shù),能夠建立輸入與輸出之間的復(fù)雜非線性關(guān)系模型,在預(yù)測(cè)領(lǐng)域應(yīng)用比較廣泛。本文使用Elman動(dòng)態(tài)神經(jīng)網(wǎng)絡(luò)來(lái)建立仿真預(yù)測(cè)模型,它屬于局部回歸的反饋網(wǎng)絡(luò),具有關(guān)聯(lián)記憶功能,在預(yù)測(cè)精度上優(yōu)于傳統(tǒng)的BP神經(jīng)網(wǎng)絡(luò)。但是,由于Elman神經(jīng)網(wǎng)絡(luò)仍采用前饋網(wǎng)絡(luò)的梯度下降法進(jìn)行網(wǎng)絡(luò)訓(xùn)練,因此存在網(wǎng)絡(luò)訓(xùn)練速度慢、容易陷入局部極小值等缺陷,且有網(wǎng)絡(luò)權(quán)值敏感和網(wǎng)絡(luò)結(jié)構(gòu)不易確定等問(wèn)題。針對(duì)這些問(wèn)題,引入基于濃度的自適應(yīng)免疫遺傳算法來(lái)優(yōu)化Elman網(wǎng)絡(luò)模型,實(shí)現(xiàn)了動(dòng)態(tài)遞歸神經(jīng)網(wǎng)絡(luò)的自動(dòng)構(gòu)造和設(shè)計(jì)。實(shí)驗(yàn)結(jié)果表明,使用免疫遺傳算法優(yōu)化的Elman網(wǎng)絡(luò)優(yōu)于未優(yōu)化的Elman網(wǎng)絡(luò),并且在與使用傳統(tǒng)GA優(yōu)化后的模型對(duì)比后發(fā)現(xiàn),免疫遺傳算法優(yōu)化的Elman網(wǎng)絡(luò)效果更好,預(yù)測(cè)精度有很大提升,且優(yōu)化后的網(wǎng)絡(luò)預(yù)測(cè)比較穩(wěn)定。
[Abstract]:Membrane bioreactor (MBR), as a new technology in wastewater treatment, has a good prospect of development, and has been gradually paid attention to by experts and scholars in related fields. However, membrane fouling has seriously affected the development of MBR technology. How to adjust the operating conditions and parameters of the system, slow down the membrane fouling phenomenon, and how to establish the simulation model of membrane fouling has become a research hotspot. The purpose of this paper is to establish a nonlinear relationship between the factors affecting the fouling of MBR membrane and the membrane flux which characterizes the fouling degree of the membrane so as to complete the prediction of the membrane flux. Before establishing the simulation prediction model, the data generated during the operation of the membrane bioreactor system should be processed, and the data needed for modeling should be extracted from it. With the development of MBR, more and more data will be generated by the system. Therefore, big data distributed system is introduced to store and process the data related to membrane fouling. A complete data processing model is established by using Hadoop components, and the data is processed automatically by shell script. It includes using Flume component to complete data collection, using MapReduce program to complete data cleaning, using Hive component to build data warehouse and analyzing data in table, and using Sqoop component to import the analyzed result data into relational database. The theoretical study shows that the neural network can approach any continuous function with arbitrary precision and can establish a complex nonlinear relation model between input and output. It is widely used in the field of prediction. In this paper, Elman dynamic neural network is used to establish the simulation prediction model, which belongs to the feedback network of local regression and has the function of associative memory, which is superior to the traditional BP neural network in prediction accuracy. However, the Elman neural network still uses the gradient descent method of feedforward neural network to train the network, so the network training speed is slow, it is easy to fall into the local minimum, and the network weight is sensitive and the network structure is difficult to determine. To solve these problems, an adaptive immune genetic algorithm based on concentration is introduced to optimize the Elman network model, and the automatic construction and design of dynamic recurrent neural network are realized. The experimental results show that the Elman network optimized by immune genetic algorithm is superior to the unoptimized Elman network, and compared with the model optimized by traditional GA, it is found that the Elman network optimized by immune genetic algorithm is more effective. The prediction accuracy is greatly improved, and the network prediction after optimization is relatively stable.
【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;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 郭榮華;;MBR工藝在城市污水處理廠的應(yīng)用及分析[J];資源節(jié)約與環(huán)保;2015年03期

2 榮佳慧;張卿堯;韋浩;潘婧晶;任建新;曹雯雯;;膜生物反應(yīng)器研究及應(yīng)用現(xiàn)狀[J];黑龍江科技信息;2015年07期

3 何君;;膜生物反應(yīng)器在工業(yè)廢水處理中的應(yīng)用分析[J];環(huán)境與生活;2014年14期

4 尹東陽(yáng);盛義發(fā);蔣明潔;李永勝;謝曲天;;基于粗糙集理論-主成分分析的Elman神經(jīng)網(wǎng)絡(luò)短期風(fēng)速預(yù)測(cè)[J];電力系統(tǒng)保護(hù)與控制;2014年11期

5 劉爾凱;崔振東;;基于HADOOP技術(shù) 實(shí)現(xiàn)銀行歷史數(shù)據(jù)線上化研究[J];金融電子化;2014年01期

6 劉長(zhǎng)征;李威兵;;Hadoop技術(shù)在海量信息處理上的優(yōu)勢(shì)[J];黑龍江科學(xué);2013年12期

7 彭玉梅;吳歆悅;施金豆;楊平;;生物膜-膜生物反應(yīng)器廢水處理技術(shù)進(jìn)展[J];環(huán)境科學(xué)與技術(shù);2013年S1期

8 崔東文;;改進(jìn)Elman神經(jīng)網(wǎng)絡(luò)在徑流預(yù)測(cè)中的應(yīng)用[J];水利水運(yùn)工程學(xué)報(bào);2013年02期

9 朱志潔;張宏偉;韓軍;宋衛(wèi)華;;基于PCA-BP神經(jīng)網(wǎng)絡(luò)的煤與瓦斯突出預(yù)測(cè)研究[J];中國(guó)安全科學(xué)學(xué)報(bào);2013年04期

10 范舉紅;余素林;張培帥;蘭亞瓊;劉銳;陳呂軍;;膜生物反應(yīng)器處理工業(yè)廢水中膜污染及膜過(guò)濾特性研究[J];環(huán)境科學(xué);2013年03期

相關(guān)博士學(xué)位論文 前6條

1 鄭a睿;基于免疫遺傳算法的鋼筋混凝土框剪結(jié)構(gòu)優(yōu)化研究[D];上海大學(xué);2015年

2 林文輝;基于Hadoop的海量網(wǎng)絡(luò)數(shù)據(jù)處理平臺(tái)的關(guān)鍵技術(shù)研究[D];北京郵電大學(xué);2014年

3 舒萬(wàn)能;人工免疫算法的優(yōu)化及其關(guān)鍵問(wèn)題研究[D];武漢大學(xué);2013年

4 吳建輝;混合免疫優(yōu)化理論與算法及其應(yīng)用研究[D];湖南大學(xué);2013年

5 李辰;一體式膜生物反應(yīng)器系統(tǒng)優(yōu)化及脫氮性能研究[D];西安建筑科技大學(xué);2010年

6 馬佳;改進(jìn)免疫遺傳算法及其在優(yōu)化調(diào)度問(wèn)題中的應(yīng)用研究[D];東北大學(xué);2008年

相關(guān)碩士學(xué)位論文 前5條

1 何向婷;基于免疫遺傳算法的多目標(biāo)優(yōu)化研究[D];西安科技大學(xué);2013年

2 張玉潔;外置式動(dòng)態(tài)膜生物反應(yīng)器處理廢水研究[D];河南工業(yè)大學(xué);2012年

3 李鳳萍;幾類人工免疫算法及其應(yīng)用研究[D];吉林大學(xué);2009年

4 劉憲寅;基于免疫遺傳算法的工程項(xiàng)目多目標(biāo)優(yōu)化研究[D];天津大學(xué);2008年

5 韓旭明;Elman神經(jīng)網(wǎng)絡(luò)的應(yīng)用研究[D];天津大學(xué);2006年

，

本文編號(hào)：1849006