本文選題：小波神經(jīng)網(wǎng)絡(luò) + 水質(zhì)評價(jià)　； 參考：《江西理工大學(xué)》2015年碩士論文

【摘要】：水資源是一種不可替代的資源。近年來,國內(nèi)外一直重視水資源的保護(hù)和治理工作。然而隨著科技和產(chǎn)業(yè)的發(fā)展,水資源的問題還是一直制約著社會(huì)和生態(tài)環(huán)境的發(fā)展。同時(shí)傳統(tǒng)的水質(zhì)評價(jià)方法面對水環(huán)境問題的復(fù)雜性和非線性缺少高效的處理效率,因此,提高水資源的保護(hù)措施刻不容緩。人工神經(jīng)網(wǎng)絡(luò)(ANN)的發(fā)展為水質(zhì)研究帶來了新的方向,目前國內(nèi)外已經(jīng)有不少關(guān)于基于人工神經(jīng)網(wǎng)絡(luò)的水質(zhì)方面的研究。本文根據(jù)前人對人工神經(jīng)網(wǎng)絡(luò)和水質(zhì)評價(jià)的研究,深入研究小波神經(jīng)網(wǎng)絡(luò)的理論、結(jié)構(gòu)和算法后,嘗試采用小波神經(jīng)網(wǎng)絡(luò)(Wavelet Neural Network,WNN)應(yīng)用于水質(zhì)評價(jià)研究。論文主要研究包括以下幾個(gè)方面:1.鑒于傳統(tǒng)水質(zhì)評價(jià)方法存在一定的局限性,利用小波神經(jīng)網(wǎng)絡(luò)收斂速度快、泛化能力好、精度高和良好非線性處理能力,提出采用小波神經(jīng)網(wǎng)絡(luò)用于水質(zhì)評價(jià)建模,把評價(jià)結(jié)果和傳統(tǒng)評價(jià)實(shí)驗(yàn)結(jié)果進(jìn)行對比,證明該想法的可行性。2.由于傳統(tǒng)小波神經(jīng)網(wǎng)絡(luò)算法,存在收斂速度慢等缺點(diǎn),因此引入自適應(yīng)學(xué)習(xí)和動(dòng)量因子,加快網(wǎng)絡(luò)學(xué)習(xí)速度,提高網(wǎng)絡(luò)的學(xué)習(xí)能力。3.由于傳統(tǒng)小波神經(jīng)網(wǎng)絡(luò)算法易陷入局部極小,將遺傳算法(Genetic Algorithm,GA)引入小波神經(jīng)網(wǎng)絡(luò)中,雖然遺傳算法具有良好的自適應(yīng)學(xué)習(xí)能力和全局搜索能力,但其收斂速度慢,因此將一種改進(jìn)的遺傳算法-自適應(yīng)遺傳算法(Adaptive Genetic Algorithm,AGA)應(yīng)用于小波神經(jīng)網(wǎng)絡(luò)的優(yōu)化研究。在遺傳算法的基礎(chǔ)上引入自適應(yīng)調(diào)整參數(shù),加快收斂速度,提高算法的性能;在創(chuàng)建水質(zhì)評價(jià)模型時(shí),先采用自適應(yīng)遺傳算法優(yōu)化WNN的初始權(quán)值、閾值、伸縮和平移參數(shù),然后將選擇好的參數(shù)作為改進(jìn)WNN的初始參數(shù)值,該方法結(jié)合了AGA算法的全局搜索能力以及自適應(yīng)動(dòng)量梯度下降法的局部搜索能力,經(jīng)過仿真結(jié)果比較研究,證明該理論的可實(shí)現(xiàn)性。4.分別對傳統(tǒng)WNN算法、改進(jìn)WNN算法和AGA算法建立基于小波神經(jīng)網(wǎng)絡(luò)的水質(zhì)評價(jià)模型,進(jìn)行仿真實(shí)驗(yàn),對實(shí)驗(yàn)結(jié)果進(jìn)行對比分析。研究結(jié)果表明:采用AGA算法的小波神經(jīng)網(wǎng)絡(luò)模型比其他方法有較大的提高,該方法可以對水環(huán)境的評價(jià)有較高的準(zhǔn)確性和有效性。最后,創(chuàng)建基于WNN的水質(zhì)評價(jià)圖形用戶界面(GUI),方便用戶的使用。
[Abstract]:Water resource is an irreplaceable resource. In recent years, domestic and international attention has been attached to the protection and management of water resources. However, with the development of science and technology and industry, the problem of water resources still restricts the development of society and ecological environment. At the same time, the traditional water quality assessment methods face the complexity of water environmental problems and lack of efficient treatment efficiency. Therefore, it is urgent to improve the protection measures of water resources. The development of artificial neural network (Ann) has brought a new direction to water quality research. At present, there have been a lot of research on water quality based on artificial neural network at home and abroad. Based on the previous researches on artificial neural network and water quality evaluation, the theory, structure and algorithm of wavelet neural network are deeply studied in this paper, and then wavelet neural network (WNN) is applied to water quality evaluation. The main research includes the following aspects: 1. In view of the limitations of traditional water quality assessment methods, wavelet neural network is used to model water quality evaluation by using wavelet neural network, which has the advantages of fast convergence, good generalization ability, high precision and good nonlinear processing ability. Compare the evaluation results with the traditional experimental results to prove the feasibility of the idea. 2. 2. Because the traditional wavelet neural network algorithm has some shortcomings such as slow convergence speed, so the adaptive learning and momentum factor are introduced to accelerate the learning speed of the network and improve the learning ability of the network. Because traditional wavelet neural network algorithm is easy to fall into local minima, genetic algorithm (GA) is introduced into wavelet neural network. Although genetic algorithm has good adaptive learning ability and global searching ability, its convergence speed is slow. Therefore, an improved genetic algorithm (Adaptive genetic algorithm) is applied to the optimization of wavelet neural networks. On the basis of genetic algorithm, adaptive adjustment parameters are introduced to accelerate the convergence speed and improve the performance of the algorithm, and the adaptive genetic algorithm is used to optimize the initial weight, threshold, scaling and translation parameters of WNN when the water quality evaluation model is created. Then the parameters are selected as the initial parameters of the improved WNN. The method combines the global search ability of the AGA algorithm and the local search ability of the adaptive momentum gradient descent method. The simulation results are compared and studied. The realizability of this theory is proved. 4. The traditional WNN algorithm, the improved WNN algorithm and the AGA algorithm are used to establish the water quality evaluation model based on the wavelet neural network, and the simulation experiments are carried out, and the experimental results are compared and analyzed. The results show that the wavelet neural network model based on AGA algorithm is more accurate and effective than other methods. Finally, the graphical user interface (GUI) for water quality evaluation based on WNN is created to facilitate the use of users.
【學(xué)位授予單位】：江西理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：X824;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙越;徐鑫;趙焱;初雪寧;;自適應(yīng)記憶遺傳算法研究[J];計(jì)算機(jī)技術(shù)與發(fā)展;2014年02期

2 牛紅惠;尚艷玲;;模糊神經(jīng)網(wǎng)絡(luò)在水質(zhì)評價(jià)中的研究[J];計(jì)算機(jī)仿真;2012年04期

3 宋雪英;金彩霞;胡曉鈞;李玉雙;李卉穎;楊繼松;;太子河流域水質(zhì)模糊綜合評價(jià)[J];巖礦測試;2011年06期

4 龐博;李玉霞;童玲;;基于灰色聚類法和模糊綜合法的水質(zhì)評價(jià)[J];環(huán)境科學(xué)與技術(shù);2011年11期

5 梁珊珊;殷健;;基于遺傳算法的改進(jìn)BP神經(jīng)網(wǎng)絡(luò)模型在水質(zhì)評價(jià)中的應(yīng)用[J];上海環(huán)境科學(xué);2007年04期

6 高廷耀;陳洪斌;夏四清;周增炎;;我國水污染控制的思考[J];給水排水;2006年05期

7 陳守煜,李亞偉;基于模糊人工神經(jīng)網(wǎng)絡(luò)識別的水質(zhì)評價(jià)模型[J];水科學(xué)進(jìn)展;2005年01期

8 吳利斌,尚士友,岳海軍,馬清艷;利用模糊神經(jīng)網(wǎng)絡(luò)對湖泊富營養(yǎng)化程度進(jìn)行評價(jià)的研究[J];內(nèi)蒙古農(nóng)業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年04期

9 陸琦,郭宗樓,姚杰;灰色神經(jīng)網(wǎng)絡(luò)模型在湖泊水質(zhì)預(yù)測中的應(yīng)用[J];農(nóng)機(jī)化研究;2004年03期

10 陳永燦,陳燕,鄭敬云,高千紅;概率神經(jīng)網(wǎng)絡(luò)水質(zhì)評價(jià)模型及其對三峽近壩水域的水質(zhì)評價(jià)分析[J];水力發(fā)電學(xué)報(bào);2004年03期

相關(guān)碩士學(xué)位論文 前2條

1 牟潔;基于神經(jīng)網(wǎng)絡(luò)和灰色系統(tǒng)的水質(zhì)預(yù)測研究[D];天津大學(xué);2010年

2 李峻;青弋江蕪湖市區(qū)段水質(zhì)評價(jià)與預(yù)測方法研究[D];合肥工業(yè)大學(xué);2008年

，

本文編號：2089424