本文選題：遺傳算法 + BP神經(jīng)網(wǎng)絡(luò)��； 參考：《河南師范大學(xué)》2015年碩士論文

【摘要】：中共中央、國(guó)務(wù)院于2015年初印發(fā)了《關(guān)于加大改革創(chuàng)新力度加快農(nóng)業(yè)現(xiàn)代化建設(shè)的若干意見(jiàn)》.意見(jiàn)指出:要不斷增強(qiáng)糧食生產(chǎn)能力.由此可以看出,糧食產(chǎn)量是衡量一個(gè)國(guó)家經(jīng)濟(jì)實(shí)力的標(biāo)準(zhǔn)之一,是保障人民群眾豐衣足食的不竭動(dòng)力,是實(shí)現(xiàn)傳統(tǒng)農(nóng)業(yè)向現(xiàn)代農(nóng)業(yè)過(guò)渡的重要保障.盡管我國(guó)的糧食產(chǎn)量年年穩(wěn)定增長(zhǎng),但我們依然面臨著很多的困難,例如:土地濫用、土地鹽堿化、天氣災(zāi)難等等,這些都是可能造成糧食減產(chǎn)的隱患因素.雖然,自古我國(guó)對(duì)于糧食危機(jī)均有相應(yīng)豐富的應(yīng)對(duì)經(jīng)驗(yàn),但相對(duì)于人口眾多、糧食消費(fèi)大、耕地資源匱乏的實(shí)際國(guó)情來(lái)說(shuō),保障農(nóng)業(yè)安全和糧食的穩(wěn)定可持續(xù)發(fā)展就成為農(nóng)業(yè)科學(xué)研究中亟待解決的問(wèn)題.因此,根據(jù)研究現(xiàn)階段糧食生產(chǎn)發(fā)展的變動(dòng)規(guī)律,并對(duì)其發(fā)展趨勢(shì)進(jìn)行預(yù)測(cè),不僅可以為我國(guó)制定糧食政策與實(shí)施糧食生產(chǎn)系統(tǒng)控制提供決策依據(jù),對(duì)保障國(guó)家糧食安全也具有重要的現(xiàn)實(shí)意義.本文首先分析了人工神經(jīng)網(wǎng)絡(luò)的概念、特性、網(wǎng)絡(luò)結(jié)構(gòu)和學(xué)習(xí)方式,在此基礎(chǔ)上深入研究了BP神經(jīng)網(wǎng)絡(luò)、RBF神經(jīng)網(wǎng)絡(luò)和GRNN神經(jīng)網(wǎng)絡(luò).在實(shí)際應(yīng)用過(guò)程中,BP神經(jīng)網(wǎng)絡(luò)存在收斂速度較慢、甚至不能收斂的問(wèn)題;初始連接權(quán)值、閾值和網(wǎng)絡(luò)結(jié)構(gòu)選擇具有隨機(jī)性,選取的初始點(diǎn)不一定具有全局性的問(wèn)題,致使網(wǎng)絡(luò)最后迭代出的結(jié)果也不一定是全局最優(yōu)的問(wèn)題.RBF神經(jīng)網(wǎng)絡(luò)存在隱含層單元通常是局部的,不能保證選擇最優(yōu)的隱層單元;隱層單元數(shù)量通常固定的,往往是通過(guò)經(jīng)驗(yàn)選擇,時(shí)間消耗大的問(wèn)題.GRNN神經(jīng)網(wǎng)絡(luò)存在徑向基函數(shù)的中心和寬度、隱含層到輸出層的連接權(quán)選取對(duì)于神經(jīng)網(wǎng)絡(luò)的函數(shù)逼近能力具有很大的影響;且常規(guī)GRNN學(xué)習(xí)規(guī)則很容易使結(jié)果收斂到局部最小,甚至根本不收斂的問(wèn)題.遺傳算法是模仿自然界生物進(jìn)化機(jī)制發(fā)展起來(lái)的隨機(jī)全局搜索和優(yōu)化方法,是一種高效、并行、全局搜索的方法,它能在搜索過(guò)程中自動(dòng)獲取和積累有關(guān)搜索空間的知識(shí),并自適應(yīng)地控制搜索過(guò)程以求得最優(yōu)解.本文引入遺傳算法對(duì)BP神經(jīng)網(wǎng)絡(luò)、RBF神經(jīng)網(wǎng)絡(luò)和GRNN神經(jīng)網(wǎng)絡(luò)進(jìn)行優(yōu)化,將優(yōu)化后的GA-BP、GA-RBF和GA-GRNN網(wǎng)絡(luò)用來(lái)預(yù)測(cè)糧食產(chǎn)量,以提高各單項(xiàng)模型的預(yù)測(cè)性能.傳統(tǒng)的組合預(yù)測(cè)方法是按照單項(xiàng)預(yù)測(cè)方法的不同而賦予不同的加權(quán)平均系數(shù),同一個(gè)單項(xiàng)預(yù)測(cè)方法在樣本區(qū)間上各個(gè)時(shí)點(diǎn)的加權(quán)平均系數(shù)是不變的.然而實(shí)際上,就同一個(gè)單項(xiàng)預(yù)測(cè)方法而言,它在不同時(shí)刻的表現(xiàn)可能不相同,即在某個(gè)時(shí)點(diǎn)上預(yù)測(cè)精度較高,而在另一時(shí)點(diǎn)上預(yù)測(cè)精度較低.因此現(xiàn)有的組合預(yù)測(cè)方法存在與現(xiàn)實(shí)不符的缺陷.基于IOWA算子的組合預(yù)測(cè)模型,通過(guò)引進(jìn)IOWA算子,對(duì)每個(gè)單項(xiàng)預(yù)測(cè)方法在樣本區(qū)間上各個(gè)時(shí)點(diǎn)的擬合精度的高低按順序賦權(quán),以誤差平方和為準(zhǔn)則建立組合預(yù)測(cè)模型,因此,本文采用基于IOWA算子的組合預(yù)測(cè)模型將GA-BP、GA-RBF、GA-GRNN單項(xiàng)預(yù)測(cè)模型的結(jié)果融合,進(jìn)一步提高預(yù)測(cè)精度.實(shí)驗(yàn)結(jié)果表明,采用本文方法可以有效提高糧食產(chǎn)量的預(yù)測(cè)精度.此外,本文在分析比較C#和MATLAB混合編程的幾種方法的優(yōu)缺點(diǎn),利用C#作為前端開(kāi)發(fā)環(huán)境,設(shè)計(jì)系統(tǒng)界面,并顯示和輸出結(jié)果;而采用MATLAB R2010a作為后端計(jì)算和圖形繪制工具進(jìn)行設(shè)計(jì)與開(kāi)發(fā),開(kāi)發(fā)了糧食產(chǎn)量預(yù)測(cè)系統(tǒng)簡(jiǎn)化糧食預(yù)測(cè)流程,有效地減少了人工計(jì)算量,具有很廣泛的應(yīng)用前景.
[Abstract]:In the Central Committee of the Communist Party of China, in early 2015, the State Council issued a number of opinions on increasing the reform and innovation to speed up the construction of agricultural modernization. Although our country's grain output is steadily increasing year by year, we still face a lot of difficulties, such as land abuse, land salinization, weather disaster and so on. These are all potential risks of grain production reduction. Although in ancient times, China has a corresponding grain crisis. Rich in coping experience, but relative to the actual situation of large population, large food consumption and lack of arable land resources, it is an urgent problem to ensure the stability and sustainable development of agricultural safety and grain. Therefore, according to the study of the changing laws of the development of grain production and development at the present stage, the development trend is previewed. In this paper, the concept, characteristics, network structure and learning methods of artificial neural network are analyzed, and the BP neural network and RBF neural network are studied in this paper. And GRNN neural network. In the practical application process, the BP neural network has a slow convergence rate and even cannot converge. The initial connection weights, threshold and network structure selection are random, and the initial points selected are not necessarily global, and the results of the last iteration of the network are not necessarily the problem of global optimal. The RBF neural network has implicit layer units which are usually local and can not guarantee the optimal selection of hidden layer units. The number of hidden layer units is usually fixed. It is often selected through experience and the time consuming problem.GRNN neural network has the center and width of radial basis function, and the connection weight of the hidden layer to the output layer is selected for the neural network. The function approximation ability has a great influence, and the regular GRNN learning rules can easily make the result converge to the local minimum and even do not converge at all. The genetic algorithm is a stochastic global search and optimization method that imitates the evolution mechanism of natural organisms. It is a efficient, parallel, global search method. It can be used in the search process. It automatically obtains and accumulates knowledge about search space and adaptively controls the search process to get the optimal solution. In this paper, the genetic algorithm is introduced to optimize the BP neural network, RBF neural network and GRNN neural network, and the optimized GA-BP, GA-RBF and GA-GRNN networks are used to pretest grain output to improve the predictability of the single model. Yes. The traditional combination forecasting method is given the different weighted mean coefficients according to the difference of single prediction method. The weighted mean coefficient of the same single prediction method at each time point in the sample interval is constant. However, in fact, it may be different at different times in terms of the same single prediction method, that is, The prediction precision is high at some point, and the prediction accuracy is low at the other point. Therefore, the existing combination prediction method has the defects that are not consistent with the reality. The combined prediction model based on the IOWA operator, by introducing the IOWA operator, gives the right to the order of the fitting accuracy of each single prediction method at each time point in the sample interval. The square sum of error is a combination prediction model. Therefore, this paper uses a combination prediction model based on IOWA operator to combine the results of GA-BP, GA-RBF, GA-GRNN single item prediction model to further improve the prediction accuracy. The experimental results show that the prediction accuracy of high grain yield can be effectively raised by this method. In addition, the analysis ratio is also analyzed in this paper. Compared with the advantages and disadvantages of several methods of C# and MATLAB, C# is used as the front-end development environment, the system interface is designed, and the results are displayed and output, while MATLAB R2010a is used as the back end calculation and drawing tool to design and develop, and the grain yield prediction system is developed to simplify the grain prediction process and effectively reduce the artificial meter. It has a wide application prospect.
【學(xué)位授予單位】：河南師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：F326.11;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 吳玉鳴,徐建華;中國(guó)糧食生產(chǎn)的多元回歸與神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)比較[J];華東師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2003年04期

2 曾勇,唐小我;幾種無(wú)偏組合預(yù)測(cè)模型的分析[J];數(shù)量經(jīng)濟(jì)技術(shù)經(jīng)濟(jì)研究;1996年11期

3 陳華友,侯定丕;基于標(biāo)準(zhǔn)差的預(yù)測(cè)有效度的組合預(yù)測(cè)模型[J];系統(tǒng)工程學(xué)報(bào);2003年03期

4 高仁祥，，張世英，劉豹;組合預(yù)測(cè)貝葉斯方法研究[J];系統(tǒng)工程學(xué)報(bào);1996年01期

5 王應(yīng)明,羅英;調(diào)和平均組合預(yù)測(cè)中的參數(shù)估計(jì)技術(shù)[J];系統(tǒng)工程與電子技術(shù);1997年10期

6 王應(yīng)明;基于相關(guān)性的組合預(yù)測(cè)方法研究[J];預(yù)測(cè);2002年02期

7 唐小我，曹長(zhǎng)修，金德運(yùn);組合預(yù)測(cè)最優(yōu)加權(quán)系數(shù)向量的進(jìn)一步研究[J];預(yù)測(cè);1994年02期

8 周傳世;非線(xiàn)性權(quán)組合預(yù)測(cè)模型及其最優(yōu)權(quán)的確定[J];預(yù)測(cè);1994年02期

相關(guān)碩士學(xué)位論文 前1條

1 李武鵬;基于AIGA-BP神經(jīng)網(wǎng)絡(luò)的糧食產(chǎn)量預(yù)測(cè)研究[D];太原理工大學(xué);2011年

本文編號(hào)：2000226