【摘要】：現(xiàn)如今世界經(jīng)濟(jì)發(fā)展的一個(gè)主要趨勢(shì)便是經(jīng)濟(jì)全球化。經(jīng)濟(jì)全球化不僅有助于當(dāng)下中國(guó)市場(chǎng)經(jīng)濟(jì)體制的加速組建,而且對(duì)于國(guó)內(nèi)一些企業(yè)的成長(zhǎng)及發(fā)展起到了推動(dòng)作用。當(dāng)然經(jīng)濟(jì)全球化也會(huì)給我們帶來很多挑戰(zhàn)。準(zhǔn)確把握經(jīng)濟(jì)發(fā)展的短期走勢(shì)和長(zhǎng)期趨勢(shì),為我國(guó)國(guó)民經(jīng)濟(jì)的快速發(fā)展出謀獻(xiàn)策自然變得尤為重要。由此對(duì)于那些未來事物發(fā)展情況的預(yù)測(cè)便越來越受到人們的重視。為了使經(jīng)濟(jì)決策的錯(cuò)誤降到最低,就要保證未來事物發(fā)展情況的預(yù)測(cè)高度準(zhǔn)確,以此來為經(jīng)濟(jì)決策提供可靠依據(jù)。因此準(zhǔn)確預(yù)測(cè)國(guó)內(nèi)生產(chǎn)總值(Gross Domestic Product,GDP)對(duì)政府進(jìn)行經(jīng)濟(jì)結(jié)構(gòu)調(diào)整及宏觀經(jīng)濟(jì)提供決策支撐意義重大。本文首先介紹了粒子群(Paeticle Swarm Optimization,PSO)算法,它屬于群智能優(yōu)化算法中的一種。該算法源于對(duì)鳥群覓食過程中的遷徙和聚集的模擬,它的優(yōu)點(diǎn)在于收斂速度快,同時(shí)只需要調(diào)整一些少量參數(shù),簡(jiǎn)單且易于實(shí)現(xiàn)。標(biāo)準(zhǔn)粒子群算法能夠用非常快的速率找到局部最好解,但它也有局限性,在尋找全局最優(yōu)解時(shí)往往有些遜色,易陷入局部最優(yōu)的狀態(tài)。由此針對(duì)標(biāo)準(zhǔn)粒子群算法的一些局限性進(jìn)行改進(jìn),提出了加入加速常數(shù)1c和2c,然后對(duì)比標(biāo)準(zhǔn)粒子群算法和改進(jìn)的粒子群算法分別對(duì)Ackley、Rastrigin、Rosenbrock和Schaffer函數(shù)進(jìn)行尋優(yōu)測(cè)試。實(shí)驗(yàn)結(jié)果可以看出,改進(jìn)后的粒子群算法尋找全局最優(yōu)解的能力得到明顯改善,收斂速度顯著提高,適合應(yīng)用于優(yōu)化問題的求解。其次針對(duì)靜態(tài)的前饋型BP神經(jīng)網(wǎng)絡(luò)在時(shí)序序列預(yù)測(cè)問題中精度低、不具有記憶性等問題,提出了采用動(dòng)態(tài)的、有局部記憶功能的Elman神經(jīng)網(wǎng)絡(luò)建立GDP預(yù)測(cè)模型。同時(shí)用改進(jìn)的PSO對(duì)ElmanNN的權(quán)值和閾值進(jìn)行優(yōu)化,以此來提高ElmanNN的訓(xùn)練效率。最后以安徽省為實(shí)驗(yàn)對(duì)象,詳細(xì)地分析了GDP的影響因子,在此基礎(chǔ)上建立了WCPSO優(yōu)化ElmanNN的GDP預(yù)測(cè)模型。將WCPSO優(yōu)化ElmanNN模型、ElmanNN模型和BPNN模型的預(yù)測(cè)結(jié)果分別與GDP實(shí)際數(shù)據(jù)進(jìn)行對(duì)比。結(jié)果表明,所提出的WCPSO-ElmanNN模型的預(yù)測(cè)精度相比其它兩個(gè)模型預(yù)測(cè)精度更高。
[Abstract]:Today, one of the main trends of world economic development is economic globalization. Economic globalization not only helps to accelerate the establishment of the present market economy system in China, but also promotes the growth and development of some domestic enterprises. Of course, economic globalization will also bring us a lot of challenges. It is of great importance to accurately grasp the short-term and long-term trends of economic development and to offer suggestions for the rapid development of our national economy. As a result, people pay more and more attention to the prediction of the development of those things in the future. In order to minimize the errors in economic decision-making, it is necessary to ensure that the prediction of future development is highly accurate, so as to provide a reliable basis for economic decision-making. Therefore, it is of great significance for the government to adjust its economic structure and provide decision-making support for macro-economy by accurately forecasting the gross domestic product (Gross Domestic Product,GDP). In this paper, we first introduce particle swarm optimization (Paeticle Swarm Optimization,PSO) algorithm, which belongs to one of the swarm intelligent optimization algorithms. The algorithm is derived from the simulation of migration and aggregation of birds during foraging. It has the advantage of fast convergence, and only a few parameters need to be adjusted, so it is simple and easy to realize. The standard particle swarm optimization (PSO) algorithm can find the local best solution at a very fast rate, but it also has its limitations. When searching for the global optimal solution, it is often somewhat inferior and easy to fall into the local optimal state. In view of some limitations of the standard particle swarm optimization algorithm, an acceleration constant of 1c and 2C is proposed, and then the Ackley,Rastrigin,Rosenbrock and Schaffer functions are tested by comparing the standard particle swarm optimization algorithm and the improved particle swarm optimization algorithm. The experimental results show that the ability of the improved PSO algorithm to find the global optimal solution is obviously improved, and the convergence rate is significantly increased, which is suitable for the solution of the optimization problem. Secondly, aiming at the problems such as low precision and no memory of the static feedforward BP neural network, a dynamic, local memory based Elman neural network is proposed to build the GDP prediction model. At the same time, the improved PSO is used to optimize the weight and threshold of ElmanNN in order to improve the training efficiency of ElmanNN. Finally, taking Anhui Province as the experimental object, the influence factors of GDP are analyzed in detail. On the basis of this, the GDP prediction model of WCPSO optimized ElmanNN is established. The prediction results of WCPSO optimized ElmanNN model, ElmanNN model and BPNN model are compared with the actual data of GDP respectively. The results show that the prediction accuracy of the proposed WCPSO-ElmanNN model is higher than that of the other two models.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：F124;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 范新明;曹劍中;楊洪濤;王華偉;楊磊;廖加文;王華;雷楊杰;;改進(jìn)粒子群優(yōu)化在穩(wěn)定平臺(tái)多空間分析模型的應(yīng)用[J];紅外與激光工程;2015年08期

2 索澤輝;冼軍;;Lomb-Scargle周期圖法在GDP預(yù)測(cè)中的應(yīng)用[J];統(tǒng)計(jì)與決策;2015年15期

3 原晶晶;麥雄發(fā);楊仁欣;李玲;;基于QPSO算法的模糊關(guān)系方程求解[J];廣西師范學(xué)院學(xué)報(bào)(自然科學(xué)版);2015年02期

4 劉花璐;湯濤;;湖北省GDP預(yù)測(cè)的數(shù)學(xué)模型及其影響因素分析[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2015年05期

5 孫泗龍;李少博;范辰;劉洪;;基于ARIMA的GDP預(yù)測(cè)模型的構(gòu)建及應(yīng)用[J];遼寧科技大學(xué)學(xué)報(bào);2014年04期

6 張淑紅;楊萬才;武新乾;;“十二五”時(shí)期河南省人均GDP預(yù)測(cè)[J];數(shù)理統(tǒng)計(jì)與管理;2014年03期

7 龍會(huì)典;嚴(yán)廣樂;;基于SARIMA、GM(1,1)和BP神經(jīng)網(wǎng)絡(luò)集成模型的GDP時(shí)間序列預(yù)測(cè)研究[J];數(shù)理統(tǒng)計(jì)與管理;2013年05期

8 齊麗云;何躍;;基于PMI和PPI的GDP預(yù)測(cè)模型[J];統(tǒng)計(jì)與決策;2013年16期

9 孫彩;姜明輝;;基于GP的非線性GDP預(yù)測(cè)模型的構(gòu)建與應(yīng)用[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2008年01期

10 劉穎,張智慧;中國(guó)人均GDP(1952-2002)時(shí)間序列分析[J];統(tǒng)計(jì)與決策;2005年04期

相關(guān)博士學(xué)位論文 前8條

1 朱小檬;沿海港口集裝箱吞吐量與國(guó)內(nèi)生產(chǎn)總值關(guān)聯(lián)模型研究[D];大連海事大學(xué);2014年

2 徐鶴鳴;多目標(biāo)粒子群優(yōu)化算法的研究[D];上海交通大學(xué);2013年

3 涂娟娟;PSO優(yōu)化神經(jīng)網(wǎng)絡(luò)算法的研究及其應(yīng)用[D];江蘇大學(xué);2013年

4 Atlas Khan;神經(jīng)網(wǎng)絡(luò)的優(yōu)化與用于優(yōu)化的神經(jīng)網(wǎng)絡(luò)[D];大連理工大學(xué);2013年

5 劉衍民;粒子群算法的研究及應(yīng)用[D];山東師范大學(xué);2011年

6 劉建華;粒子群算法的基本理論及其改進(jìn)研究[D];中南大學(xué);2009年

7 魏秀業(yè);基于粒子群優(yōu)化的齒輪箱智能故障診斷研究[D];中北大學(xué);2009年

8 趙志遠(yuǎn);縣域經(jīng)濟(jì)產(chǎn)業(yè)發(fā)展理論與應(yīng)用研究[D];北京交通大學(xué);2007年

相關(guān)碩士學(xué)位論文 前9條

1 詹英;組合預(yù)測(cè)方法在我國(guó)人均GDP預(yù)測(cè)中的應(yīng)用[D];華中師范大學(xué);2014年

2 單玉隆;ARIMA模型與遺傳算法優(yōu)化神經(jīng)網(wǎng)絡(luò)在GDP預(yù)測(cè)中的應(yīng)用[D];蘭州大學(xué);2014年

3 劉榮;基于Elman神經(jīng)網(wǎng)絡(luò)的短期負(fù)荷預(yù)測(cè)[D];浙江大學(xué);2013年

4 劉天舒;BP神經(jīng)網(wǎng)絡(luò)的改進(jìn)研究及應(yīng)用[D];東北農(nóng)業(yè)大學(xué);2011年

5 隨聰慧;粒子群算法的改進(jìn)方法研究[D];西南交通大學(xué);2010年

6 楊挺;基于BP神經(jīng)網(wǎng)絡(luò)改進(jìn)算法的湖南省GDP預(yù)測(cè)研究[D];中南大學(xué);2008年

7 梁軍;粒子群算法在最優(yōu)化問題中的研究[D];廣西師范大學(xué);2008年

8 劉國(guó)宏;基于人工神經(jīng)網(wǎng)絡(luò)的經(jīng)濟(jì)預(yù)測(cè)研究[D];天津大學(xué);2005年

9 吳建生;基于遺傳算法的BP神經(jīng)網(wǎng)絡(luò)氣象預(yù)報(bào)建模[D];廣西師范大學(xué);2004年

，

本文編號(hào)：2437302