【摘要】：隨著經(jīng)濟(jì)的不斷發(fā)展,我國在短短時(shí)間內(nèi)迅速發(fā)展成工業(yè)大國,甲醇在中國工業(yè)發(fā)展中扮演著重要角色。甲醇產(chǎn)品價(jià)格隨時(shí)間變化,具有不穩(wěn)定性和波動(dòng)性,受季節(jié)因素、月度產(chǎn)量、國家宏觀經(jīng)濟(jì)等因素的影響,受到國內(nèi)外的高度關(guān)注。傳統(tǒng)的預(yù)測(cè)方法主要基于專家經(jīng)驗(yàn)和統(tǒng)計(jì)學(xué)等方面,很難對(duì)波動(dòng)的價(jià)格進(jìn)行準(zhǔn)確有效地預(yù)測(cè)。大宗商品關(guān)乎國家戰(zhàn)略利益,經(jīng)濟(jì)的興衰,越來越多的專家投身于甲醇產(chǎn)品的預(yù)測(cè)中。針對(duì)多維因子預(yù)測(cè),本文結(jié)合了統(tǒng)計(jì)學(xué)與專家經(jīng)驗(yàn)對(duì)這些因素進(jìn)行篩選,提出一種融合網(wǎng)絡(luò)情感值和專家經(jīng)驗(yàn)值等多源數(shù)據(jù)的預(yù)測(cè)模型。首先,對(duì)歷史數(shù)據(jù)進(jìn)行預(yù)處理和相關(guān)性分析,選擇適當(dāng)預(yù)測(cè)模型對(duì)其進(jìn)行預(yù)測(cè),同時(shí)比較預(yù)測(cè)誤差,建立最優(yōu)GARCH和ARMA相結(jié)合的長期預(yù)測(cè)模型。其次,通過挖掘甲醇產(chǎn)品的相關(guān)網(wǎng)絡(luò)數(shù)據(jù)信息,對(duì)其進(jìn)行預(yù)處理、統(tǒng)計(jì)分析,構(gòu)造針對(duì)甲醇產(chǎn)品的情感詞典,獲取網(wǎng)絡(luò)數(shù)據(jù)情感值。通過長時(shí)間的預(yù)測(cè),設(shè)計(jì)各個(gè)行業(yè)的專家調(diào)查問卷,量化調(diào)查問卷并獲得專家經(jīng)驗(yàn)值。最后,結(jié)合網(wǎng)絡(luò)數(shù)據(jù)情感值和專家經(jīng)驗(yàn)值模擬新的預(yù)測(cè)模型,并且評(píng)估原模型和新模型的短期和長期預(yù)測(cè)誤差。進(jìn)一步地,基于甲醇多源數(shù)據(jù)的預(yù)測(cè),設(shè)計(jì)了交互性強(qiáng)、具有層次結(jié)構(gòu)的可視化分析系統(tǒng)。由于甲醇價(jià)格受到多維因素的影響,本系統(tǒng)采用時(shí)間序列圖來反映歷史甲醇價(jià)格走勢(shì)和情感走向,并且有效地將多維數(shù)據(jù)的預(yù)測(cè)結(jié)果進(jìn)行展示；通過動(dòng)態(tài)餅狀圖來呈現(xiàn)預(yù)測(cè)誤差；通過搜索框?qū)v史數(shù)據(jù)情感文本進(jìn)行有效的搜索；同時(shí)專家也可以通過用戶交互界面將自己的情感值、觀點(diǎn)融入到本系統(tǒng)中,通過量化數(shù)據(jù)動(dòng)態(tài)更改預(yù)測(cè)結(jié)果,顯示出融合專家經(jīng)驗(yàn)的預(yù)測(cè)值。通過動(dòng)態(tài)時(shí)間序列圖和交互技術(shù)等可視化分析技術(shù),解決數(shù)據(jù)的預(yù)測(cè)、顯示。通過實(shí)驗(yàn)跟蹤分析以及用戶使用調(diào)查,發(fā)現(xiàn)該方法提高預(yù)測(cè)準(zhǔn)確性,本系統(tǒng)具有較強(qiáng)的實(shí)用性。
[Abstract]:With the development of economy, China has developed rapidly into a large industrial country in a short time. Methanol plays an important role in the industrial development of China. The price of methanol products varies with time, which is unstable and fluctuating, which is influenced by seasonal factors, monthly output, national macroeconomic and so on, and is highly concerned at home and abroad. The traditional forecasting methods are mainly based on expert experience and statistics, so it is difficult to predict the fluctuating price accurately and effectively. Commodities are a matter of national strategic interest, economic rise and fall, more and more experts are engaged in methanol product forecast. Aiming at multidimensional factor prediction, this paper combines statistics and expert experience to screen these factors, and puts forward a prediction model which combines network emotion value with expert experience value and other multi-source data. Firstly, the preprocessing and correlation analysis of historical data are carried out, and the appropriate prediction model is selected to predict it. At the same time, the prediction error is compared, and a long-term prediction model combining optimal GARCH and ARMA is established. Secondly, through mining the related network data information of methanol product, preprocessing and statistical analysis, the emotion dictionary for methanol product is constructed, and the emotional value of network data is obtained. Through long-term prediction, the questionnaire of experts in various industries is designed, the questionnaire is quantified and the experience of experts is obtained. Finally, the new prediction model is simulated with the emotional value of network data and expert experience value, and the short-term and long-term prediction errors of the original model and the new model are evaluated. Furthermore, based on the prediction of methanol multi-source data, a visual analysis system with high interactivity and hierarchical structure is designed. Because the price of methanol is influenced by multi-dimension factors, this system adopts time series diagram to reflect the trend of historical methanol price and emotional trend, and effectively displays the forecast results of multidimensional data. The prediction error is presented by dynamic pie chart; the emotional text of historical data is searched effectively by searching box; at the same time, experts can integrate their emotional values into the system through the user interface. By changing the prediction result dynamically by quantifying data, the prediction value of fusion expert experience is shown. Dynamic time series diagram and interactive technology are used to solve the problem of data prediction and display. It is found that the method can improve the accuracy of prediction and the system has strong practicability.
【學(xué)位授予單位】：華東師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：F767

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 ;山東省2009年3季度工業(yè)用甲醇產(chǎn)品質(zhì)量監(jiān)督抽查結(jié)果[J];中國石油和化工標(biāo)準(zhǔn)與質(zhì)量;2010年01期

2 ;[J];;年期

相關(guān)重要報(bào)紙文章 前4條

1 記者 師嘯;吐哈甲醇產(chǎn)品上半年產(chǎn)銷兩旺[N];中國石油報(bào);2005年

2 范新南 徐京磐;甲醇產(chǎn)品技術(shù)交流會(huì)將開[N];中國化工報(bào);2007年

3 郭桂杰 李沖;聯(lián)洋公司發(fā)揮優(yōu)勢(shì)快速發(fā)展[N];廠長經(jīng)理日?qǐng)?bào);2001年

4 記者 呂紅麗;中潤化工國債項(xiàng)目穩(wěn)步推進(jìn)[N];盤錦日?qǐng)?bào);2006年

相關(guān)碩士學(xué)位論文 前1條

1 張霞;基于多源數(shù)據(jù)的甲醇產(chǎn)品價(jià)格預(yù)測(cè)與可視分析[D];華東師范大學(xué);2016年

，

本文編號(hào)：2217390