本文選題：BP神經(jīng)網(wǎng)絡(luò)　切入點(diǎn)：電網(wǎng)物資　出處：《華北電力大學(xué)》2014年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：隨著國(guó)家電網(wǎng)公司“三集五大’’建設(shè)的全力推進(jìn),物資集約化管理越來(lái)越受到重視,電網(wǎng)物資的一級(jí)集中采購(gòu)范圍也越來(lái)越廣,這也就意味著國(guó)家電網(wǎng)公司對(duì)各網(wǎng)省電力公司所需申報(bào)的年度物資需求計(jì)劃的要求也越來(lái)越嚴(yán)格。而現(xiàn)有的年度物資需求計(jì)劃提報(bào)信息主要還是依據(jù)項(xiàng)目資料以及人為經(jīng)驗(yàn),缺乏一定的科學(xué)依據(jù),準(zhǔn)確度也難以滿足要求,因此開(kāi)展電網(wǎng)物資的需求預(yù)測(cè)有著重要的實(shí)際意義。另外,對(duì)于電網(wǎng)物資的采購(gòu)管理來(lái)說(shuō),需求預(yù)測(cè)的開(kāi)展對(duì)合理安排物資招標(biāo)、提高資金利用率以及減少物資積壓等也有著重要的意義。 本文深入分析了電網(wǎng)物資的需求特性,按照物資的用途維度詳細(xì)闡述了項(xiàng)目類(lèi)物資以及非項(xiàng)目類(lèi)物資的需求特性,確立了以基建項(xiàng)目為單位,開(kāi)展電網(wǎng)物資需求預(yù)測(cè)的研究思路。 同時(shí),通過(guò)對(duì)現(xiàn)有的物資需求預(yù)測(cè)方法的分析比選,確定了應(yīng)用BP神經(jīng)網(wǎng)絡(luò)模型來(lái)進(jìn)行電網(wǎng)物資需求預(yù)測(cè)的思路,并詳細(xì)闡述了BP神經(jīng)網(wǎng)絡(luò)的模型結(jié)構(gòu)、學(xué)習(xí)參數(shù)選擇以及學(xué)習(xí)算法。并在對(duì)標(biāo)準(zhǔn)BP神經(jīng)網(wǎng)絡(luò)算法分析的基礎(chǔ)上,利用SCG算法以及遺傳算法分別對(duì)其訓(xùn)練算法以及初始權(quán)值、閾值的選取進(jìn)行了改進(jìn),構(gòu)建了基于改進(jìn)BP神經(jīng)網(wǎng)絡(luò)的電網(wǎng)物資需求預(yù)測(cè)模型,并給出了詳細(xì)的網(wǎng)絡(luò)設(shè)計(jì)。最后以110kV新建線路工程物資-鋼芯鋁絞線需求預(yù)測(cè)為例,進(jìn)行了實(shí)例計(jì)算,驗(yàn)證了模型的科學(xué)性和有效性,并對(duì)模型的適用性進(jìn)行了深入探討。
[Abstract]:Along with the national Power Grid Corp "three sets of five 'efforts to promote the construction, material intensive management has been paid more and more attention, the level of power supplies centralized procurement range more widely, which means that the national Power Grid Corp of the annual material demand plan each provincial power network company to declare more and more strict. But the existing annual MRP report information is mainly based on the project information and human experience, lack of scientific basis, the accuracy can not meet the requirements, so to carry out the grid material demand forecast has practical need. In addition, for the procurement management of power supplies, the demand forecast of reasonable development arrange material bidding, improve capital utilization and reduce the backlog of material also has important significance.
This paper analyzes the demand characteristics of the power grid materials, expounds the demand characteristics of items and non project materials according to the dimension of materials, and establishes the research train of thought for the prediction of power grid material demand based on infrastructure projects.
At the same time, through the analysis of the existing material demand forecasting method selection, the application of BP neural network model to forecast the demand of power grid construction ideas, and expounds the model structure of BP neural network, learning parameter selection and learning algorithms. And based on the analysis of the standard BP neural network algorithm, respectively the training algorithm and the initial weights by SCG algorithm and genetic algorithm, the threshold selection is improved, build a prediction model of grid material demand based on improved BP neural network, and gives the detailed design of the network. Finally, with the newly built 110kV line engineering materials - ACSR demand forecast for example, was calculated. Verify the scientificity and validity of the model, and the applicability of the model are discussed.

【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】：2014
【分類(lèi)號(hào)】：TP183;F274;F426.61

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉楊;任德奎;;基于灰色理論的間斷性需求備件預(yù)測(cè)方法[J];四川兵工學(xué)報(bào);2011年04期

2 韓超,車(chē)永才,王繼波;改進(jìn)的BP神經(jīng)網(wǎng)絡(luò)煤炭需求預(yù)測(cè)模型[J];遼寧工程技術(shù)大學(xué)學(xué)報(bào);2005年S1期

3 張冬;明新國(guó);趙成雷;李冬;王鵬鵬;;基于BP神經(jīng)網(wǎng)絡(luò)和設(shè)備特性的工業(yè)設(shè)備備件需求預(yù)測(cè)[J];機(jī)械設(shè)計(jì)與研究;2010年01期

4 董蒙;彭紹雄;楊雪;;主成分分析—BP神經(jīng)網(wǎng)絡(luò)在備件需求預(yù)測(cè)中的應(yīng)用[J];物流科技;2010年11期

5 韓慶田;;物資需求預(yù)測(cè)模型與應(yīng)用研究[J];價(jià)值工程;2013年21期

6 馬英華;劉輝;辛東升;;當(dāng)前形勢(shì)下鞋類(lèi)市場(chǎng)需求定量預(yù)測(cè)方法之探討[J];皮革科學(xué)與工程;2010年02期

7 韓君;梁亞民;;趨勢(shì)外推與ARMA組合的能源需求預(yù)測(cè)模型[J];蘭州商學(xué)院學(xué)報(bào);2005年06期

8 楊超;劉軍;;結(jié)合預(yù)分類(lèi)的備件需求預(yù)測(cè)與訂貨批量計(jì)算[J];物流技術(shù);2009年09期

9 沈娟;杜暉;;基于BP神經(jīng)網(wǎng)絡(luò)的MRO需求量預(yù)測(cè)模型研究[J];物流技術(shù);2010年17期

10 陳琦;馬向陽(yáng);賀敏;;備件需求量的灰色理論預(yù)測(cè)法[J];組合機(jī)床與自動(dòng)化加工技術(shù);2009年06期

，

本文編號(hào)：1637055