發(fā)布時(shí)間：2018-08-21 12:37

【摘要】：在風(fēng)洞試驗(yàn)中,馬赫數(shù)的穩(wěn)定性和快速性對(duì)風(fēng)洞流場品質(zhì)有著重要影響。為了實(shí)現(xiàn)馬赫數(shù)的精確控制,必須對(duì)馬赫數(shù)進(jìn)行快速、準(zhǔn)確的預(yù)測。風(fēng)洞試驗(yàn)積累了大量數(shù)據(jù),大數(shù)據(jù)集包含了更多的有益信息,為實(shí)現(xiàn)馬赫數(shù)的精確預(yù)測提拱了可能性,但也增加了建模的復(fù)雜度。通常高度復(fù)雜的模型會(huì)加重其在實(shí)際使用時(shí)的計(jì)算負(fù)擔(dān)。針對(duì)大數(shù)據(jù)集問題,本文將隨機(jī)森林方法應(yīng)用于風(fēng)洞馬赫數(shù)建模。隨機(jī)森林是一種集成模型建模方法,它從3方面降低模型的復(fù)雜度:產(chǎn)生多個(gè)樣本子集,減少了子模型的訓(xùn)練樣本個(gè)數(shù);具有并行集成結(jié)構(gòu),子模型可在不同的CPU上運(yùn)行,提高了運(yùn)行速度;以簡單學(xué)習(xí)算法回歸樹作為基學(xué)習(xí)機(jī),降低了子模型的復(fù)雜度。試驗(yàn)證明基于隨機(jī)森林的馬赫數(shù)預(yù)測模型能夠有效利用試驗(yàn)積累的大數(shù)據(jù),滿足工程上預(yù)測速度及精度的要求。
[Abstract]:In wind tunnel test, the stability and rapidity of Mach number have an important effect on the quality of wind tunnel flow field. In order to control Mach numbers accurately, Mach numbers must be predicted quickly and accurately. Wind tunnel experiments have accumulated a large amount of data and the big data set contains more useful information, which raises the possibility of accurate prediction of Mach numbers, but also increases the complexity of modeling. Usually, highly complex models increase the computational burden when they are actually used. For the big data set problem, this paper applies the stochastic forest method to wind tunnel Mach number modeling. Stochastic forest is an integrated model modeling method, which reduces the complexity of the model in three aspects: generating multiple subsets of samples, reducing the number of training samples of the sub-model, having a parallel integration structure, and the sub-model can be run on different CPU. The simple learning algorithm regression tree is used as the basic learning machine to reduce the complexity of the submodel. The experimental results show that the Mach number prediction model based on random forest can effectively utilize the accumulated big data and meet the requirements of engineering prediction speed and precision.
【作者單位】： 東北大學(xué)信息科學(xué)與工程學(xué)院;中國空氣動(dòng)力研究與發(fā)展中心高速空氣動(dòng)力研究所;
【基金】：國家自然科學(xué)基金(61473073,61333006)~~
【分類號(hào)】：V211.74

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 Liu Wei;Ma Xin;Li Xiao;Chen Ling;Zhang Yang;Li Xiaodong;Shang Zhiliang;Jia Zhenyuan;;High-precision pose measurement method in wind tunnels based on laser-aided vision technology[J];Chinese Journal of Aeronautics;2015年04期

2 Yan Yunju;Xi Zhuyou;Zhang Shanzhi;;Numerical simulation and transonic wind-tunnel test for elastic thin-shell structure considering fluid structure interaction[J];Chinese Journal of Aeronautics;2015年01期

3 錢衛(wèi);張桂江;劉鐘坤;;飛機(jī)全動(dòng)平尾顫振特性風(fēng)洞試驗(yàn)[J];航空學(xué)報(bào);2015年04期

4 路波;呂彬彬;羅建國;余立;楊興華;郭洪濤;曾開春;;跨聲速風(fēng)洞全模顫振試驗(yàn)技術(shù)[J];航空學(xué)報(bào);2015年04期

5 孫智偉;白俊強(qiáng);高正紅;肖春生;郝禮書;;現(xiàn)代超臨界翼型設(shè)計(jì)及其風(fēng)洞試驗(yàn)[J];航空學(xué)報(bào);2015年03期

6 郭昌輝;劉貴全;張磊;;基于回歸樹與K-最近鄰交互模型的存儲(chǔ)設(shè)備性能預(yù)測[J];南京大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年02期

7 陳湘芳;陳明;馮國富;池濤;;多變量時(shí)序回歸樹的黃瓜產(chǎn)量預(yù)測模型[J];計(jì)算機(jī)工程與設(shè)計(jì);2012年01期

【共引文獻(xiàn)】

相關(guān)期刊論文 前3條

1 王曉軍;袁平;毛志忠;杜寧;;基于隨機(jī)森林的風(fēng)洞馬赫數(shù)預(yù)測模型[J];航空學(xué)報(bào);2016年05期

2 阮輝;羅興，

本文編號(hào)：2195760