- 摘 要
-
(遼寧工程技術(shù)大學(xué)建筑工程學(xué)院,阜新123000)
[摘要] 近年來(lái)在役土木工程結(jié)構(gòu)的安全性越來(lái)越受到重視,而混凝土材料的長(zhǎng)期強(qiáng)度在土木工程結(jié)構(gòu)的安全性及耐久性評(píng)估中扮演中重要角色。在土木工程結(jié)構(gòu)的長(zhǎng)期服役中,混凝土的強(qiáng)度會(huì)慢慢下降。準(zhǔn)確地預(yù)測(cè)出混凝土材料在長(zhǎng)期使用過(guò)程的強(qiáng)度退化對(duì)于正確評(píng)估結(jié)構(gòu)安全性有著重要的意義。影響混凝土材料長(zhǎng)期強(qiáng)度的主要因素包括環(huán)境類別、齡期、氣候條件、水灰比、膠凝材料用量等等。本文選取具有強(qiáng)大模式識(shí)別能力的人工神經(jīng)網(wǎng)絡(luò)工具進(jìn)行混凝土長(zhǎng)期強(qiáng)度的預(yù)測(cè)研究。首先以混凝土齡期、結(jié)構(gòu)所處環(huán)境類別、水膠比以及粉煤灰用量作為神經(jīng)網(wǎng)絡(luò)輸入,以混凝土長(zhǎng)期強(qiáng)度作為網(wǎng)絡(luò)輸出建立三層BP神經(jīng)網(wǎng)絡(luò),之后用試驗(yàn)及公開文獻(xiàn)中的混凝土實(shí)測(cè)強(qiáng)度數(shù)據(jù)進(jìn)行網(wǎng)絡(luò)訓(xùn)練及測(cè)試。測(cè)試結(jié)果表明,經(jīng)過(guò)訓(xùn)練的人工神經(jīng)網(wǎng)絡(luò)能夠準(zhǔn)確地預(yù)測(cè)混凝土材料的長(zhǎng)期強(qiáng)度,其誤差控制在7%以內(nèi),可以滿足工程的需要。
[關(guān)鍵詞] 混凝土;長(zhǎng)期強(qiáng)度;人工神經(jīng)網(wǎng)絡(luò);預(yù)測(cè)
中圖分類號(hào):TU375 文獻(xiàn)標(biāo)識(shí)碼:A 文章編號(hào):1002-848X()
*國(guó)家自然科學(xué)基金資助(51008148)。
作者簡(jiǎn)介:楊曉明,博士,副教授,碩士生導(dǎo)師,主要從事結(jié)構(gòu)損傷識(shí)別及耐久性研究,Email:xiao_m_y@163.com。
Prediction of long-term strength of concrete based on artificial neural network
Yang Xiaoming, Li Fuzhai, Shi Dan
(College of Civil Engineering and Architecture, Liaoning Technical University, Fuxin 123000, China )
Abstract: Recently, the safety of existing civil engineering structures attracts more and more attention. The long-term strength of concrete plays a key role during the assessment of safety and durability for civil engineering structures. The strength of concrete will gradually decrease during the service of civil engineering structures. It is significant to accurately predict the strength deterioration of concrete for correctly evaluating the safety of structures. The factors affecting the long-term strength of concrete include environment type, age, climate, water cement ratio, amount of cementing material and so on. In this paper, artificial neural network with powerful mapping ability has been selected to predict the long-term strength of concrete. First, there-layer BP neural network with age, type of environment, water cement ratio, amount of fly ash as input and long-term strength as output was built. Then, the neural network was trained by the samples measured in real structures and the well-trained neural network was test. From the test results, the trained neural network can accurately predict the long-term strength of concrete with the error less then 7%.
Keywords: concrete; long-term strength; artificial neural network; prediction
參 考 文 獻(xiàn)
[1] 歐進(jìn)萍. 重大工程結(jié)構(gòu)智能傳感網(wǎng)絡(luò)與健康監(jiān)測(cè)系統(tǒng)的研究與應(yīng)用[J]. 中國(guó)科學(xué)基金,2005,19(1):8-12.
[2] 潘洪科,邊亞?wèn)|,楊林德. 鋼筋混凝土結(jié)構(gòu)基于耐久性劣化度的可靠性分析[J]. 建筑結(jié)構(gòu)學(xué)報(bào),2011,32(1):105-109.
[3] 程云虹,劉斌. 混凝土結(jié)構(gòu)耐久性研究現(xiàn)狀及趨勢(shì)[J]. 東北大學(xué)學(xué)報(bào),2003,24(6):600-605.
[4] 陳劍毅,胡明玉,肖燁,等. 復(fù)雜環(huán)境下礦物摻合料混凝土的耐久性研究[J]. 硅酸鹽通報(bào),2011,30(3):639-644.
[5] 張?jiān)魄?/span>,余紅發(fā),王甲春. 鋼筋混凝土構(gòu)件的抗鹽凍性能研究[J]. 硅酸鹽通報(bào),2010,29(2):345-351.
[6] 蔣思晨,李曉麗,張鵬遠(yuǎn). 不同粉煤灰摻量高強(qiáng)混合骨料混凝土力學(xué)性能及本構(gòu)關(guān)系試驗(yàn)研究[J]. 硅酸鹽通報(bào),2011,30(5):989-994.
[7] OKAN KARAHAN, HARUN TANYILDIZI, CENGIZ D ATIS. An artificial neural network approach for prediction of long-term strength properties of steel fiber reinforced concrete containing fly ash [J]. Journal of Zhejiang University(Science A:An International Applied Physics & Engineering Journal), 2008, 9(11): 1514-1523.
[8] 聶法智,王天柱,李麗霞. 混凝土后期強(qiáng)度評(píng)定的研究及應(yīng)用[J]. 粉煤灰綜合利用, 2008(1):40-42.
[9] 蘇崢. 摻粉煤灰C60泵送混凝土的配制及應(yīng)用[J]. 混凝土,1996(2):31-36.
[10] 趙勝利,劉燕. 基于RBF網(wǎng)絡(luò)的商品混凝土強(qiáng)度預(yù)測(cè)分析[J]. 計(jì)算機(jī)工程,2005,31(18):36-37.
- 下載地址
-
你還沒(méi)注冊(cè)?或者沒(méi)有登錄?這篇論文要求至少是本站的注冊(cè)會(huì)員才能閱讀!
如果你還沒(méi)注冊(cè),請(qǐng)趕緊點(diǎn)此注冊(cè)吧!
如果你已經(jīng)注冊(cè)但還沒(méi)登錄,請(qǐng)趕緊點(diǎn)此登錄吧!