【摘要】：隨著我國經(jīng)濟(jì)的快速發(fā)展及城市化水平的不斷提高,城市可利用的土地資源正不斷減少,各類高層建筑正迅速崛起。由于樓層的增加,荷載的增加,其施工將給建筑物本身及周邊建筑群體帶來復(fù)雜的形變影響。其中,最常見的是導(dǎo)致其發(fā)生不均勻沉降,若沉降嚴(yán)重則將危及建筑物的安全。 變形監(jiān)測作為信息化施工的關(guān)鍵環(huán)節(jié),貫穿于建筑物設(shè)計期、施工期和運營期的整個過程,工程參建各方都對監(jiān)測工作和數(shù)據(jù)分析給予了極大的重視。近年來,為探索出一種快速有效的沉降預(yù)測的方法,許多學(xué)者從理論與實踐等多方面進(jìn)行了大量的探索與研究,并取得了一定的成效,但也存在著許多的問題與不足。本文根據(jù)建筑地基沉降的特點,以及目前在該領(lǐng)域所廣泛研討的熱點方法,將具有自學(xué)習(xí)、自組織且非線性逼近能力較好的人工神經(jīng)網(wǎng)絡(luò)模型納入建筑沉降的預(yù)測中來,以BP神經(jīng)網(wǎng)絡(luò)為基礎(chǔ),并利用小波分析等方法對傳統(tǒng)的網(wǎng)絡(luò)模型進(jìn)行了優(yōu)化改進(jìn)。通過實例工程的變形預(yù)測對傳統(tǒng)網(wǎng)絡(luò)模型與改進(jìn)模型進(jìn)行了分析與研究,并對其預(yù)測效果進(jìn)行了評價,結(jié)果比較理想。從而表明小波分析與神經(jīng)網(wǎng)絡(luò)模型結(jié)合在建筑沉降預(yù)測中是可行的,且具有廣闊的工程應(yīng)用價值。本文主要從以下幾個方面作了研究： (1)研究了BP神經(jīng)網(wǎng)絡(luò)算法。對單一的BP神經(jīng)網(wǎng)絡(luò)模型算法的局限性進(jìn)行分析,針對傳統(tǒng)網(wǎng)絡(luò)模型存在的問題,對其進(jìn)行了優(yōu)化改進(jìn),較好克服了易形成局部極小而得不到全局最優(yōu)、訓(xùn)學(xué)習(xí)效率低、收斂速度慢等問題,并將改進(jìn)模型應(yīng)用于變形預(yù)測。 (2)對小波分析進(jìn)行研究。結(jié)合MATLAB軟件探討了小波分析在信號去噪領(lǐng)域中的應(yīng)用,研究了利用小波分析實現(xiàn)信號去噪的方法,以及小波函數(shù)選取、閾值選取和小波分解、重構(gòu)等問題,合理地運用小波分析對變形監(jiān)測數(shù)據(jù)進(jìn)行去噪預(yù)處理,以求預(yù)測結(jié)果更加準(zhǔn)確。 (3)探討了小波分析和神經(jīng)網(wǎng)絡(luò)模型的結(jié)合方式。二者的結(jié)合通常有兩種式：一種是輔助式結(jié)合,也稱為松散型結(jié)合方式；另一種是嵌入式結(jié)合,也即緊致型結(jié)合方式。 (4)以BP神經(jīng)網(wǎng)絡(luò)模型為基礎(chǔ),借助MATLAB,將改進(jìn)的BP神經(jīng)網(wǎng)絡(luò)、輔助式小波神經(jīng)網(wǎng)絡(luò)和嵌入式小波神經(jīng)網(wǎng)絡(luò)模型應(yīng)用于實際工程的沉降預(yù)測當(dāng)中,通過和實測值的對比,分析比較三種模型的整體性能。結(jié)果表明,后兩種小波神經(jīng)網(wǎng)絡(luò)的組合模型精度大體相當(dāng),預(yù)測效果明顯優(yōu)于單一的BP神經(jīng)網(wǎng)絡(luò)模型。最后對本文的不足之處作了簡要的說明。
[Abstract]:With the rapid development of economy and the improvement of urbanization level, the available land resources in cities are decreasing, and various kinds of high-rise buildings are rising rapidly. Because of the increase of floor and the increase of load, the construction will bring complex deformation effect to the building itself and the surrounding buildings. Among them, the most common is to cause uneven settlement, if the settlement will endanger the safety of the building. Deformation monitoring, as a key link of information construction, runs through the whole process of building design period, construction period and operation period. All parties involved in the project pay great attention to monitoring work and data analysis. In recent years, in order to explore a rapid and effective method of settlement prediction, many scholars have made a great deal of exploration and research in theory and practice, and achieved certain results, but there are also many problems and shortcomings. In this paper, according to the characteristics of building foundation settlement and the hot methods which are widely studied in this field, the artificial neural network model with self-learning, self-organization and better nonlinear approximation ability is applied to the prediction of building settlement. Based on BP neural network and wavelet analysis, the traditional network model is optimized and improved. The traditional network model and the improved model are analyzed and studied through the deformation prediction of practical engineering, and the prediction effect is evaluated. The results are satisfactory. It shows that the combination of wavelet analysis and neural network model is feasible in building settlement prediction and has broad engineering application value. This paper mainly studies the following aspects: (1) the BP neural network algorithm is studied. The limitation of the single BP neural network model algorithm is analyzed. Aiming at the problems existing in the traditional network model, the optimization and improvement are carried out to overcome the local minima easily formed but not the global optimum, and the training and learning efficiency is low. The improved model is applied to the deformation prediction. (2) the wavelet analysis is studied. This paper discusses the application of wavelet analysis in signal denoising with MATLAB software, studies the method of signal denoising using wavelet analysis, and the selection of wavelet function, threshold selection, wavelet decomposition, reconstruction and so on. In order to obtain more accurate prediction results, wavelet analysis is used to preprocess the deformation monitoring data reasonably. (3) the combination of wavelet analysis and neural network model is discussed. There are usually two types of combination: one is auxiliary combination, also known as loose combination; the other is embedded combination, that is, compact combination. (4) based on BP neural network model, The improved BP neural network, the auxiliary wavelet neural network and the embedded wavelet neural network model are applied to the settlement prediction of practical engineering with the help of MATLAB,. The overall performance of the three models is analyzed and compared with the measured values. The results show that the combined models of the latter two kinds of wavelet neural networks have similar accuracy and the prediction effect is obviously better than that of the single BP neural network model. At last, the deficiency of this paper is briefly explained.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：TP183;TU196.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 徐培亮;大壩變形預(yù)測方法的擴(kuò)展[J];測繪學(xué)報;1987年04期

2 劉哲,郝重陽,馮偉,劉曉翔,樊養(yǎng)余;一種基于小波系數(shù)特征的遙感圖像融合算法[J];測繪學(xué)報;2004年01期

3 李波;劉明軍;張治軍;;未確知濾波法和灰色模型在大壩變形預(yù)測中的應(yīng)用[J];長江科學(xué)院院報;2011年10期

4 戴吾蛟;伍錫銹;;變形監(jiān)測中Kalman濾波狀態(tài)模型的比較分析[J];大地測量與地球動力學(xué);2009年06期

5 陶青川,鄧宏彬;基于小波變換的高斯點擴(kuò)展函數(shù)估計[J];光學(xué)技術(shù);2004年03期

6 鄭偉濤;丁嘯;;灰色與線性回歸組合模型在變形預(yù)測中的應(yīng)用研究[J];電腦與電信;2012年05期

7 白雪武;梁東偉;馬友利;;Elman神經(jīng)網(wǎng)絡(luò)在變形預(yù)報中的應(yīng)用研究[J];測繪與空間地理信息;2012年10期

8 吳云芳,李珍照,徐帆;BP神經(jīng)網(wǎng)絡(luò)在大壩安全綜合評價中的應(yīng)用[J];河海大學(xué)學(xué)報(自然科學(xué)版);2003年01期

9 蘭孝奇;楊永平;黃慶;嚴(yán)紅萍;;建筑物沉降的時間序列分析與預(yù)報[J];河海大學(xué)學(xué)報(自然科學(xué)版);2006年04期

10 艾子欣;楊維闊;;弄另水電站廠房后邊坡變形監(jiān)測與變形預(yù)測[J];黑龍江水專學(xué)報;2010年03期

，

本文編號：2229214