【摘要】：巖土工程變形是工程系統(tǒng)內(nèi)部復(fù)雜力學(xué)機(jī)制的宏觀反應(yīng),蘊(yùn)含了施工過(guò)程中的力學(xué)演化信息,若能從中挖掘演化規(guī)律,利用已有的實(shí)測(cè)變形數(shù)據(jù)建模預(yù)測(cè)未來(lái)變形量,進(jìn)而反饋于原設(shè)計(jì),及時(shí)調(diào)整施工方案或采取相應(yīng)處理措施,可有效降低發(fā)生工程事故的可能性。該方法成功避開(kāi)了復(fù)雜的巖土變形機(jī)理,可作為工程信息化施工和動(dòng)態(tài)控制的有效途徑。因此,針對(duì)巖土工程的變形預(yù)測(cè)和控制研究具有重要意義。 巖土工程多以巖土體作為工程環(huán)境或工程材料,巖土體是一種非均質(zhì)的、各向異性的彈塑黏性體,加之地質(zhì)條件的復(fù)雜性,使其力學(xué)參數(shù)和力學(xué)現(xiàn)象都具有很強(qiáng)的隨機(jī)性和不確定性,導(dǎo)致巖土工程的變形預(yù)測(cè)和控制具有相當(dāng)?shù)碾y度。此外,巖土工程變形還受到工程地質(zhì)條件、場(chǎng)地環(huán)境條件、地面荷載、施工方法、施工進(jìn)度、時(shí)間和溫度等多種因素影響,使其變形序列除了具有巖土力學(xué)變化的內(nèi)在規(guī)律外,通常還帶有一定的隨機(jī)性,即可將巖土實(shí)測(cè)變形序列分解為趨勢(shì)序列和隨機(jī)序列。其中,趨勢(shì)序列體現(xiàn)了巖土工程變形的內(nèi)在規(guī)律,是變形預(yù)測(cè)的主要依據(jù)；隨機(jī)序列屬于噪聲序列,具有一定的平穩(wěn)性,若選擇人為剔除該部分信息,會(huì)降低預(yù)測(cè)結(jié)果的精度和真實(shí)性。因此,在巖土變形預(yù)測(cè)過(guò)程中,應(yīng)針對(duì)趨勢(shì)序列和隨機(jī)序列的各自特征分別建立預(yù)測(cè)模型進(jìn)行分析。 本文基于時(shí)間序列預(yù)測(cè)法理論,以巖土工程變形實(shí)測(cè)數(shù)據(jù)為基礎(chǔ)數(shù)據(jù),結(jié)合小波變換、粒子群算法優(yōu)化的最小二乘支持向量機(jī)(PSO-LSSVM)和自回歸移動(dòng)平均模型(ARMA)提出了聯(lián)合的巖土變形預(yù)測(cè)方法和模型,基本思路是：對(duì)于施工前期的變形實(shí)測(cè)數(shù)據(jù),首先利用Db4正交小波將其分解為趨勢(shì)時(shí)間序列和隨機(jī)時(shí)間序列；然后,針對(duì)趨勢(shì)時(shí)間序列,先采用相空間重構(gòu)技術(shù)進(jìn)行預(yù)處理,再建立PSO-LSSVM模型對(duì)其進(jìn)行預(yù)測(cè),針對(duì)隨機(jī)時(shí)間序列,直接利用EViews軟件中的ARMA模型對(duì)其進(jìn)行預(yù)測(cè)；最后將兩個(gè)子序列的預(yù)測(cè)值疊加作為最終預(yù)測(cè)結(jié)果。將本文方法分別用于基坑工程實(shí)例和地基工程實(shí)例的變形預(yù)測(cè)分析,充分驗(yàn)證了預(yù)測(cè)方法和模型的有效性。
[Abstract]:Geotechnical engineering deformation is the macroscopic response of the complex mechanical mechanism in the engineering system, which contains the mechanical evolution information in the construction process. If the evolution law can be excavated, the future deformation can be predicted by using the existing measured deformation data modeling, and then feedback to the original design, timely adjusting the construction scheme or taking corresponding treatment measures, it can be effective. This method successfully avoids the complicated deformation mechanism of rock and soil and can be used as an effective way for information construction and dynamic control of engineering.
Geotechnical engineering mostly uses geotechnical body as engineering environment or material. Geotechnical body is a kind of heterogeneous and anisotropic elastic-plastic viscous body. In addition, the complexity of geological conditions makes its mechanical parameters and mechanical phenomena have strong randomness and uncertainty, which makes it difficult to predict and control the deformation of geotechnical engineering. In addition, the deformation of geotechnical engineering is also affected by many factors, such as engineering geological conditions, site environment conditions, ground load, construction method, construction schedule, time and temperature, which make the deformation sequence not only have the inherent law of geomechanical changes, but also have a certain randomness, that is, the measured deformation sequence can be decomposed into trend sequence. The trend sequence reflects the inherent law of geotechnical engineering deformation and is the main basis of deformation prediction; the random sequence belongs to noise sequence and has a certain degree of stability. If this part of information is removed artificially, the accuracy and authenticity of prediction results will be reduced. The prediction model is established by analyzing the respective characteristics of trend series and random sequences.
In this paper, based on the theory of time series prediction method, a combined prediction method and model of geotechnical deformation is proposed, which is based on the measured data of geotechnical engineering deformation, combined with wavelet transform, least squares support vector machine (PSO-LSSVM) optimized by particle swarm optimization and autoregressive moving average model (ARMA). The basic idea is as follows: For the pre-construction period, the prediction method and model are combined. First, Db4 orthogonal wavelet is used to decompose the deformation data into trend time series and random time series. Then, for trend time series, phase space reconstruction technique is used to pre-process the deformation data, and then PSO-LSSVM model is established to predict the deformation data. For the random time series, the ARMA model in EViews software is directly used to advance the deformation data. Finally, the prediction values of the two subsequences are superimposed as the final prediction results. The proposed method is applied to the deformation prediction analysis of foundation pit engineering and foundation engineering respectively, which fully verifies the effectiveness of the prediction method and model.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TU43

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 曾凡永,谷東兵,宋正勛;基于小波變換的圖像壓縮方法中小波基的選取問(wèn)題探討[J];長(zhǎng)春光學(xué)精密機(jī)械學(xué)院學(xué)報(bào);2000年02期

2 王軍,杜榮忠;城市地面沉降的原因與控制研究[J];城市管理與科技;2005年03期

3 常鵬;高亞靜;張琳;李均強(qiáng);;基于EEMD與時(shí)間序列法的短期風(fēng)電場(chǎng)功率預(yù)測(cè)[J];電力科學(xué)與工程;2012年03期

4 張顯;王錫凡;;短期電價(jià)預(yù)測(cè)綜述[J];電力系統(tǒng)自動(dòng)化;2006年03期

5 張亮;元松;曾勝;;基于小波-神經(jīng)網(wǎng)絡(luò)的軟土路基沉降預(yù)測(cè)方法[J];中外公路;2006年03期

6 吳吉賢;杜海燕;張耀文;;Kalman濾波在沉降監(jiān)測(cè)數(shù)據(jù)處理中的應(yīng)用[J];高原地震;2010年01期

7 張忠苗,辛公鋒;剛?cè)峤M合樁復(fù)合地基沉降的灰色預(yù)測(cè)[J];工業(yè)建筑;2003年08期

8 李玉岐,謝康和;深基開(kāi)挖引起的基坑變形預(yù)測(cè)與研究分析[J];工業(yè)建筑;2004年09期

9 王鵬,朱小燕;基于RBF核的SVM的模型選擇及其應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2003年24期

10 王曉丹,王積勤;支持向量機(jī)訓(xùn)練和實(shí)現(xiàn)算法綜述[J];計(jì)算機(jī)工程與應(yīng)用;2004年13期

相關(guān)博士學(xué)位論文 前1條

1 張冬青;非線性非高斯時(shí)間序列預(yù)測(cè)研究[D];南京航空航天大學(xué);2008年

，

本文編號(hào)：2189821